{"podcast":{"title":"Daily Paper Cast","slug":"daily-paper-cast-7079649","podcast_index_feed_id":7079649,"rss_url":"https://feeds.transistor.fm/daily-paper-cast-ai","website_url":"https://dailypapercast.transistor.fm/","image_url":"https://img.transistorcdn.com/IxaBeiMluxrMS9W9wB8hFMfmvH27KvwaSMzuhucupn0/rs:fill:0:0:1/w:1400/h:1400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS81Zjg1/YzRhODczMDU4MmE4/OGMwN2FiNDlmYzI2/MDliMi5qcGVn.jpg","author":"Jingwen Liang, Gengyu Wang","episode_count":2000,"summary":"We update every weekday to discuss highest-voted papers from Huggingface Daily Paper (https://huggingface.co/papers). Both the podcast scripts and audio are generated by AI. Feedback and suggestions are welcome! Email us: dailypapercast.ai@gmail.com Creator: Jingwen Liang, 3D ML, https://www.linkedin.com/in/jingwen-liang/ Gengyu Wang, LLM ML, http://wanggengyu.com Listen on: Spotify: https://open.spotify.com/show/21nrhmdaA8qoBiH8q03NXL Apple Podcast: https://podcasts.apple.com/us/podcast/daily-paper-cast/id1777620236 Cover Image by Kawen Kuang https://kawen.art","last_synced_at":"2026-09-09T20:18:08.781137+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649"},"episodes":[{"title":"NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness","slug":"neohorse-1-towards-recursive-self-improvement-via-agentic-post-training-with-routing-harness","published_at":"2026-09-09T09:14:21+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/neohorse-1-towards-recursive-self-improvement-via-agentic-post-training-with-routing-harness","url":"https://share.transistor.fm/s/abdae4bf","duration_seconds":1197,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/neohorse-1-towards-recursive-self-improvement-via-agentic-post-training-with-routing-harness/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/neohorse-1-towards-recursive-self-improvement-via-agentic-post-training-with-routing-harness.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation","slug":"eliciting-weak-to-strong-generalization-with-on-policy-reverse-distillation","published_at":"2026-09-09T09:05:12+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/eliciting-weak-to-strong-generalization-with-on-policy-reverse-distillation","url":"https://share.transistor.fm/s/7cb4c5a7","duration_seconds":1281,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/eliciting-weak-to-strong-generalization-with-on-policy-reverse-distillation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/eliciting-weak-to-strong-generalization-with-on-policy-reverse-distillation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Omni Interaction Agent Technical Report","slug":"omni-interaction-agent-technical-report","published_at":"2026-09-09T08:56:06+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/omni-interaction-agent-technical-report","url":"https://share.transistor.fm/s/f38447c2","duration_seconds":1343,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/omni-interaction-agent-technical-report/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/omni-interaction-agent-technical-report.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"DriveZero: End-to-End Driving Beyond Human Demonstrations","slug":"drivezero-end-to-end-driving-beyond-human-demonstrations","published_at":"2026-09-09T08:47:13+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/drivezero-end-to-end-driving-beyond-human-demonstrations","url":"https://share.transistor.fm/s/b7ae44fe","duration_seconds":1333,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/drivezero-end-to-end-driving-beyond-human-demonstrations/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/drivezero-end-to-end-driving-beyond-human-demonstrations.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"GE-Act 2.0: Pretraining and Scaling a World-Action Model for Robotic Manipulation","slug":"ge-act-2-0-pretraining-and-scaling-a-world-action-model-for-robotic-manipulation","published_at":"2026-09-09T08:38:19+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/ge-act-2-0-pretraining-and-scaling-a-world-action-model-for-robotic-manipulation","url":"https://share.transistor.fm/s/38c0118b","duration_seconds":1206,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/ge-act-2-0-pretraining-and-scaling-a-world-action-model-for-robotic-manipulation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/ge-act-2-0-pretraining-and-scaling-a-world-action-model-for-robotic-manipulation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout","slug":"mask-forcing-improving-autoregressive-video-diffusion-distillation-via-dual-noise-masking-rollout","published_at":"2026-09-09T08:29:55+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/mask-forcing-improving-autoregressive-video-diffusion-distillation-via-dual-noise-masking-rollout","url":"https://share.transistor.fm/s/d98e3d61","duration_seconds":1255,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/mask-forcing-improving-autoregressive-video-diffusion-distillation-via-dual-noise-masking-rollout/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/mask-forcing-improving-autoregressive-video-diffusion-distillation-via-dual-noise-masking-rollout.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing","slug":"auk-technical-report-an-open-source-foundational-model-for-speech-generation-and-editing","published_at":"2026-09-09T08:20:51+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/auk-technical-report-an-open-source-foundational-model-for-speech-generation-and-editing","url":"https://share.transistor.fm/s/9fd46524","duration_seconds":1171,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/auk-technical-report-an-open-source-foundational-model-for-speech-generation-and-editing/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/auk-technical-report-an-open-source-foundational-model-for-speech-generation-and-editing.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Miles v0.1: Production-Level Post-Training","slug":"miles-v0-1-production-level-post-training","published_at":"2026-09-09T08:12:50+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/miles-v0-1-production-level-post-training","url":"https://share.transistor.fm/s/354e197c","duration_seconds":1234,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/miles-v0-1-production-level-post-training/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/miles-v0-1-production-level-post-training.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"SceneMosaic: Efficient and Diverse Simulation-Ready Scene Generation via Hybrid Agentic Layout Evolution","slug":"scenemosaic-efficient-and-diverse-simulation-ready-scene-generation-via-hybrid-agentic-layout-evolution","published_at":"2026-09-09T08:04:26+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/scenemosaic-efficient-and-diverse-simulation-ready-scene-generation-via-hybrid-agentic-layout-evolution","url":"https://share.transistor.fm/s/92fa5cfc","duration_seconds":1100,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/scenemosaic-efficient-and-diverse-simulation-ready-scene-generation-via-hybrid-agentic-layout-evolution/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/scenemosaic-efficient-and-diverse-simulation-ready-scene-generation-via-hybrid-agentic-layout-evolution.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes","slug":"llada-image-building-strong-image-generators-with-fully-open-training-recipes","published_at":"2026-09-04T08:31:46+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/llada-image-building-strong-image-generators-with-fully-open-training-recipes","url":"https://share.transistor.fm/s/57ee1150","duration_seconds":1369,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/llada-image-building-strong-image-generators-with-fully-open-training-recipes/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/llada-image-building-strong-image-generators-with-fully-open-training-recipes.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"LatentPress: Context Compression Beyond Text and Vision","slug":"latentpress-context-compression-beyond-text-and-vision","published_at":"2026-09-04T08:21:45+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/latentpress-context-compression-beyond-text-and-vision","url":"https://share.transistor.fm/s/d0235eed","duration_seconds":1222,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/latentpress-context-compression-beyond-text-and-vision/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/latentpress-context-compression-beyond-text-and-vision.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM","slug":"why-gated-deltanet-survives-4-bit-quantization-nvfp4-w4a4-for-the-recurrent-half-of-a-hybrid-27b-llm","published_at":"2026-09-04T08:13:09+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/why-gated-deltanet-survives-4-bit-quantization-nvfp4-w4a4-for-the-recurrent-half-of-a-hybrid-27b-llm","url":"https://share.transistor.fm/s/43af8c54","duration_seconds":1203,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/why-gated-deltanet-survives-4-bit-quantization-nvfp4-w4a4-for-the-recurrent-half-of-a-hybrid-27b-llm/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/why-gated-deltanet-survives-4-bit-quantization-nvfp4-w4a4-for-the-recurrent-half-of-a-hybrid-27b-llm.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning","slug":"random-attention-rethinking-kv-cache-eviction-for-efficient-reasoning","published_at":"2026-09-04T08:05:52+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/random-attention-rethinking-kv-cache-eviction-for-efficient-reasoning","url":"https://share.transistor.fm/s/b0997aa9","duration_seconds":1237,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/random-attention-rethinking-kv-cache-eviction-for-efficient-reasoning/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/random-attention-rethinking-kv-cache-eviction-for-efficient-reasoning.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Rethinking On-Policy Distillation of Large Language Models II: One Training Example","slug":"rethinking-on-policy-distillation-of-large-language-models-ii-one-training-example","published_at":"2026-09-04T07:57:57+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/rethinking-on-policy-distillation-of-large-language-models-ii-one-training-example","url":"https://share.transistor.fm/s/e95ac04d","duration_seconds":1332,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/rethinking-on-policy-distillation-of-large-language-models-ii-one-training-example/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/rethinking-on-policy-distillation-of-large-language-models-ii-one-training-example.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States","slug":"puffin-world-scaling-a-unified-multimodal-model-with-native-3d-world-states","published_at":"2026-09-04T07:49:10+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/puffin-world-scaling-a-unified-multimodal-model-with-native-3d-world-states","url":"https://share.transistor.fm/s/fa0f3c67","duration_seconds":1323,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/puffin-world-scaling-a-unified-multimodal-model-with-native-3d-world-states/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/puffin-world-scaling-a-unified-multimodal-model-with-native-3d-world-states.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments","slug":"terminal-universe-turning-agent-trajectories-into-scalable-terminal-environments","published_at":"2026-09-04T07:39:34+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/terminal-universe-turning-agent-trajectories-into-scalable-terminal-environments","url":"https://share.transistor.fm/s/041c078c","duration_seconds":1322,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/terminal-universe-turning-agent-trajectories-into-scalable-terminal-environments/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/terminal-universe-turning-agent-trajectories-into-scalable-terminal-environments.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills","slug":"repo-to-skill-distilling-github-repositories-into-ai4ai-skills","published_at":"2026-09-03T08:51:18+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/repo-to-skill-distilling-github-repositories-into-ai4ai-skills","url":"https://share.transistor.fm/s/326e5728","duration_seconds":1276,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/repo-to-skill-distilling-github-repositories-into-ai4ai-skills/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/repo-to-skill-distilling-github-repositories-into-ai4ai-skills.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models","slug":"solarwm-open-data-and-scalable-training-for-long-horizon-video-world-models","published_at":"2026-09-03T08:42:34+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/solarwm-open-data-and-scalable-training-for-long-horizon-video-world-models","url":"https://share.transistor.fm/s/5023ec64","duration_seconds":1241,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/solarwm-open-data-and-scalable-training-for-long-horizon-video-world-models/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/solarwm-open-data-and-scalable-training-for-long-horizon-video-world-models.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction","slug":"earlyeval-cheaper-agent-evaluation-via-early-outcome-prediction","published_at":"2026-09-03T08:34:17+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/earlyeval-cheaper-agent-evaluation-via-early-outcome-prediction","url":"https://share.transistor.fm/s/b2cc9e6f","duration_seconds":1265,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/earlyeval-cheaper-agent-evaluation-via-early-outcome-prediction/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/earlyeval-cheaper-agent-evaluation-via-early-outcome-prediction.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning","slug":"it-takes-two-to-match-co-evolving-generative-retriever-with-reinforcement-learning","published_at":"2026-09-03T08:26:30+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/it-takes-two-to-match-co-evolving-generative-retriever-with-reinforcement-learning","url":"https://share.transistor.fm/s/48c332ae","duration_seconds":1241,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/it-takes-two-to-match-co-evolving-generative-retriever-with-reinforcement-learning/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/it-takes-two-to-match-co-evolving-generative-retriever-with-reinforcement-learning.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Language Models Can Control Their Own Attention","slug":"language-models-can-control-their-own-attention","published_at":"2026-09-03T08:19:11+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/language-models-can-control-their-own-attention","url":"https://share.transistor.fm/s/c6f3d073","duration_seconds":1259,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/language-models-can-control-their-own-attention/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/language-models-can-control-their-own-attention.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"On the Design Fundamentals of Pixel Text Representation Learning","slug":"on-the-design-fundamentals-of-pixel-text-representation-learning","published_at":"2026-09-03T08:10:40+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/on-the-design-fundamentals-of-pixel-text-representation-learning","url":"https://share.transistor.fm/s/df027c33","duration_seconds":1182,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/on-the-design-fundamentals-of-pixel-text-representation-learning/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/on-the-design-fundamentals-of-pixel-text-representation-learning.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"StudentSim: Training LLM-based Student Simulators","slug":"studentsim-training-llm-based-student-simulators","published_at":"2026-09-02T08:26:26+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/studentsim-training-llm-based-student-simulators","url":"https://share.transistor.fm/s/819545df","duration_seconds":1248,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/studentsim-training-llm-based-student-simulators/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/studentsim-training-llm-based-student-simulators.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers","slug":"smelt-scaling-laws-for-compute-matched-moe-looped-transformers","published_at":"2026-09-02T08:18:16+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/smelt-scaling-laws-for-compute-matched-moe-looped-transformers","url":"https://share.transistor.fm/s/d8dde809","duration_seconds":1268,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/smelt-scaling-laws-for-compute-matched-moe-looped-transformers/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/smelt-scaling-laws-for-compute-matched-moe-looped-transformers.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"UI-Venus-2 Technical Report","slug":"ui-venus-2-technical-report","published_at":"2026-09-02T08:09:45+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/ui-venus-2-technical-report","url":"https://share.transistor.fm/s/2eb70f45","duration_seconds":1384,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/ui-venus-2-technical-report/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/ui-venus-2-technical-report.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis","slug":"askchem-claim-centered-infrastructure-for-chemistry-literature-synthesis","published_at":"2026-08-01T04:55:00+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/askchem-claim-centered-infrastructure-for-chemistry-literature-synthesis","url":"https://share.transistor.fm/s/9a953c88","duration_seconds":1178,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/askchem-claim-centered-infrastructure-for-chemistry-literature-synthesis/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/askchem-claim-centered-infrastructure-for-chemistry-literature-synthesis.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents","slug":"qwen-ui-agent-technical-report-toward-next-generation-real-world-centric-foundation-gui-agents","published_at":"2026-08-01T04:47:39+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/qwen-ui-agent-technical-report-toward-next-generation-real-world-centric-foundation-gui-agents","url":"https://share.transistor.fm/s/05c65ebb","duration_seconds":1392,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/qwen-ui-agent-technical-report-toward-next-generation-real-world-centric-foundation-gui-agents/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/qwen-ui-agent-technical-report-toward-next-generation-real-world-centric-foundation-gui-agents.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Metis: Memory Foundation Model","slug":"metis-memory-foundation-model","published_at":"2026-08-01T04:37:33+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/metis-memory-foundation-model","url":"https://share.transistor.fm/s/22649fde","duration_seconds":1113,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/metis-memory-foundation-model/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/metis-memory-foundation-model.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering","slug":"frontis-ma1-training-an-ai4ai-model-towards-recursive-self-improvement-in-machine-learning-engineering","published_at":"2026-08-01T04:27:34+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/frontis-ma1-training-an-ai4ai-model-towards-recursive-self-improvement-in-machine-learning-engineering","url":"https://share.transistor.fm/s/dd0c00bc","duration_seconds":1298,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/frontis-ma1-training-an-ai4ai-model-towards-recursive-self-improvement-in-machine-learning-engineering/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/frontis-ma1-training-an-ai4ai-model-towards-recursive-self-improvement-in-machine-learning-engineering.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"PhiZero: A World Model Built Around Physical Language","slug":"phizero-a-world-model-built-around-physical-language","published_at":"2026-08-01T04:18:28+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/phizero-a-world-model-built-around-physical-language","url":"https://share.transistor.fm/s/9e6fc395","duration_seconds":1177,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/phizero-a-world-model-built-around-physical-language/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/phizero-a-world-model-built-around-physical-language.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System","slug":"videococo-code-as-cot-for-physically-consistent-video-generation-via-an-agentic-dual-engine-system","published_at":"2026-08-01T04:10:19+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/videococo-code-as-cot-for-physically-consistent-video-generation-via-an-agentic-dual-engine-system","url":"https://share.transistor.fm/s/d0fc4240","duration_seconds":1341,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/videococo-code-as-cot-for-physically-consistent-video-generation-via-an-agentic-dual-engine-system/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/videococo-code-as-cot-for-physically-consistent-video-generation-via-an-agentic-dual-engine-system.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory","slug":"memory-decoder-at-scale-a-pretrained-parametric-long-term-memory","published_at":"2026-08-01T04:02:06+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/memory-decoder-at-scale-a-pretrained-parametric-long-term-memory","url":"https://share.transistor.fm/s/758c95f9","duration_seconds":1343,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/memory-decoder-at-scale-a-pretrained-parametric-long-term-memory/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/memory-decoder-at-scale-a-pretrained-parametric-long-term-memory.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Beacon: Knowing When and How to Perform Agentic Visual Reasoning","slug":"beacon-knowing-when-and-how-to-perform-agentic-visual-reasoning","published_at":"2026-08-01T03:53:05+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/beacon-knowing-when-and-how-to-perform-agentic-visual-reasoning","url":"https://share.transistor.fm/s/11578e60","duration_seconds":1218,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/beacon-knowing-when-and-how-to-perform-agentic-visual-reasoning/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/beacon-knowing-when-and-how-to-perform-agentic-visual-reasoning.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms","slug":"bm25-wins-at-scale-a-scaling-study-of-retrieval-augmented-generation-paradigms","published_at":"2026-08-01T03:44:53+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/bm25-wins-at-scale-a-scaling-study-of-retrieval-augmented-generation-paradigms","url":"https://share.transistor.fm/s/5a0e9032","duration_seconds":1217,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/bm25-wins-at-scale-a-scaling-study-of-retrieval-augmented-generation-paradigms/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/bm25-wins-at-scale-a-scaling-study-of-retrieval-augmented-generation-paradigms.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Flux-OPD: On-Policy Distillation with Evolving Contexts","slug":"flux-opd-on-policy-distillation-with-evolving-contexts","published_at":"2026-08-01T03:37:16+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/flux-opd-on-policy-distillation-with-evolving-contexts","url":"https://share.transistor.fm/s/c0b436c9","duration_seconds":1238,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/flux-opd-on-policy-distillation-with-evolving-contexts/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/flux-opd-on-policy-distillation-with-evolving-contexts.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM","slug":"turbovla-real-time-vision-language-action-model-at-32-hz-on-an-rtx-4090-with-1-gb-vram","published_at":"2026-07-31T03:58:53+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/turbovla-real-time-vision-language-action-model-at-32-hz-on-an-rtx-4090-with-1-gb-vram","url":"https://share.transistor.fm/s/bae73e74","duration_seconds":1250,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/turbovla-real-time-vision-language-action-model-at-32-hz-on-an-rtx-4090-with-1-gb-vram/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/turbovla-real-time-vision-language-action-model-at-32-hz-on-an-rtx-4090-with-1-gb-vram.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization","slug":"cort-counterfactual-replay-for-token-level-rubric-guided-policy-optimization","published_at":"2026-07-31T03:51:29+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/cort-counterfactual-replay-for-token-level-rubric-guided-policy-optimization","url":"https://share.transistor.fm/s/7b7b9011","duration_seconds":1206,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/cort-counterfactual-replay-for-token-level-rubric-guided-policy-optimization/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/cort-counterfactual-replay-for-token-level-rubric-guided-policy-optimization.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"HumanCLAW: Can Vision-Language Models Act Through a Body?","slug":"humanclaw-can-vision-language-models-act-through-a-body","published_at":"2026-07-31T03:43:21+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/humanclaw-can-vision-language-models-act-through-a-body","url":"https://share.transistor.fm/s/6fec1841","duration_seconds":1181,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/humanclaw-can-vision-language-models-act-through-a-body/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/humanclaw-can-vision-language-models-act-through-a-body.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"DecoEvo: Score-Decoupled Co-Evolution of Solver and Rubric-Generator Skills in Text Space","slug":"decoevo-score-decoupled-co-evolution-of-solver-and-rubric-generator-skills-in-text-space","published_at":"2026-07-31T03:34:43+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/decoevo-score-decoupled-co-evolution-of-solver-and-rubric-generator-skills-in-text-space","url":"https://share.transistor.fm/s/7a27ea4d","duration_seconds":1179,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/decoevo-score-decoupled-co-evolution-of-solver-and-rubric-generator-skills-in-text-space/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/decoevo-score-decoupled-co-evolution-of-solver-and-rubric-generator-skills-in-text-space.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"CLBench-V: Evaluating Multimodal Context Learning from Grounding to Knowledge Acquisition","slug":"clbench-v-evaluating-multimodal-context-learning-from-grounding-to-knowledge-acquisition","published_at":"2026-07-31T03:27:01+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/clbench-v-evaluating-multimodal-context-learning-from-grounding-to-knowledge-acquisition","url":"https://share.transistor.fm/s/873348af","duration_seconds":1279,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/clbench-v-evaluating-multimodal-context-learning-from-grounding-to-knowledge-acquisition/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/clbench-v-evaluating-multimodal-context-learning-from-grounding-to-knowledge-acquisition.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"CAST: Game Solvers as Turn-Level Teachers for LLM Agents","slug":"cast-game-solvers-as-turn-level-teachers-for-llm-agents","published_at":"2026-07-31T03:19:17+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/cast-game-solvers-as-turn-level-teachers-for-llm-agents","url":"https://share.transistor.fm/s/da38c7a9","duration_seconds":1231,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/cast-game-solvers-as-turn-level-teachers-for-llm-agents/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/cast-game-solvers-as-turn-level-teachers-for-llm-agents.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone","slug":"hifi-umi-learning-deployable-manipulation-policies-from-high-fidelity-umi-data-alone","published_at":"2026-07-30T04:03:40+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/hifi-umi-learning-deployable-manipulation-policies-from-high-fidelity-umi-data-alone","url":"https://share.transistor.fm/s/77f7d058","duration_seconds":1157,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/hifi-umi-learning-deployable-manipulation-policies-from-high-fidelity-umi-data-alone/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/hifi-umi-learning-deployable-manipulation-policies-from-high-fidelity-umi-data-alone.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"A New Role for Relevance: Guiding Corpus Interaction in Agentic Search","slug":"a-new-role-for-relevance-guiding-corpus-interaction-in-agentic-search","published_at":"2026-07-30T03:55:53+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/a-new-role-for-relevance-guiding-corpus-interaction-in-agentic-search","url":"https://share.transistor.fm/s/d5b82491","duration_seconds":1199,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/a-new-role-for-relevance-guiding-corpus-interaction-in-agentic-search/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/a-new-role-for-relevance-guiding-corpus-interaction-in-agentic-search.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents","slug":"codenib-a-multi-view-data-system-for-serving-repository-context-to-coding-agents","published_at":"2026-07-30T03:48:17+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/codenib-a-multi-view-data-system-for-serving-repository-context-to-coding-agents","url":"https://share.transistor.fm/s/35258158","duration_seconds":1140,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/codenib-a-multi-view-data-system-for-serving-repository-context-to-coding-agents/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/codenib-a-multi-view-data-system-for-serving-repository-context-to-coding-agents.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition","slug":"redesign-recovering-editable-design-structures-from-images-via-agentic-decomposition","published_at":"2026-07-30T03:40:27+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/redesign-recovering-editable-design-structures-from-images-via-agentic-decomposition","url":"https://share.transistor.fm/s/2871b6bc","duration_seconds":1291,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/redesign-recovering-editable-design-structures-from-images-via-agentic-decomposition/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/redesign-recovering-editable-design-structures-from-images-via-agentic-decomposition.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Keep It InMind: Benchmarking the Implicit-Association Blind Spot in Agent Memory","slug":"keep-it-inmind-benchmarking-the-implicit-association-blind-spot-in-agent-memory","published_at":"2026-07-30T03:31:59+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/keep-it-inmind-benchmarking-the-implicit-association-blind-spot-in-agent-memory","url":"https://share.transistor.fm/s/796f31d4","duration_seconds":1142,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/keep-it-inmind-benchmarking-the-implicit-association-blind-spot-in-agent-memory/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/keep-it-inmind-benchmarking-the-implicit-association-blind-spot-in-agent-memory.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Pass the Baton: Trajectory-Relayed On-Policy Distillation","slug":"pass-the-baton-trajectory-relayed-on-policy-distillation","published_at":"2026-07-30T03:18:12+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/pass-the-baton-trajectory-relayed-on-policy-distillation","url":"https://share.transistor.fm/s/2c945e76","duration_seconds":1219,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/pass-the-baton-trajectory-relayed-on-policy-distillation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/pass-the-baton-trajectory-relayed-on-policy-distillation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Kimi K3: Open Frontier Intelligence","slug":"kimi-k3-open-frontier-intelligence","published_at":"2026-07-29T04:34:36+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/kimi-k3-open-frontier-intelligence","url":"https://share.transistor.fm/s/0624f2d1","duration_seconds":1234,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/kimi-k3-open-frontier-intelligence/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/kimi-k3-open-frontier-intelligence.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents","slug":"jarvishub-an-open-harness-for-canvas-native-multimodal-creative-agents","published_at":"2026-07-29T04:25:48+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/jarvishub-an-open-harness-for-canvas-native-multimodal-creative-agents","url":"https://share.transistor.fm/s/73710d18","duration_seconds":1226,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/jarvishub-an-open-harness-for-canvas-native-multimodal-creative-agents/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/jarvishub-an-open-harness-for-canvas-native-multimodal-creative-agents.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Progress Reward Modeling for Robotic Learning: A Comprehensive Survey","slug":"progress-reward-modeling-for-robotic-learning-a-comprehensive-survey","published_at":"2026-07-29T04:18:04+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/progress-reward-modeling-for-robotic-learning-a-comprehensive-survey","url":"https://share.transistor.fm/s/ff114da2","duration_seconds":1298,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/progress-reward-modeling-for-robotic-learning-a-comprehensive-survey/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/progress-reward-modeling-for-robotic-learning-a-comprehensive-survey.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search","slug":"from-proprietary-to-open-source-bridging-the-distribution-gap-via-multi-agent-protocol-distillation-in-agentic-search","published_at":"2026-07-29T04:10:20+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/from-proprietary-to-open-source-bridging-the-distribution-gap-via-multi-agent-protocol-distillation-in-agentic-search","url":"https://share.transistor.fm/s/9aa267fb","duration_seconds":1243,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/from-proprietary-to-open-source-bridging-the-distribution-gap-via-multi-agent-protocol-distillation-in-agentic-search/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/from-proprietary-to-open-source-bridging-the-distribution-gap-via-multi-agent-protocol-distillation-in-agentic-search.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation","slug":"rethinking-classifier-free-guidance-in-on-policy-diffusion-distillation","published_at":"2026-07-29T04:01:59+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/rethinking-classifier-free-guidance-in-on-policy-diffusion-distillation","url":"https://share.transistor.fm/s/9ffa4904","duration_seconds":1278,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/rethinking-classifier-free-guidance-in-on-policy-diffusion-distillation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/rethinking-classifier-free-guidance-in-on-policy-diffusion-distillation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents","slug":"stateact-program-state-before-pixels-for-long-horizon-computer-use-agents","published_at":"2026-07-29T03:53:44+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/stateact-program-state-before-pixels-for-long-horizon-computer-use-agents","url":"https://share.transistor.fm/s/736ebc34","duration_seconds":1289,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/stateact-program-state-before-pixels-for-long-horizon-computer-use-agents/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/stateact-program-state-before-pixels-for-long-horizon-computer-use-agents.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Data Pyramid for Embodied Manipulation","slug":"data-pyramid-for-embodied-manipulation","published_at":"2026-07-29T03:46:14+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/data-pyramid-for-embodied-manipulation","url":"https://share.transistor.fm/s/c02a0306","duration_seconds":1391,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/data-pyramid-for-embodied-manipulation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/data-pyramid-for-embodied-manipulation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","slug":"sol-attn-accelerating-video-generation-inference-via-on-the-fly-attention-sparsification","published_at":"2026-07-29T03:36:56+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/sol-attn-accelerating-video-generation-inference-via-on-the-fly-attention-sparsification","url":"https://share.transistor.fm/s/46907ae6","duration_seconds":1321,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/sol-attn-accelerating-video-generation-inference-via-on-the-fly-attention-sparsification/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/sol-attn-accelerating-video-generation-inference-via-on-the-fly-attention-sparsification.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation","slug":"omnivae-an-audio-video-vae-with-cross-modal-alignment-for-joint-generation","published_at":"2026-07-29T03:27:29+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/omnivae-an-audio-video-vae-with-cross-modal-alignment-for-joint-generation","url":"https://share.transistor.fm/s/98c800c7","duration_seconds":1204,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/omnivae-an-audio-video-vae-with-cross-modal-alignment-for-joint-generation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/omnivae-an-audio-video-vae-with-cross-modal-alignment-for-joint-generation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Oxygen-TryOn: Fashion-Native Foundation Model for Any-item Virtual Try-On","slug":"oxygen-tryon-fashion-native-foundation-model-for-any-item-virtual-try-on","published_at":"2026-07-29T03:20:23+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/oxygen-tryon-fashion-native-foundation-model-for-any-item-virtual-try-on","url":"https://share.transistor.fm/s/c4cd3577","duration_seconds":1397,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/oxygen-tryon-fashion-native-foundation-model-for-any-item-virtual-try-on/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/oxygen-tryon-fashion-native-foundation-model-for-any-item-virtual-try-on.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"DataPrep-Bench: Benchmarking LLMs as Training Data Preparators","slug":"dataprep-bench-benchmarking-llms-as-training-data-preparators","published_at":"2026-07-28T03:37:14+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/dataprep-bench-benchmarking-llms-as-training-data-preparators","url":"https://share.transistor.fm/s/d4f30016","duration_seconds":1296,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/dataprep-bench-benchmarking-llms-as-training-data-preparators/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/dataprep-bench-benchmarking-llms-as-training-data-preparators.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills","slug":"skill-self-play-pushing-the-frontier-of-llm-capability-with-co-evolving-skills","published_at":"2026-07-28T03:28:25+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/skill-self-play-pushing-the-frontier-of-llm-capability-with-co-evolving-skills","url":"https://share.transistor.fm/s/9e05d462","duration_seconds":1166,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/skill-self-play-pushing-the-frontier-of-llm-capability-with-co-evolving-skills/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/skill-self-play-pushing-the-frontier-of-llm-capability-with-co-evolving-skills.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning","slug":"molt-a-scalable-pytorch-native-training-framework-for-agentic-reinforcement-learning","published_at":"2026-07-28T03:19:57+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/molt-a-scalable-pytorch-native-training-framework-for-agentic-reinforcement-learning","url":"https://share.transistor.fm/s/dfaa8e13","duration_seconds":1183,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/molt-a-scalable-pytorch-native-training-framework-for-agentic-reinforcement-learning/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/molt-a-scalable-pytorch-native-training-framework-for-agentic-reinforcement-learning.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"AREX: Towards a Recursively Self-Improving Agent for Deep Research","slug":"arex-towards-a-recursively-self-improving-agent-for-deep-research","published_at":"2026-07-25T03:48:33+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/arex-towards-a-recursively-self-improving-agent-for-deep-research","url":"https://share.transistor.fm/s/e4ff2020","duration_seconds":1191,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/arex-towards-a-recursively-self-improving-agent-for-deep-research/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/arex-towards-a-recursively-self-improving-agent-for-deep-research.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"ReferTrack: Referring Then Tracking for Embodied Visual Tracking","slug":"refertrack-referring-then-tracking-for-embodied-visual-tracking","published_at":"2026-07-25T03:41:54+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/refertrack-referring-then-tracking-for-embodied-visual-tracking","url":"https://share.transistor.fm/s/78209b35","duration_seconds":1248,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/refertrack-referring-then-tracking-for-embodied-visual-tracking/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/refertrack-referring-then-tracking-for-embodied-visual-tracking.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs","slug":"k12-kgraph-a-curriculum-aligned-knowledge-graph-for-benchmarking-and-training-educational-llms","published_at":"2026-07-25T03:33:47+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/k12-kgraph-a-curriculum-aligned-knowledge-graph-for-benchmarking-and-training-educational-llms","url":"https://share.transistor.fm/s/72da1bd9","duration_seconds":1365,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/k12-kgraph-a-curriculum-aligned-knowledge-graph-for-benchmarking-and-training-educational-llms/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/k12-kgraph-a-curriculum-aligned-knowledge-graph-for-benchmarking-and-training-educational-llms.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Visual Contrastive Self-Distillation","slug":"visual-contrastive-self-distillation","published_at":"2026-07-25T03:25:26+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/visual-contrastive-self-distillation","url":"https://share.transistor.fm/s/36304bfd","duration_seconds":1284,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/visual-contrastive-self-distillation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/visual-contrastive-self-distillation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text","slug":"show-don-t-tell-evaluating-spatial-cognition-in-generative-pixels-rather-than-llm-text","published_at":"2026-07-25T03:17:07+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/show-don-t-tell-evaluating-spatial-cognition-in-generative-pixels-rather-than-llm-text","url":"https://share.transistor.fm/s/eb4c5b55","duration_seconds":1239,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/show-don-t-tell-evaluating-spatial-cognition-in-generative-pixels-rather-than-llm-text/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/show-don-t-tell-evaluating-spatial-cognition-in-generative-pixels-rather-than-llm-text.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD","slug":"slai-t-rex-full-parameter-post-training-of-the-deepseek-v4-family-on-ascend-superpod","published_at":"2026-07-24T03:27:36+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/slai-t-rex-full-parameter-post-training-of-the-deepseek-v4-family-on-ascend-superpod","url":"https://share.transistor.fm/s/14e3bceb","duration_seconds":1197,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/slai-t-rex-full-parameter-post-training-of-the-deepseek-v4-family-on-ascend-superpod/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/slai-t-rex-full-parameter-post-training-of-the-deepseek-v4-family-on-ascend-superpod.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding","slug":"videochat3-fully-open-video-mllm-for-efficient-and-generalist-video-understanding","published_at":"2026-07-18T04:32:50+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/videochat3-fully-open-video-mllm-for-efficient-and-generalist-video-understanding","url":"https://share.transistor.fm/s/bed89c24","duration_seconds":1481,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/videochat3-fully-open-video-mllm-for-efficient-and-generalist-video-understanding/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/videochat3-fully-open-video-mllm-for-efficient-and-generalist-video-understanding.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning","slug":"seed-self-evolving-on-policy-distillation-for-agentic-reinforcement-learning","published_at":"2026-07-18T04:22:49+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/seed-self-evolving-on-policy-distillation-for-agentic-reinforcement-learning","url":"https://share.transistor.fm/s/170dbcfd","duration_seconds":1156,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/seed-self-evolving-on-policy-distillation-for-agentic-reinforcement-learning/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/seed-self-evolving-on-policy-distillation-for-agentic-reinforcement-learning.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget","slug":"longstraw-long-context-rl-beyond-2m-tokens-under-a-fixed-gpu-budget","published_at":"2026-07-18T04:14:33+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/longstraw-long-context-rl-beyond-2m-tokens-under-a-fixed-gpu-budget","url":"https://share.transistor.fm/s/4d98794b","duration_seconds":1176,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/longstraw-long-context-rl-beyond-2m-tokens-under-a-fixed-gpu-budget/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/longstraw-long-context-rl-beyond-2m-tokens-under-a-fixed-gpu-budget.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration","slug":"searchos-v1-towards-robust-open-domain-information-seeking-agent-collaboration","published_at":"2026-07-18T04:06:25+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/searchos-v1-towards-robust-open-domain-information-seeking-agent-collaboration","url":"https://share.transistor.fm/s/b85efd85","duration_seconds":957,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/searchos-v1-towards-robust-open-domain-information-seeking-agent-collaboration/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/searchos-v1-towards-robust-open-domain-information-seeking-agent-collaboration.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"BadWAM: When World-Action Models Dream Right but Act Wrong","slug":"badwam-when-world-action-models-dream-right-but-act-wrong","published_at":"2026-07-18T03:57:58+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/badwam-when-world-action-models-dream-right-but-act-wrong","url":"https://share.transistor.fm/s/abf24a34","duration_seconds":1263,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/badwam-when-world-action-models-dream-right-but-act-wrong/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/badwam-when-world-action-models-dream-right-but-act-wrong.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"KeyFrame-Compass: Towards Comprehensive Evaluation of Keyframe-Conditioned Video Generation","slug":"keyframe-compass-towards-comprehensive-evaluation-of-keyframe-conditioned-video-generation","published_at":"2026-07-18T03:50:05+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/keyframe-compass-towards-comprehensive-evaluation-of-keyframe-conditioned-video-generation","url":"https://share.transistor.fm/s/30ad1c1d","duration_seconds":1340,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/keyframe-compass-towards-comprehensive-evaluation-of-keyframe-conditioned-video-generation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/keyframe-compass-towards-comprehensive-evaluation-of-keyframe-conditioned-video-generation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generation","slug":"multiref-compass-towards-comprehensive-evaluation-of-multi-reference-to-audio-video-generation","published_at":"2026-07-18T03:40:29+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/multiref-compass-towards-comprehensive-evaluation-of-multi-reference-to-audio-video-generation","url":"https://share.transistor.fm/s/019b59c4","duration_seconds":1251,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/multiref-compass-towards-comprehensive-evaluation-of-multi-reference-to-audio-video-generation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/multiref-compass-towards-comprehensive-evaluation-of-multi-reference-to-audio-video-generation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Concurrent Image Understanding and Generation: Self-Correcting Coupled Markov Jump Processes","slug":"concurrent-image-understanding-and-generation-self-correcting-coupled-markov-jump-processes","published_at":"2026-07-18T03:32:24+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/concurrent-image-understanding-and-generation-self-correcting-coupled-markov-jump-processes","url":"https://share.transistor.fm/s/d8d98877","duration_seconds":1300,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/concurrent-image-understanding-and-generation-self-correcting-coupled-markov-jump-processes/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/concurrent-image-understanding-and-generation-self-correcting-coupled-markov-jump-processes.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"From Pixels to States: Rethinking Interactive World Models as Game Engines","slug":"from-pixels-to-states-rethinking-interactive-world-models-as-game-engines","published_at":"2026-07-18T03:23:56+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/from-pixels-to-states-rethinking-interactive-world-models-as-game-engines","url":"https://share.transistor.fm/s/66269037","duration_seconds":1076,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/from-pixels-to-states-rethinking-interactive-world-models-as-game-engines/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/from-pixels-to-states-rethinking-interactive-world-models-as-game-engines.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"UniVR: Thinking in Visual Space for Unified Visual Reasoning","slug":"univr-thinking-in-visual-space-for-unified-visual-reasoning","published_at":"2026-07-18T03:16:58+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/univr-thinking-in-visual-space-for-unified-visual-reasoning","url":"https://share.transistor.fm/s/d476143c","duration_seconds":1097,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/univr-thinking-in-visual-space-for-unified-visual-reasoning/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/univr-thinking-in-visual-space-for-unified-visual-reasoning.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable","slug":"harness-handbook-making-evolving-agent-harnesses-readable-navigable-and-editable","published_at":"2026-07-17T04:27:58+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/harness-handbook-making-evolving-agent-harnesses-readable-navigable-and-editable","url":"https://share.transistor.fm/s/cf6127ba","duration_seconds":1152,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/harness-handbook-making-evolving-agent-harnesses-readable-navigable-and-editable/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/harness-handbook-making-evolving-agent-harnesses-readable-navigable-and-editable.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Boogu-Image-0.1: Boosting Open-Source Unified Multimodal Understanding and Generation","slug":"boogu-image-0-1-boosting-open-source-unified-multimodal-understanding-and-generation","published_at":"2026-07-17T04:19:38+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/boogu-image-0-1-boosting-open-source-unified-multimodal-understanding-and-generation","url":"https://share.transistor.fm/s/5428bda5","duration_seconds":1168,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/boogu-image-0-1-boosting-open-source-unified-multimodal-understanding-and-generation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/boogu-image-0-1-boosting-open-source-unified-multimodal-understanding-and-generation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning","slug":"ring-zero-scaling-zero-rl-to-a-trillion-parameters-for-emergent-reasoning","published_at":"2026-07-17T04:05:43+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/ring-zero-scaling-zero-rl-to-a-trillion-parameters-for-emergent-reasoning","url":"https://share.transistor.fm/s/2692e8a7","duration_seconds":1249,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/ring-zero-scaling-zero-rl-to-a-trillion-parameters-for-emergent-reasoning/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/ring-zero-scaling-zero-rl-to-a-trillion-parameters-for-emergent-reasoning.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill","slug":"knowact-guiclaw-know-deeply-act-perfectly-personal-gui-assistant-with-self-evolving-memory-and-skill","published_at":"2026-07-17T03:56:36+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/knowact-guiclaw-know-deeply-act-perfectly-personal-gui-assistant-with-self-evolving-memory-and-skill","url":"https://share.transistor.fm/s/da4075d8","duration_seconds":1336,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/knowact-guiclaw-know-deeply-act-perfectly-personal-gui-assistant-with-self-evolving-memory-and-skill/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/knowact-guiclaw-know-deeply-act-perfectly-personal-gui-assistant-with-self-evolving-memory-and-skill.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"OvisOCR2 Technical Report","slug":"ovisocr2-technical-report","published_at":"2026-07-17T03:46:32+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/ovisocr2-technical-report","url":"https://share.transistor.fm/s/49b396cf","duration_seconds":1246,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/ovisocr2-technical-report/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/ovisocr2-technical-report.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails","slug":"policyshiftguard-benchmarking-and-improving-policy-adaptive-image-guardrails","published_at":"2026-07-17T03:36:53+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/policyshiftguard-benchmarking-and-improving-policy-adaptive-image-guardrails","url":"https://share.transistor.fm/s/066736ea","duration_seconds":1182,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/policyshiftguard-benchmarking-and-improving-policy-adaptive-image-guardrails/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/policyshiftguard-benchmarking-and-improving-policy-adaptive-image-guardrails.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"MetaView: Monocular Novel View Synthesis with Scale-Aware Implicit Geometry Priors","slug":"metaview-monocular-novel-view-synthesis-with-scale-aware-implicit-geometry-priors","published_at":"2026-07-17T03:28:08+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/metaview-monocular-novel-view-synthesis-with-scale-aware-implicit-geometry-priors","url":"https://share.transistor.fm/s/d0655b61","duration_seconds":1112,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/metaview-monocular-novel-view-synthesis-with-scale-aware-implicit-geometry-priors/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/metaview-monocular-novel-view-synthesis-with-scale-aware-implicit-geometry-priors.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch","slug":"gigaworld-policy-0-5-a-faster-and-stronger-wam-empowered-by-autoresearch","published_at":"2026-07-17T03:19:57+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/gigaworld-policy-0-5-a-faster-and-stronger-wam-empowered-by-autoresearch","url":"https://share.transistor.fm/s/65d7b1a5","duration_seconds":1273,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/gigaworld-policy-0-5-a-faster-and-stronger-wam-empowered-by-autoresearch/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/gigaworld-policy-0-5-a-faster-and-stronger-wam-empowered-by-autoresearch.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"SynthDocBench: Controlled Benchmark for Long-Context Visual Document Understanding","slug":"synthdocbench-controlled-benchmark-for-long-context-visual-document-understanding","published_at":"2026-07-16T03:44:21+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/synthdocbench-controlled-benchmark-for-long-context-visual-document-understanding","url":"https://share.transistor.fm/s/e9f23009","duration_seconds":1259,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/synthdocbench-controlled-benchmark-for-long-context-visual-document-understanding/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/synthdocbench-controlled-benchmark-for-long-context-visual-document-understanding.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation","slug":"read-it-back-pretrained-mllms-are-zero-shot-reward-models-for-text-to-image-generation","published_at":"2026-07-16T03:36:18+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/read-it-back-pretrained-mllms-are-zero-shot-reward-models-for-text-to-image-generation","url":"https://share.transistor.fm/s/e28356b6","duration_seconds":1157,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/read-it-back-pretrained-mllms-are-zero-shot-reward-models-for-text-to-image-generation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/read-it-back-pretrained-mllms-are-zero-shot-reward-models-for-text-to-image-generation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation","slug":"search-beyond-what-can-be-taught-evolving-the-knowledge-boundary-in-agentic-visual-generation","published_at":"2026-07-16T03:27:06+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/search-beyond-what-can-be-taught-evolving-the-knowledge-boundary-in-agentic-visual-generation","url":"https://share.transistor.fm/s/d4f85c2a","duration_seconds":1164,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/search-beyond-what-can-be-taught-evolving-the-knowledge-boundary-in-agentic-visual-generation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/search-beyond-what-can-be-taught-evolving-the-knowledge-boundary-in-agentic-visual-generation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models","slug":"blind-spots-bench-evaluating-blind-spots-in-multimodal-models","published_at":"2026-07-16T03:18:41+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/blind-spots-bench-evaluating-blind-spots-in-multimodal-models","url":"https://share.transistor.fm/s/2d4e982c","duration_seconds":1179,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/blind-spots-bench-evaluating-blind-spots-in-multimodal-models/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/blind-spots-bench-evaluating-blind-spots-in-multimodal-models.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Weak-to-Strong Generalization via Direct On-Policy Distillation","slug":"weak-to-strong-generalization-via-direct-on-policy-distillation","published_at":"2026-07-15T03:45:23+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/weak-to-strong-generalization-via-direct-on-policy-distillation","url":"https://share.transistor.fm/s/c2959ca2","duration_seconds":1182,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/weak-to-strong-generalization-via-direct-on-policy-distillation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/weak-to-strong-generalization-via-direct-on-policy-distillation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory","slug":"abot-agentos-a-general-robotic-agent-os-with-lifelong-multi-modal-memory","published_at":"2026-07-15T03:36:42+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/abot-agentos-a-general-robotic-agent-os-with-lifelong-multi-modal-memory","url":"https://share.transistor.fm/s/dad85862","duration_seconds":1338,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/abot-agentos-a-general-robotic-agent-os-with-lifelong-multi-modal-memory/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/abot-agentos-a-general-robotic-agent-os-with-lifelong-multi-modal-memory.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"4D Human-Scene Reconstruction from Low-Overlap Captures","slug":"4d-human-scene-reconstruction-from-low-overlap-captures","published_at":"2026-07-15T03:26:33+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/4d-human-scene-reconstruction-from-low-overlap-captures","url":"https://share.transistor.fm/s/c3142205","duration_seconds":1196,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/4d-human-scene-reconstruction-from-low-overlap-captures/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/4d-human-scene-reconstruction-from-low-overlap-captures.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation","slug":"rynnworld-4d-4d-embodied-world-models-for-robotic-manipulation","published_at":"2026-07-09T04:18:50+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/rynnworld-4d-4d-embodied-world-models-for-robotic-manipulation","url":"https://share.transistor.fm/s/74cad849","duration_seconds":1516,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/rynnworld-4d-4d-embodied-world-models-for-robotic-manipulation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/rynnworld-4d-4d-embodied-world-models-for-robotic-manipulation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation","slug":"rynnworld-teleop-an-action-conditioned-world-model-for-digital-teleoperation","published_at":"2026-07-09T03:48:44+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/rynnworld-teleop-an-action-conditioned-world-model-for-digital-teleoperation","url":"https://share.transistor.fm/s/e56a2721","duration_seconds":1301,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/rynnworld-teleop-an-action-conditioned-world-model-for-digital-teleoperation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/rynnworld-teleop-an-action-conditioned-world-model-for-digital-teleoperation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling","slug":"hierarchical-sparse-attention-done-right-toward-infinite-context-modeling","published_at":"2026-07-09T03:41:56+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/hierarchical-sparse-attention-done-right-toward-infinite-context-modeling","url":"https://share.transistor.fm/s/2a4aad18","duration_seconds":1257,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/hierarchical-sparse-attention-done-right-toward-infinite-context-modeling/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/hierarchical-sparse-attention-done-right-toward-infinite-context-modeling.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Vision as Unified Multimodal Generation","slug":"vision-as-unified-multimodal-generation","published_at":"2026-07-09T03:34:11+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/vision-as-unified-multimodal-generation","url":"https://share.transistor.fm/s/b29bc9e3","duration_seconds":1578,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/vision-as-unified-multimodal-generation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/vision-as-unified-multimodal-generation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Gemma 4 Technical Report","slug":"gemma-4-technical-report","published_at":"2026-07-09T03:26:11+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/gemma-4-technical-report","url":"https://share.transistor.fm/s/d7c796e8","duration_seconds":1431,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/gemma-4-technical-report/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/gemma-4-technical-report.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers","slug":"omniopt-taxonomy-geometry-and-benchmarking-of-modern-optimizers","published_at":"2026-07-08T04:26:28+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/omniopt-taxonomy-geometry-and-benchmarking-of-modern-optimizers","url":"https://share.transistor.fm/s/37daef44","duration_seconds":1244,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/omniopt-taxonomy-geometry-and-benchmarking-of-modern-optimizers/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/omniopt-taxonomy-geometry-and-benchmarking-of-modern-optimizers.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning","slug":"ui-mopd-multi-platform-on-policy-distillation-for-continual-gui-agent-learning","published_at":"2026-07-08T04:19:10+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/ui-mopd-multi-platform-on-policy-distillation-for-continual-gui-agent-learning","url":"https://share.transistor.fm/s/6d7f3786","duration_seconds":1301,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/ui-mopd-multi-platform-on-policy-distillation-for-continual-gui-agent-learning/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/ui-mopd-multi-platform-on-policy-distillation-for-continual-gui-agent-learning.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog","slug":"researchstudio-reel-automate-the-last-mile-of-research-from-paper-to-poster-video-and-blog","published_at":"2026-07-08T04:12:05+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/researchstudio-reel-automate-the-last-mile-of-research-from-paper-to-poster-video-and-blog","url":"https://share.transistor.fm/s/89017ca7","duration_seconds":1417,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/researchstudio-reel-automate-the-last-mile-of-research-from-paper-to-poster-video-and-blog/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/researchstudio-reel-automate-the-last-mile-of-research-from-paper-to-poster-video-and-blog.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space","slug":"pixworld-unifying-3d-scene-generation-and-reconstruction-in-pixel-space","published_at":"2026-07-08T04:04:11+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/pixworld-unifying-3d-scene-generation-and-reconstruction-in-pixel-space","url":"https://share.transistor.fm/s/3e77b855","duration_seconds":1421,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/pixworld-unifying-3d-scene-generation-and-reconstruction-in-pixel-space/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/pixworld-unifying-3d-scene-generation-and-reconstruction-in-pixel-space.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes","slug":"researchstudio-idea-an-evidence-grounded-research-ideation-skill-suite-from-ml-conference-outcomes","published_at":"2026-07-08T03:56:45+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/researchstudio-idea-an-evidence-grounded-research-ideation-skill-suite-from-ml-conference-outcomes","url":"https://share.transistor.fm/s/08b95944","duration_seconds":1621,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/researchstudio-idea-an-evidence-grounded-research-ideation-skill-suite-from-ml-conference-outcomes/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/researchstudio-idea-an-evidence-grounded-research-ideation-skill-suite-from-ml-conference-outcomes.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"MANCE: Manifold Aware Concept Erasure","slug":"mance-manifold-aware-concept-erasure","published_at":"2026-07-08T03:48:13+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/mance-manifold-aware-concept-erasure","url":"https://share.transistor.fm/s/b5808a0f","duration_seconds":1340,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/mance-manifold-aware-concept-erasure/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/mance-manifold-aware-concept-erasure.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"GigaWorld-1: A Roadmap to Build World Models for Robot Policy Evaluation","slug":"gigaworld-1-a-roadmap-to-build-world-models-for-robot-policy-evaluation","published_at":"2026-07-08T03:41:06+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/gigaworld-1-a-roadmap-to-build-world-models-for-robot-policy-evaluation","url":"https://share.transistor.fm/s/8e5d08e1","duration_seconds":1549,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/gigaworld-1-a-roadmap-to-build-world-models-for-robot-policy-evaluation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/gigaworld-1-a-roadmap-to-build-world-models-for-robot-policy-evaluation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Wan-Streamer v0.2: Higher Resolution, Same Latency","slug":"wan-streamer-v0-2-higher-resolution-same-latency","published_at":"2026-07-08T03:26:09+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/wan-streamer-v0-2-higher-resolution-same-latency","url":"https://share.transistor.fm/s/fcd90bf9","duration_seconds":1301,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/wan-streamer-v0-2-higher-resolution-same-latency/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/wan-streamer-v0-2-higher-resolution-same-latency.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"EVA-Client: A Unified Data Collection, Inference, and Deployment Framework for Embodied Policies on Real Robots","slug":"eva-client-a-unified-data-collection-inference-and-deployment-framework-for-embodied-policies-on-real-robots","published_at":"2026-07-08T03:18:58+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/eva-client-a-unified-data-collection-inference-and-deployment-framework-for-embodied-policies-on-real-robots","url":"https://share.transistor.fm/s/ad2d40dc","duration_seconds":1350,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/eva-client-a-unified-data-collection-inference-and-deployment-framework-for-embodied-policies-on-real-robots/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/eva-client-a-unified-data-collection-inference-and-deployment-framework-for-embodied-policies-on-real-robots.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning","slug":"the-mirage-of-optimizing-training-policies-monotonic-inference-policies-as-the-real-objective-for-llm-reinforcement-learning","published_at":"2026-07-07T03:51:00+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/the-mirage-of-optimizing-training-policies-monotonic-inference-policies-as-the-real-objective-for-llm-reinforcement-learning","url":"https://share.transistor.fm/s/e36ac227","duration_seconds":1285,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/the-mirage-of-optimizing-training-policies-monotonic-inference-policies-as-the-real-objective-for-llm-reinforcement-learning/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/the-mirage-of-optimizing-training-policies-monotonic-inference-policies-as-the-real-objective-for-llm-reinforcement-learning.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots","slug":"embodied-cpp-a-portable-inference-runtime-of-embodied-ai-models-on-heterogeneous-robots","published_at":"2026-07-07T03:43:08+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/embodied-cpp-a-portable-inference-runtime-of-embodied-ai-models-on-heterogeneous-robots","url":"https://share.transistor.fm/s/0e4399ab","duration_seconds":1350,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/embodied-cpp-a-portable-inference-runtime-of-embodied-ai-models-on-heterogeneous-robots/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/embodied-cpp-a-portable-inference-runtime-of-embodied-ai-models-on-heterogeneous-robots.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers","slug":"orbitquant-data-agnostic-quantization-for-image-and-video-diffusion-transformers","published_at":"2026-07-07T03:35:58+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/orbitquant-data-agnostic-quantization-for-image-and-video-diffusion-transformers","url":"https://share.transistor.fm/s/f03d2d1c","duration_seconds":1387,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/orbitquant-data-agnostic-quantization-for-image-and-video-diffusion-transformers/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/orbitquant-data-agnostic-quantization-for-image-and-video-diffusion-transformers.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon","slug":"vla-corrector-lightweight-detect-and-correct-inference-for-adaptive-action-horizon","published_at":"2026-07-07T03:28:20+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/vla-corrector-lightweight-detect-and-correct-inference-for-adaptive-action-horizon","url":"https://share.transistor.fm/s/69880cac","duration_seconds":1229,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/vla-corrector-lightweight-detect-and-correct-inference-for-adaptive-action-horizon/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/vla-corrector-lightweight-detect-and-correct-inference-for-adaptive-action-horizon.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"DataComp-VLM: Improved Open Datasets for Vision-Language Models","slug":"datacomp-vlm-improved-open-datasets-for-vision-language-models","published_at":"2026-07-07T03:21:00+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/datacomp-vlm-improved-open-datasets-for-vision-language-models","url":"https://share.transistor.fm/s/b3d340a7","duration_seconds":1355,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/datacomp-vlm-improved-open-datasets-for-vision-language-models/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/datacomp-vlm-improved-open-datasets-for-vision-language-models.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Program-as-Weights: A Programming Paradigm for Fuzzy Functions","slug":"program-as-weights-a-programming-paradigm-for-fuzzy-functions","published_at":"2026-07-04T03:58:49+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/program-as-weights-a-programming-paradigm-for-fuzzy-functions","url":"https://share.transistor.fm/s/196c54b8","duration_seconds":1466,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/program-as-weights-a-programming-paradigm-for-fuzzy-functions/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/program-as-weights-a-programming-paradigm-for-fuzzy-functions.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents","slug":"agenticsts-a-bounded-memory-testbed-for-long-horizon-llm-agents","published_at":"2026-07-04T03:50:58+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/agenticsts-a-bounded-memory-testbed-for-long-horizon-llm-agents","url":"https://share.transistor.fm/s/f25d5edd","duration_seconds":1410,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/agenticsts-a-bounded-memory-testbed-for-long-horizon-llm-agents/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/agenticsts-a-bounded-memory-testbed-for-long-horizon-llm-agents.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments","slug":"evopolicygym-evaluating-autonomous-policy-evolution-in-interactive-environments","published_at":"2026-07-04T03:42:54+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/evopolicygym-evaluating-autonomous-policy-evolution-in-interactive-environments","url":"https://share.transistor.fm/s/f30a665f","duration_seconds":1386,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/evopolicygym-evaluating-autonomous-policy-evolution-in-interactive-environments/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/evopolicygym-evaluating-autonomous-policy-evolution-in-interactive-environments.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Morphing into Hybrid Attention Models","slug":"morphing-into-hybrid-attention-models","published_at":"2026-07-04T03:35:07+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/morphing-into-hybrid-attention-models","url":"https://share.transistor.fm/s/975927dc","duration_seconds":1487,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/morphing-into-hybrid-attention-models/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/morphing-into-hybrid-attention-models.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"AgenticDataBench: A Comprehensive Benchmark for Data Agents","slug":"agenticdatabench-a-comprehensive-benchmark-for-data-agents","published_at":"2026-07-04T03:27:13+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/agenticdatabench-a-comprehensive-benchmark-for-data-agents","url":"https://share.transistor.fm/s/cbf201a6","duration_seconds":1298,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/agenticdatabench-a-comprehensive-benchmark-for-data-agents/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/agenticdatabench-a-comprehensive-benchmark-for-data-agents.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling","slug":"multi-resolution-flow-matching-training-free-diffusion-acceleration-via-staged-sampling","published_at":"2026-07-04T03:19:49+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/multi-resolution-flow-matching-training-free-diffusion-acceleration-via-staged-sampling","url":"https://share.transistor.fm/s/64025e78","duration_seconds":1349,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/multi-resolution-flow-matching-training-free-diffusion-acceleration-via-staged-sampling/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/multi-resolution-flow-matching-training-free-diffusion-acceleration-via-staged-sampling.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Orca: The World is in Your Mind","slug":"orca-the-world-is-in-your-mind","published_at":"2026-07-02T04:20:53+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/orca-the-world-is-in-your-mind","url":"https://share.transistor.fm/s/328d22cb","duration_seconds":1473,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/orca-the-world-is-in-your-mind/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/orca-the-world-is-in-your-mind.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Dockerless: Environment-Free Program Verifier for Coding Agents","slug":"dockerless-environment-free-program-verifier-for-coding-agents","published_at":"2026-07-02T04:12:53+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/dockerless-environment-free-program-verifier-for-coding-agents","url":"https://share.transistor.fm/s/bbbc53ce","duration_seconds":1452,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/dockerless-environment-free-program-verifier-for-coding-agents/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/dockerless-environment-free-program-verifier-for-coding-agents.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"DOPD: Dual On-policy Distillation","slug":"dopd-dual-on-policy-distillation","published_at":"2026-07-02T04:04:36+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/dopd-dual-on-policy-distillation","url":"https://share.transistor.fm/s/ba4a0597","duration_seconds":1526,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/dopd-dual-on-policy-distillation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/dopd-dual-on-policy-distillation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models","slug":"does-vla-even-know-the-basics-measuring-commonsense-and-world-knowledge-retention-in-vision-language-action-models","published_at":"2026-07-02T03:54:05+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/does-vla-even-know-the-basics-measuring-commonsense-and-world-knowledge-retention-in-vision-language-action-models","url":"https://share.transistor.fm/s/e917439b","duration_seconds":1261,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/does-vla-even-know-the-basics-measuring-commonsense-and-world-knowledge-retention-in-vision-language-action-models/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/does-vla-even-know-the-basics-measuring-commonsense-and-world-knowledge-retention-in-vision-language-action-models.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views","slug":"scenes-as-objects-not-primitives-instance-structured-3d-tokenization-from-unposed-views","published_at":"2026-07-02T03:46:17+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/scenes-as-objects-not-primitives-instance-structured-3d-tokenization-from-unposed-views","url":"https://share.transistor.fm/s/2d8379e9","duration_seconds":1435,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/scenes-as-objects-not-primitives-instance-structured-3d-tokenization-from-unposed-views/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/scenes-as-objects-not-primitives-instance-structured-3d-tokenization-from-unposed-views.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"GEAR: Guided End-to-End AutoRegression for Image Synthesis","slug":"gear-guided-end-to-end-autoregression-for-image-synthesis","published_at":"2026-07-02T03:37:50+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/gear-guided-end-to-end-autoregression-for-image-synthesis","url":"https://share.transistor.fm/s/a3d4e787","duration_seconds":1590,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/gear-guided-end-to-end-autoregression-for-image-synthesis/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/gear-guided-end-to-end-autoregression-for-image-synthesis.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Multi-Block Diffusion Language Models","slug":"multi-block-diffusion-language-models","published_at":"2026-07-02T03:27:02+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/multi-block-diffusion-language-models","url":"https://share.transistor.fm/s/977ccebb","duration_seconds":1432,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/multi-block-diffusion-language-models/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/multi-block-diffusion-language-models.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Agentic Abstention: Do Agents Know When to Stop Instead of Act?","slug":"agentic-abstention-do-agents-know-when-to-stop-instead-of-act","published_at":"2026-07-01T04:33:49+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/agentic-abstention-do-agents-know-when-to-stop-instead-of-act","url":"https://share.transistor.fm/s/89ee6fbd","duration_seconds":1453,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/agentic-abstention-do-agents-know-when-to-stop-instead-of-act/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/agentic-abstention-do-agents-know-when-to-stop-instead-of-act.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing","slug":"liveedit-towards-real-time-diffusion-based-streaming-video-editing","published_at":"2026-07-01T04:26:00+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/liveedit-towards-real-time-diffusion-based-streaming-video-editing","url":"https://share.transistor.fm/s/f9ed41cb","duration_seconds":1398,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/liveedit-towards-real-time-diffusion-based-streaming-video-editing/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/liveedit-towards-real-time-diffusion-based-streaming-video-editing.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent","slug":"scaling-the-horizon-not-the-parameters-reaching-trillion-parameter-performance-with-a-35b-agent","published_at":"2026-07-01T04:17:37+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/scaling-the-horizon-not-the-parameters-reaching-trillion-parameter-performance-with-a-35b-agent","url":"https://share.transistor.fm/s/1744418d","duration_seconds":1583,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/scaling-the-horizon-not-the-parameters-reaching-trillion-parameter-performance-with-a-35b-agent/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/scaling-the-horizon-not-the-parameters-reaching-trillion-parameter-performance-with-a-35b-agent.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents","slug":"tua-bench-a-benchmark-for-general-purpose-terminal-use-agents","published_at":"2026-07-01T04:08:20+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/tua-bench-a-benchmark-for-general-purpose-terminal-use-agents","url":"https://share.transistor.fm/s/2777ff4a","duration_seconds":1363,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/tua-bench-a-benchmark-for-general-purpose-terminal-use-agents/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/tua-bench-a-benchmark-for-general-purpose-terminal-use-agents.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Beyond IID: How General Are Tabular Foundation Models, Really?","slug":"beyond-iid-how-general-are-tabular-foundation-models-really","published_at":"2026-07-01T03:58:47+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/beyond-iid-how-general-are-tabular-foundation-models-really","url":"https://share.transistor.fm/s/a625c151","duration_seconds":1363,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/beyond-iid-how-general-are-tabular-foundation-models-really/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/beyond-iid-how-general-are-tabular-foundation-models-really.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Trimming the Long-Tail of Visual World Modeling Evaluation","slug":"trimming-the-long-tail-of-visual-world-modeling-evaluation","published_at":"2026-07-01T03:51:08+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/trimming-the-long-tail-of-visual-world-modeling-evaluation","url":"https://share.transistor.fm/s/91a75afe","duration_seconds":1554,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/trimming-the-long-tail-of-visual-world-modeling-evaluation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/trimming-the-long-tail-of-visual-world-modeling-evaluation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"AsyncOPD: How Stale Can On-Policy Distillation Be?","slug":"asyncopd-how-stale-can-on-policy-distillation-be","published_at":"2026-07-01T03:42:20+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/asyncopd-how-stale-can-on-policy-distillation-be","url":"https://share.transistor.fm/s/f0992ff3","duration_seconds":1358,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/asyncopd-how-stale-can-on-policy-distillation-be/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/asyncopd-how-stale-can-on-policy-distillation-be.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Video-MME-Logical: A Controlled Diagnostic Benchmark for Video Temporal-Logical Reasoning","slug":"video-mme-logical-a-controlled-diagnostic-benchmark-for-video-temporal-logical-reasoning","published_at":"2026-07-01T03:34:51+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/video-mme-logical-a-controlled-diagnostic-benchmark-for-video-temporal-logical-reasoning","url":"https://share.transistor.fm/s/ff30966b","duration_seconds":1240,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/video-mme-logical-a-controlled-diagnostic-benchmark-for-video-temporal-logical-reasoning/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/video-mme-logical-a-controlled-diagnostic-benchmark-for-video-temporal-logical-reasoning.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction","slug":"bridging-videoqa-and-video-guided-agentic-tasks-via-generalized-keyframe-extraction","published_at":"2026-07-01T03:27:48+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/bridging-videoqa-and-video-guided-agentic-tasks-via-generalized-keyframe-extraction","url":"https://share.transistor.fm/s/19acb893","duration_seconds":1370,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/bridging-videoqa-and-video-guided-agentic-tasks-via-generalized-keyframe-extraction/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/bridging-videoqa-and-video-guided-agentic-tasks-via-generalized-keyframe-extraction.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation","slug":"physisforcing-physics-reinforced-world-simulator-for-robotic-manipulation","published_at":"2026-06-30T03:45:16+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/physisforcing-physics-reinforced-world-simulator-for-robotic-manipulation","url":"https://share.transistor.fm/s/8100e4d4","duration_seconds":1278,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/physisforcing-physics-reinforced-world-simulator-for-robotic-manipulation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/physisforcing-physics-reinforced-world-simulator-for-robotic-manipulation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Translation as a Bridging Action: Transferring Manipulation Skills from Humans to Robots","slug":"translation-as-a-bridging-action-transferring-manipulation-skills-from-humans-to-robots","published_at":"2026-06-30T03:37:12+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/translation-as-a-bridging-action-transferring-manipulation-skills-from-humans-to-robots","url":"https://share.transistor.fm/s/db9eff5d","duration_seconds":1436,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/translation-as-a-bridging-action-transferring-manipulation-skills-from-humans-to-robots/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/translation-as-a-bridging-action-transferring-manipulation-skills-from-humans-to-robots.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Qwen-Image-2.0-RL Technical Report","slug":"qwen-image-2-0-rl-technical-report","published_at":"2026-06-30T03:28:09+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/qwen-image-2-0-rl-technical-report","url":"https://share.transistor.fm/s/e0b171e0","duration_seconds":1630,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/qwen-image-2-0-rl-technical-report/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/qwen-image-2-0-rl-technical-report.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"DanceOPD: On-Policy Generative Field Distillation","slug":"danceopd-on-policy-generative-field-distillation","published_at":"2026-06-28T06:12:25+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/danceopd-on-policy-generative-field-distillation","url":"https://share.transistor.fm/s/0a694477","duration_seconds":1546,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/danceopd-on-policy-generative-field-distillation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/danceopd-on-policy-generative-field-distillation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"In-Context World Modeling for Robotic Control","slug":"in-context-world-modeling-for-robotic-control","published_at":"2026-06-28T06:04:20+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/in-context-world-modeling-for-robotic-control","url":"https://share.transistor.fm/s/6fccae0b","duration_seconds":1403,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/in-context-world-modeling-for-robotic-control/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/in-context-world-modeling-for-robotic-control.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation","slug":"qwen-image-agent-bridging-the-context-gap-in-real-world-image-generation","published_at":"2026-06-28T05:56:31+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/qwen-image-agent-bridging-the-context-gap-in-real-world-image-generation","url":"https://share.transistor.fm/s/bfdb9a71","duration_seconds":1286,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/qwen-image-agent-bridging-the-context-gap-in-real-world-image-generation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/qwen-image-agent-bridging-the-context-gap-in-real-world-image-generation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning","slug":"opid-on-policy-skill-distillation-for-agentic-reinforcement-learning","published_at":"2026-06-28T05:49:14+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/opid-on-policy-skill-distillation-for-agentic-reinforcement-learning","url":"https://share.transistor.fm/s/a6ccf440","duration_seconds":1432,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/opid-on-policy-skill-distillation-for-agentic-reinforcement-learning/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/opid-on-policy-skill-distillation-for-agentic-reinforcement-learning.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"The Verification Horizon: No Silver Bullet for Coding Agent Rewards","slug":"the-verification-horizon-no-silver-bullet-for-coding-agent-rewards","published_at":"2026-06-28T05:41:33+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/the-verification-horizon-no-silver-bullet-for-coding-agent-rewards","url":"https://share.transistor.fm/s/81b0f9d9","duration_seconds":1375,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/the-verification-horizon-no-silver-bullet-for-coding-agent-rewards/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/the-verification-horizon-no-silver-bullet-for-coding-agent-rewards.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"ViQ: Text-Aligned Visual Quantized Representations at Any Resolution","slug":"viq-text-aligned-visual-quantized-representations-at-any-resolution","published_at":"2026-06-28T05:34:03+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/viq-text-aligned-visual-quantized-representations-at-any-resolution","url":"https://share.transistor.fm/s/8864ed79","duration_seconds":1552,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/viq-text-aligned-visual-quantized-representations-at-any-resolution/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/viq-text-aligned-visual-quantized-representations-at-any-resolution.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments","slug":"evoarena-tracking-memory-evolution-for-robust-llm-agents-in-dynamic-environments","published_at":"2026-06-13T04:30:01+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/evoarena-tracking-memory-evolution-for-robust-llm-agents-in-dynamic-environments","url":"https://share.transistor.fm/s/1dcb7985","duration_seconds":1446,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/evoarena-tracking-memory-evolution-for-robust-llm-agents-in-dynamic-environments/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/evoarena-tracking-memory-evolution-for-robust-llm-agents-in-dynamic-environments.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"MiniMax Sparse Attention","slug":"minimax-sparse-attention","published_at":"2026-06-13T04:29:39+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/minimax-sparse-attention","url":"https://share.transistor.fm/s/d0da285b","duration_seconds":1562,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/minimax-sparse-attention/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/minimax-sparse-attention.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning","slug":"spatialclaw-rethinking-action-interface-for-agentic-spatial-reasoning","published_at":"2026-06-13T04:29:18+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/spatialclaw-rethinking-action-interface-for-agentic-spatial-reasoning","url":"https://share.transistor.fm/s/890ea944","duration_seconds":1374,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/spatialclaw-rethinking-action-interface-for-agentic-spatial-reasoning/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/spatialclaw-rethinking-action-interface-for-agentic-spatial-reasoning.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"InterleaveThinker: Reinforcing Agentic Interleaved Generation","slug":"interleavethinker-reinforcing-agentic-interleaved-generation","published_at":"2026-06-13T04:28:56+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/interleavethinker-reinforcing-agentic-interleaved-generation","url":"https://share.transistor.fm/s/c1b1f49f","duration_seconds":1271,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/interleavethinker-reinforcing-agentic-interleaved-generation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/interleavethinker-reinforcing-agentic-interleaved-generation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents","slug":"fort-searcher-synthesizing-shortcut-resistant-search-tasks-for-training-deep-search-agents","published_at":"2026-06-13T04:28:35+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/fort-searcher-synthesizing-shortcut-resistant-search-tasks-for-training-deep-search-agents","url":"https://share.transistor.fm/s/37fe9098","duration_seconds":1394,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/fort-searcher-synthesizing-shortcut-resistant-search-tasks-for-training-deep-search-agents/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/fort-searcher-synthesizing-shortcut-resistant-search-tasks-for-training-deep-search-agents.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?","slug":"robust-u1-can-mllms-self-recover-corrupted-visual-content-for-robust-understanding","published_at":"2026-06-13T04:28:13+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/robust-u1-can-mllms-self-recover-corrupted-visual-content-for-robust-understanding","url":"https://share.transistor.fm/s/8c03bbf5","duration_seconds":1228,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/robust-u1-can-mllms-self-recover-corrupted-visual-content-for-robust-understanding/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/robust-u1-can-mllms-self-recover-corrupted-visual-content-for-robust-understanding.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling","slug":"maxproof-scaling-mathematical-proof-with-generative-verifier-rl-and-population-level-test-time-scaling","published_at":"2026-06-13T04:27:52+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/maxproof-scaling-mathematical-proof-with-generative-verifier-rl-and-population-level-test-time-scaling","url":"https://share.transistor.fm/s/aa61258c","duration_seconds":1430,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/maxproof-scaling-mathematical-proof-with-generative-verifier-rl-and-population-level-test-time-scaling/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/maxproof-scaling-mathematical-proof-with-generative-verifier-rl-and-population-level-test-time-scaling.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces","slug":"weavebench-a-long-horizon-real-world-benchmark-for-computer-use-agents-with-hybrid-interfaces","published_at":"2026-06-13T04:27:30+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/weavebench-a-long-horizon-real-world-benchmark-for-computer-use-agents-with-hybrid-interfaces","url":"https://share.transistor.fm/s/de097270","duration_seconds":1233,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/weavebench-a-long-horizon-real-world-benchmark-for-computer-use-agents-with-hybrid-interfaces/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/weavebench-a-long-horizon-real-world-benchmark-for-computer-use-agents-with-hybrid-interfaces.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories","slug":"labvla-grounding-vision-language-action-models-in-scientific-laboratories","published_at":"2026-06-13T04:27:09+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/labvla-grounding-vision-language-action-models-in-scientific-laboratories","url":"https://share.transistor.fm/s/0f6333bd","duration_seconds":1395,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/labvla-grounding-vision-language-action-models-in-scientific-laboratories/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/labvla-grounding-vision-language-action-models-in-scientific-laboratories.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers","slug":"hydra-x-native-unified-multimodal-models-with-holistic-visual-tokenizers","published_at":"2026-06-13T04:26:47+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/hydra-x-native-unified-multimodal-models-with-holistic-visual-tokenizers","url":"https://share.transistor.fm/s/fd30be8d","duration_seconds":1248,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/hydra-x-native-unified-multimodal-models-with-holistic-visual-tokenizers/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/hydra-x-native-unified-multimodal-models-with-holistic-visual-tokenizers.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"ABot-Earth 0.5: Generative 3D Earth Model","slug":"abot-earth-0-5-generative-3d-earth-model","published_at":"2026-06-11T04:29:52+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/abot-earth-0-5-generative-3d-earth-model","url":"https://share.transistor.fm/s/5e87e298","duration_seconds":1367,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/abot-earth-0-5-generative-3d-earth-model/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/abot-earth-0-5-generative-3d-earth-model.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Kwai Keye-VL-2.0 Technical Report","slug":"kwai-keye-vl-2-0-technical-report","published_at":"2026-06-11T04:29:30+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/kwai-keye-vl-2-0-technical-report","url":"https://share.transistor.fm/s/3be59bc5","duration_seconds":1532,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/kwai-keye-vl-2-0-technical-report/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/kwai-keye-vl-2-0-technical-report.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution","slug":"role-agent-bootstrapping-llm-agents-via-dual-role-evolution","published_at":"2026-06-11T04:29:07+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/role-agent-bootstrapping-llm-agents-via-dual-role-evolution","url":"https://share.transistor.fm/s/fdd69514","duration_seconds":1369,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/role-agent-bootstrapping-llm-agents-via-dual-role-evolution/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/role-agent-bootstrapping-llm-agents-via-dual-role-evolution.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference","slug":"evolving-agents-in-the-dark-retrospective-harness-optimization-via-self-preference","published_at":"2026-06-11T04:28:45+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/evolving-agents-in-the-dark-retrospective-harness-optimization-via-self-preference","url":"https://share.transistor.fm/s/c45684dd","duration_seconds":1269,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/evolving-agents-in-the-dark-retrospective-harness-optimization-via-self-preference/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/evolving-agents-in-the-dark-retrospective-harness-optimization-via-self-preference.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research","slug":"searchswarm-towards-delegation-intelligence-in-agentic-llms-for-long-horizon-deep-research","published_at":"2026-06-11T04:28:22+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/searchswarm-towards-delegation-intelligence-in-agentic-llms-for-long-horizon-deep-research","url":"https://share.transistor.fm/s/6a886f59","duration_seconds":1437,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/searchswarm-towards-delegation-intelligence-in-agentic-llms-for-long-horizon-deep-research/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/searchswarm-towards-delegation-intelligence-in-agentic-llms-for-long-horizon-deep-research.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning","slug":"beyond-uniform-token-level-trust-region-in-llm-reinforcement-learning","published_at":"2026-06-11T04:27:59+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/beyond-uniform-token-level-trust-region-in-llm-reinforcement-learning","url":"https://share.transistor.fm/s/dc018303","duration_seconds":1589,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/beyond-uniform-token-level-trust-region-in-llm-reinforcement-learning/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/beyond-uniform-token-level-trust-region-in-llm-reinforcement-learning.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models","slug":"flow-dppo-divergence-proximal-policy-optimization-for-flow-matching-models","published_at":"2026-06-11T04:27:36+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/flow-dppo-divergence-proximal-policy-optimization-for-flow-matching-models","url":"https://share.transistor.fm/s/3c9dc9d2","duration_seconds":1300,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/flow-dppo-divergence-proximal-policy-optimization-for-flow-matching-models/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/flow-dppo-divergence-proximal-policy-optimization-for-flow-matching-models.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"SCAIL-2: Unifying Controlled Character Animation with End-to-end In-Context Conditioning","slug":"scail-2-unifying-controlled-character-animation-with-end-to-end-in-context-conditioning","published_at":"2026-06-11T04:27:14+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/scail-2-unifying-controlled-character-animation-with-end-to-end-in-context-conditioning","url":"https://share.transistor.fm/s/47d67499","duration_seconds":1321,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/scail-2-unifying-controlled-character-animation-with-end-to-end-in-context-conditioning/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/scail-2-unifying-controlled-character-animation-with-end-to-end-in-context-conditioning.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Lip Forcing: Few-Step Autoregressive Diffusion for Real-time Lip Synchronization","slug":"lip-forcing-few-step-autoregressive-diffusion-for-real-time-lip-synchronization","published_at":"2026-06-11T04:26:51+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/lip-forcing-few-step-autoregressive-diffusion-for-real-time-lip-synchronization","url":"https://share.transistor.fm/s/39e08487","duration_seconds":1468,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/lip-forcing-few-step-autoregressive-diffusion-for-real-time-lip-synchronization/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/lip-forcing-few-step-autoregressive-diffusion-for-real-time-lip-synchronization.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Agents' Last Exam","slug":"agents-last-exam","published_at":"2026-06-10T04:36:19+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/agents-last-exam","url":"https://share.transistor.fm/s/773034a2","duration_seconds":1500,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/agents-last-exam/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/agents-last-exam.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"SWE-Explore: Benchmarking How Coding Agents Explore Repositories","slug":"swe-explore-benchmarking-how-coding-agents-explore-repositories","published_at":"2026-06-10T04:35:57+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/swe-explore-benchmarking-how-coding-agents-explore-repositories","url":"https://share.transistor.fm/s/75386176","duration_seconds":1387,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/swe-explore-benchmarking-how-coding-agents-explore-repositories/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/swe-explore-benchmarking-how-coding-agents-explore-repositories.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"On the Geometry of On-Policy Distillation","slug":"on-the-geometry-of-on-policy-distillation","published_at":"2026-06-10T04:35:36+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/on-the-geometry-of-on-policy-distillation","url":"https://share.transistor.fm/s/1b89b053","duration_seconds":1613,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/on-the-geometry-of-on-policy-distillation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/on-the-geometry-of-on-policy-distillation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents","slug":"latentskill-from-in-context-textual-skills-to-in-weight-latent-skills-for-llm-agents","published_at":"2026-06-10T04:35:14+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/latentskill-from-in-context-textual-skills-to-in-weight-latent-skills-for-llm-agents","url":"https://share.transistor.fm/s/7f04106c","duration_seconds":1322,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/latentskill-from-in-context-textual-skills-to-in-weight-latent-skills-for-llm-agents/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/latentskill-from-in-context-textual-skills-to-in-weight-latent-skills-for-llm-agents.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Latent Spatial Memory for Video World Models","slug":"latent-spatial-memory-for-video-world-models","published_at":"2026-06-10T04:34:53+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/latent-spatial-memory-for-video-world-models","url":"https://share.transistor.fm/s/54ecc822","duration_seconds":1504,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/latent-spatial-memory-for-video-world-models/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/latent-spatial-memory-for-video-world-models.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention","slug":"flashmemory-deepseek-v4-lightning-index-ultra-long-context-via-lookahead-sparse-attention","published_at":"2026-06-10T04:34:31+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/flashmemory-deepseek-v4-lightning-index-ultra-long-context-via-lookahead-sparse-attention","url":"https://share.transistor.fm/s/f0cfc106","duration_seconds":1307,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/flashmemory-deepseek-v4-lightning-index-ultra-long-context-via-lookahead-sparse-attention/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/flashmemory-deepseek-v4-lightning-index-ultra-long-context-via-lookahead-sparse-attention.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"CoVEBench: Can Video Editing Models Handle Complex Instructions?","slug":"covebench-can-video-editing-models-handle-complex-instructions","published_at":"2026-06-10T04:34:10+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/covebench-can-video-editing-models-handle-complex-instructions","url":"https://share.transistor.fm/s/fef810f7","duration_seconds":1339,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/covebench-can-video-editing-models-handle-complex-instructions/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/covebench-can-video-editing-models-handle-complex-instructions.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks","slug":"spatialworld-benchmarking-interactive-spatial-reasoning-of-multimodal-agents-in-real-world-tasks","published_at":"2026-06-10T04:33:48+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/spatialworld-benchmarking-interactive-spatial-reasoning-of-multimodal-agents-in-real-world-tasks","url":"https://share.transistor.fm/s/839d05f7","duration_seconds":1459,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/spatialworld-benchmarking-interactive-spatial-reasoning-of-multimodal-agents-in-real-world-tasks/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/spatialworld-benchmarking-interactive-spatial-reasoning-of-multimodal-agents-in-real-world-tasks.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Human Psychometric Questionnaires Mischaracterize LLM Behavior","slug":"human-psychometric-questionnaires-mischaracterize-llm-behavior","published_at":"2026-06-10T04:33:27+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/human-psychometric-questionnaires-mischaracterize-llm-behavior","url":"https://share.transistor.fm/s/30fb1fb6","duration_seconds":1508,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/human-psychometric-questionnaires-mischaracterize-llm-behavior/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/human-psychometric-questionnaires-mischaracterize-llm-behavior.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Echo-Memory: A Controlled Study of Memory in Action World Models","slug":"echo-memory-a-controlled-study-of-memory-in-action-world-models","published_at":"2026-06-10T04:33:05+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/echo-memory-a-controlled-study-of-memory-in-action-world-models","url":"https://share.transistor.fm/s/a1d42248","duration_seconds":1280,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/echo-memory-a-controlled-study-of-memory-in-action-world-models/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/echo-memory-a-controlled-study-of-memory-in-action-world-models.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"From Activation to Causality: Discovery of Causal Visual Representations in the Human Brain","slug":"from-activation-to-causality-discovery-of-causal-visual-representations-in-the-human-brain","published_at":"2026-06-04T03:56:40+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/from-activation-to-causality-discovery-of-causal-visual-representations-in-the-human-brain","url":"https://share.transistor.fm/s/00f6616a","duration_seconds":1400,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/from-activation-to-causality-discovery-of-causal-visual-representations-in-the-human-brain/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/from-activation-to-causality-discovery-of-causal-visual-representations-in-the-human-brain.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking","slug":"humanoid-gpt-scaling-data-and-structure-for-zero-shot-motion-tracking","published_at":"2026-06-04T03:56:18+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/humanoid-gpt-scaling-data-and-structure-for-zero-shot-motion-tracking","url":"https://share.transistor.fm/s/7e729012","duration_seconds":1540,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/humanoid-gpt-scaling-data-and-structure-for-zero-shot-motion-tracking/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/humanoid-gpt-scaling-data-and-structure-for-zero-shot-motion-tracking.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Trust Region On-Policy Distillation","slug":"trust-region-on-policy-distillation","published_at":"2026-06-04T03:55:57+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/trust-region-on-policy-distillation","url":"https://share.transistor.fm/s/2bb037b7","duration_seconds":1445,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/trust-region-on-policy-distillation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/trust-region-on-policy-distillation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks","slug":"kvarn-variance-normalized-kv-cache-quantization-mitigates-error-accumulation-in-reasoning-tasks","published_at":"2026-06-04T03:55:36+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/kvarn-variance-normalized-kv-cache-quantization-mitigates-error-accumulation-in-reasoning-tasks","url":"https://share.transistor.fm/s/397d6a64","duration_seconds":1360,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/kvarn-variance-normalized-kv-cache-quantization-mitigates-error-accumulation-in-reasoning-tasks/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/kvarn-variance-normalized-kv-cache-quantization-mitigates-error-accumulation-in-reasoning-tasks.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation","slug":"colleague-skill-automated-ai-skill-generation-via-expert-knowledge-distillation","published_at":"2026-06-02T04:14:56+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/colleague-skill-automated-ai-skill-generation-via-expert-knowledge-distillation","url":"https://share.transistor.fm/s/dc215157","duration_seconds":1278,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/colleague-skill-automated-ai-skill-generation-via-expert-knowledge-distillation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/colleague-skill-automated-ai-skill-generation-via-expert-knowledge-distillation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Representation Forcing for Bottleneck-Free Unified Multimodal Models","slug":"representation-forcing-for-bottleneck-free-unified-multimodal-models","published_at":"2026-06-02T04:14:34+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/representation-forcing-for-bottleneck-free-unified-multimodal-models","url":"https://share.transistor.fm/s/fa685904","duration_seconds":1466,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/representation-forcing-for-bottleneck-free-unified-multimodal-models/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/representation-forcing-for-bottleneck-free-unified-multimodal-models.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Mellum2 Technical Report","slug":"mellum2-technical-report","published_at":"2026-06-02T04:14:11+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/mellum2-technical-report","url":"https://share.transistor.fm/s/562a6bc2","duration_seconds":1302,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/mellum2-technical-report/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/mellum2-technical-report.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Function2Scene: 3D Indoor Scene Layout from Functional Specifications","slug":"function2scene-3d-indoor-scene-layout-from-functional-specifications","published_at":"2026-06-02T04:13:49+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/function2scene-3d-indoor-scene-layout-from-functional-specifications","url":"https://share.transistor.fm/s/7837f3e1","duration_seconds":1318,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/function2scene-3d-indoor-scene-layout-from-functional-specifications/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/function2scene-3d-indoor-scene-layout-from-functional-specifications.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"GGT-100K: Generative Ground Truth for Generalizable Real-World Image Restoration","slug":"ggt-100k-generative-ground-truth-for-generalizable-real-world-image-restoration","published_at":"2026-06-02T04:13:27+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/ggt-100k-generative-ground-truth-for-generalizable-real-world-image-restoration","url":"https://share.transistor.fm/s/8b7766eb","duration_seconds":1397,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/ggt-100k-generative-ground-truth-for-generalizable-real-world-image-restoration/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/ggt-100k-generative-ground-truth-for-generalizable-real-world-image-restoration.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion Transformer","slug":"towards-streaming-synchronized-spatial-audio-generation-via-autoregressive-diffusion-transformer","published_at":"2026-06-02T04:13:05+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/towards-streaming-synchronized-spatial-audio-generation-via-autoregressive-diffusion-transformer","url":"https://share.transistor.fm/s/cea1adc1","duration_seconds":1576,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/towards-streaming-synchronized-spatial-audio-generation-via-autoregressive-diffusion-transformer/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/towards-streaming-synchronized-spatial-audio-generation-via-autoregressive-diffusion-transformer.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation","slug":"transitlm-a-large-scale-dataset-and-benchmark-for-map-free-transit-route-generation","published_at":"2026-05-23T04:29:47+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/transitlm-a-large-scale-dataset-and-benchmark-for-map-free-transit-route-generation","url":"https://share.transistor.fm/s/6639c3a5","duration_seconds":1375,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/transitlm-a-large-scale-dataset-and-benchmark-for-map-free-transit-route-generation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/transitlm-a-large-scale-dataset-and-benchmark-for-map-free-transit-route-generation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality?","slug":"perception-or-prejudice-can-mllms-go-beyond-first-impressions-of-personality","published_at":"2026-05-23T04:29:24+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/perception-or-prejudice-can-mllms-go-beyond-first-impressions-of-personality","url":"https://share.transistor.fm/s/05a1e45c","duration_seconds":1433,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/perception-or-prejudice-can-mllms-go-beyond-first-impressions-of-personality/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/perception-or-prejudice-can-mllms-go-beyond-first-impressions-of-personality.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards","slug":"delta-discriminative-token-credit-assignment-for-reinforcement-learning-from-verifiable-rewards","published_at":"2026-05-23T04:29:01+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/delta-discriminative-token-credit-assignment-for-reinforcement-learning-from-verifiable-rewards","url":"https://share.transistor.fm/s/428a7c58","duration_seconds":1286,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/delta-discriminative-token-credit-assignment-for-reinforcement-learning-from-verifiable-rewards/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/delta-discriminative-token-credit-assignment-for-reinforcement-learning-from-verifiable-rewards.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"$π$-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows","slug":"bench-evaluating-proactive-personal-assistant-agents-in-long-horizon-workflows","published_at":"2026-05-23T04:28:38+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/bench-evaluating-proactive-personal-assistant-agents-in-long-horizon-workflows","url":"https://share.transistor.fm/s/13d9349a","duration_seconds":1352,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/bench-evaluating-proactive-personal-assistant-agents-in-long-horizon-workflows/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/bench-evaluating-proactive-personal-assistant-agents-in-long-horizon-workflows.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps","slug":"full-attention-strikes-back-transferring-full-attention-into-sparse-within-hundred-training-steps","published_at":"2026-05-23T04:28:16+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/full-attention-strikes-back-transferring-full-attention-into-sparse-within-hundred-training-steps","url":"https://share.transistor.fm/s/d7961e0a","duration_seconds":1158,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/full-attention-strikes-back-transferring-full-attention-into-sparse-within-hundred-training-steps/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/full-attention-strikes-back-transferring-full-attention-into-sparse-within-hundred-training-steps.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"ACC: Compiling Agent Trajectories for Long-Context Training","slug":"acc-compiling-agent-trajectories-for-long-context-training","published_at":"2026-05-23T04:27:53+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/acc-compiling-agent-trajectories-for-long-context-training","url":"https://share.transistor.fm/s/09dad681","duration_seconds":1485,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/acc-compiling-agent-trajectories-for-long-context-training/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/acc-compiling-agent-trajectories-for-long-context-training.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects","slug":"physx-omni-unified-simulation-ready-physical-3d-generation-for-rigid-deformable-and-articulated-objects","published_at":"2026-05-23T04:27:30+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/physx-omni-unified-simulation-ready-physical-3d-generation-for-rigid-deformable-and-articulated-objects","url":"https://share.transistor.fm/s/56e99b00","duration_seconds":1395,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/physx-omni-unified-simulation-ready-physical-3d-generation-for-rigid-deformable-and-articulated-objects/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/physx-omni-unified-simulation-ready-physical-3d-generation-for-rigid-deformable-and-articulated-objects.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning","slug":"latentomni-rethinking-omni-modal-understanding-via-unified-audio-visual-latent-reasoning","published_at":"2026-05-23T04:27:07+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/latentomni-rethinking-omni-modal-understanding-via-unified-audio-visual-latent-reasoning","url":"https://share.transistor.fm/s/60bce2d7","duration_seconds":1323,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/latentomni-rethinking-omni-modal-understanding-via-unified-audio-visual-latent-reasoning/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/latentomni-rethinking-omni-modal-understanding-via-unified-audio-visual-latent-reasoning.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Spreadsheet-RL: Advancing Large Language Model Agents on Realistic Spreadsheet Tasks via Reinforcement Learning","slug":"spreadsheet-rl-advancing-large-language-model-agents-on-realistic-spreadsheet-tasks-via-reinforcement-learning","published_at":"2026-05-23T04:26:44+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/spreadsheet-rl-advancing-large-language-model-agents-on-realistic-spreadsheet-tasks-via-reinforcement-learning","url":"https://share.transistor.fm/s/55570710","duration_seconds":1345,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/spreadsheet-rl-advancing-large-language-model-agents-on-realistic-spreadsheet-tasks-via-reinforcement-learning/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/spreadsheet-rl-advancing-large-language-model-agents-on-realistic-spreadsheet-tasks-via-reinforcement-learning.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"WorldKV: Efficient World Memory with World Retrieval and Compression","slug":"worldkv-efficient-world-memory-with-world-retrieval-and-compression","published_at":"2026-05-23T04:26:21+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/worldkv-efficient-world-memory-with-world-retrieval-and-compression","url":"https://share.transistor.fm/s/1ceb95e4","duration_seconds":1351,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/worldkv-efficient-world-memory-with-world-retrieval-and-compression/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/worldkv-efficient-world-memory-with-world-retrieval-and-compression.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining","slug":"video2gui-synthesizing-large-scale-interaction-trajectories-for-generalized-gui-agent-pretraining","published_at":"2026-05-22T04:02:35+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/video2gui-synthesizing-large-scale-interaction-trajectories-for-generalized-gui-agent-pretraining","url":"https://share.transistor.fm/s/8e5e5cca","duration_seconds":1171,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/video2gui-synthesizing-large-scale-interaction-trajectories-for-generalized-gui-agent-pretraining/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/video2gui-synthesizing-large-scale-interaction-trajectories-for-generalized-gui-agent-pretraining.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation","slug":"mega-asr-towards-in-the-wild-2-speech-recognition-via-scaling-up-real-world-acoustic-simulation","published_at":"2026-05-22T04:02:14+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/mega-asr-towards-in-the-wild-2-speech-recognition-via-scaling-up-real-world-acoustic-simulation","url":"https://share.transistor.fm/s/c0e9ca22","duration_seconds":1381,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/mega-asr-towards-in-the-wild-2-speech-recognition-via-scaling-up-real-world-acoustic-simulation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/mega-asr-towards-in-the-wild-2-speech-recognition-via-scaling-up-real-world-acoustic-simulation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos","slug":"enhancing-train-free-infinite-frame-generation-for-consistent-long-videos","published_at":"2026-05-22T04:01:52+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/enhancing-train-free-infinite-frame-generation-for-consistent-long-videos","url":"https://share.transistor.fm/s/a48cc988","duration_seconds":1501,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/enhancing-train-free-infinite-frame-generation-for-consistent-long-videos/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/enhancing-train-free-infinite-frame-generation-for-consistent-long-videos.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Tools","slug":"indusagent-reinforcing-open-vocabulary-industrial-anomaly-detection-with-agentic-tools","published_at":"2026-05-22T04:01:20+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/indusagent-reinforcing-open-vocabulary-industrial-anomaly-detection-with-agentic-tools","url":"https://share.transistor.fm/s/e66ff5df","duration_seconds":1456,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/indusagent-reinforcing-open-vocabulary-industrial-anomaly-detection-with-agentic-tools/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/indusagent-reinforcing-open-vocabulary-industrial-anomaly-detection-with-agentic-tools.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"When Vision Speaks for Sound","slug":"when-vision-speaks-for-sound","published_at":"2026-05-21T04:38:20+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/when-vision-speaks-for-sound","url":"https://share.transistor.fm/s/726dcbfe","duration_seconds":1381,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/when-vision-speaks-for-sound/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/when-vision-speaks-for-sound.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Active Learners as Efficient PRP Rerankers","slug":"active-learners-as-efficient-prp-rerankers","published_at":"2026-05-21T04:37:55+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/active-learners-as-efficient-prp-rerankers","url":"https://share.transistor.fm/s/b44a223d","duration_seconds":1419,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/active-learners-as-efficient-prp-rerankers/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/active-learners-as-efficient-prp-rerankers.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information","slug":"anti-self-distillation-for-reasoning-rl-via-pointwise-mutual-information","published_at":"2026-05-21T04:37:32+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/anti-self-distillation-for-reasoning-rl-via-pointwise-mutual-information","url":"https://share.transistor.fm/s/3596cc0f","duration_seconds":1377,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/anti-self-distillation-for-reasoning-rl-via-pointwise-mutual-information/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/anti-self-distillation-for-reasoning-rl-via-pointwise-mutual-information.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration","slug":"autoresearchclaw-self-reinforcing-autonomous-research-with-human-ai-collaboration","published_at":"2026-05-21T04:37:08+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/autoresearchclaw-self-reinforcing-autonomous-research-with-human-ai-collaboration","url":"https://share.transistor.fm/s/ca104a60","duration_seconds":1419,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/autoresearchclaw-self-reinforcing-autonomous-research-with-human-ai-collaboration/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/autoresearchclaw-self-reinforcing-autonomous-research-with-human-ai-collaboration.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"OpenComputer: Verifiable Software Worlds for Computer-Use Agents","slug":"opencomputer-verifiable-software-worlds-for-computer-use-agents","published_at":"2026-05-21T04:36:45+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/opencomputer-verifiable-software-worlds-for-computer-use-agents","url":"https://share.transistor.fm/s/bbca1616","duration_seconds":1482,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/opencomputer-verifiable-software-worlds-for-computer-use-agents/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/opencomputer-verifiable-software-worlds-for-computer-use-agents.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment","slug":"golongrl-capability-oriented-long-context-reinforcement-learning-with-multitask-alignment","published_at":"2026-05-21T04:36:22+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/golongrl-capability-oriented-long-context-reinforcement-learning-with-multitask-alignment","url":"https://share.transistor.fm/s/dae8be06","duration_seconds":1476,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/golongrl-capability-oriented-long-context-reinforcement-learning-with-multitask-alignment/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/golongrl-capability-oriented-long-context-reinforcement-learning-with-multitask-alignment.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Process Rewards with Learned Reliability","slug":"process-rewards-with-learned-reliability","published_at":"2026-05-21T04:35:58+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/process-rewards-with-learned-reliability","url":"https://share.transistor.fm/s/dfadd2c7","duration_seconds":1401,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/process-rewards-with-learned-reliability/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/process-rewards-with-learned-reliability.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL","slug":"envfactory-scaling-tool-use-agents-via-executable-environments-synthesis-and-robust-rl","published_at":"2026-05-21T04:35:34+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/envfactory-scaling-tool-use-agents-via-executable-environments-synthesis-and-robust-rl","url":"https://share.transistor.fm/s/9f618c24","duration_seconds":1642,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/envfactory-scaling-tool-use-agents-via-executable-environments-synthesis-and-robust-rl/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/envfactory-scaling-tool-use-agents-via-executable-environments-synthesis-and-robust-rl.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"CogOmniControl: Reasoning-Driven Controllable Video Generation via Creative Intent Cognition","slug":"cogomnicontrol-reasoning-driven-controllable-video-generation-via-creative-intent-cognition","published_at":"2026-05-21T04:35:11+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/cogomnicontrol-reasoning-driven-controllable-video-generation-via-creative-intent-cognition","url":"https://share.transistor.fm/s/b64f1aec","duration_seconds":1402,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/cogomnicontrol-reasoning-driven-controllable-video-generation-via-creative-intent-cognition/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/cogomnicontrol-reasoning-driven-controllable-video-generation-via-creative-intent-cognition.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Harnessing LLM Agents with Skill Programs","slug":"harnessing-llm-agents-with-skill-programs","published_at":"2026-05-21T04:34:48+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/harnessing-llm-agents-with-skill-programs","url":"https://share.transistor.fm/s/102f0911","duration_seconds":1320,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/harnessing-llm-agents-with-skill-programs/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/harnessing-llm-agents-with-skill-programs.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Code as Agent Harness","slug":"code-as-agent-harness","published_at":"2026-05-20T04:14:37+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/code-as-agent-harness","url":"https://share.transistor.fm/s/3e5d1003","duration_seconds":1523,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/code-as-agent-harness/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/code-as-agent-harness.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution","slug":"skillsvote-lifecycle-governance-of-agent-skills-from-collection-recommendation-to-evolution","published_at":"2026-05-20T04:14:15+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/skillsvote-lifecycle-governance-of-agent-skills-from-collection-recommendation-to-evolution","url":"https://share.transistor.fm/s/6a5c9833","duration_seconds":1371,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/skillsvote-lifecycle-governance-of-agent-skills-from-collection-recommendation-to-evolution/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/skillsvote-lifecycle-governance-of-agent-skills-from-collection-recommendation-to-evolution.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation","slug":"longlive-2-0-an-nvfp4-parallel-infrastructure-for-long-video-generation","published_at":"2026-05-20T04:13:53+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/longlive-2-0-an-nvfp4-parallel-infrastructure-for-long-video-generation","url":"https://share.transistor.fm/s/ef0f6ffc","duration_seconds":1345,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/longlive-2-0-an-nvfp4-parallel-infrastructure-for-long-video-generation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/longlive-2-0-an-nvfp4-parallel-infrastructure-for-long-video-generation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","slug":"lance-unified-multimodal-modeling-by-multi-task-synergy","published_at":"2026-05-20T04:13:31+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/lance-unified-multimodal-modeling-by-multi-task-synergy","url":"https://share.transistor.fm/s/f20fd799","duration_seconds":1391,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/lance-unified-multimodal-modeling-by-multi-task-synergy/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/lance-unified-multimodal-modeling-by-multi-task-synergy.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"AI for Auto-Research: Roadmap & User Guide","slug":"ai-for-auto-research-roadmap-user-guide","published_at":"2026-05-20T04:13:10+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/ai-for-auto-research-roadmap-user-guide","url":"https://share.transistor.fm/s/0f48e7af","duration_seconds":1342,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/ai-for-auto-research-roadmap-user-guide/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/ai-for-auto-research-roadmap-user-guide.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?","slug":"chi-bench-can-ai-agents-automate-end-to-end-long-horizon-policy-rich-healthcare-workflows","published_at":"2026-05-20T04:12:48+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/chi-bench-can-ai-agents-automate-end-to-end-long-horizon-policy-rich-healthcare-workflows","url":"https://share.transistor.fm/s/93c04a08","duration_seconds":1390,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/chi-bench-can-ai-agents-automate-end-to-end-long-horizon-policy-rich-healthcare-workflows/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/chi-bench-can-ai-agents-automate-end-to-end-long-horizon-policy-rich-healthcare-workflows.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"KVPO: ODE-Native GRPO for Autoregressive Video Alignment via KV Semantic Exploration","slug":"kvpo-ode-native-grpo-for-autoregressive-video-alignment-via-kv-semantic-exploration","published_at":"2026-05-20T04:12:27+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/kvpo-ode-native-grpo-for-autoregressive-video-alignment-via-kv-semantic-exploration","url":"https://share.transistor.fm/s/14186699","duration_seconds":1420,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/kvpo-ode-native-grpo-for-autoregressive-video-alignment-via-kv-semantic-exploration/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/kvpo-ode-native-grpo-for-autoregressive-video-alignment-via-kv-semantic-exploration.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence","slug":"citevqa-benchmarking-evidence-attribution-for-trustworthy-document-intelligence","published_at":"2026-05-19T04:21:59+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/citevqa-benchmarking-evidence-attribution-for-trustworthy-document-intelligence","url":"https://share.transistor.fm/s/95291574","duration_seconds":1390,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/citevqa-benchmarking-evidence-attribution-for-trustworthy-document-intelligence/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/citevqa-benchmarking-evidence-attribution-for-trustworthy-document-intelligence.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"PhysBrain 1.0 Technical Report","slug":"physbrain-1-0-technical-report","published_at":"2026-05-19T04:21:38+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/physbrain-1-0-technical-report","url":"https://share.transistor.fm/s/053171c2","duration_seconds":1524,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/physbrain-1-0-technical-report/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/physbrain-1-0-technical-report.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"MMSkills: Towards Multimodal Skills for General Visual Agents","slug":"mmskills-towards-multimodal-skills-for-general-visual-agents","published_at":"2026-05-19T04:21:16+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/mmskills-towards-multimodal-skills-for-general-visual-agents","url":"https://share.transistor.fm/s/457d4957","duration_seconds":1360,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/mmskills-towards-multimodal-skills-for-general-visual-agents/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/mmskills-towards-multimodal-skills-for-general-visual-agents.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"DexJoCo: A Benchmark and Toolkit for Task-Oriented Dexterous Manipulation on MuJoCo","slug":"dexjoco-a-benchmark-and-toolkit-for-task-oriented-dexterous-manipulation-on-mujoco","published_at":"2026-05-19T04:20:55+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/dexjoco-a-benchmark-and-toolkit-for-task-oriented-dexterous-manipulation-on-mujoco","url":"https://share.transistor.fm/s/8743282c","duration_seconds":1392,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/dexjoco-a-benchmark-and-toolkit-for-task-oriented-dexterous-manipulation-on-mujoco/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/dexjoco-a-benchmark-and-toolkit-for-task-oriented-dexterous-manipulation-on-mujoco.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding","slug":"distilling-long-cot-reasoning-through-collaborative-step-wise-multi-teacher-decoding","published_at":"2026-05-19T04:20:34+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/distilling-long-cot-reasoning-through-collaborative-step-wise-multi-teacher-decoding","url":"https://share.transistor.fm/s/e1a410e1","duration_seconds":1272,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/distilling-long-cot-reasoning-through-collaborative-step-wise-multi-teacher-decoding/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/distilling-long-cot-reasoning-through-collaborative-step-wise-multi-teacher-decoding.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation","slug":"insighttok-improving-text-and-face-fidelity-in-discrete-tokenization-for-autoregressive-image-generation","published_at":"2026-05-19T04:20:12+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/insighttok-improving-text-and-face-fidelity-in-discrete-tokenization-for-autoregressive-image-generation","url":"https://share.transistor.fm/s/f4eaa239","duration_seconds":1462,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/insighttok-improving-text-and-face-fidelity-in-discrete-tokenization-for-autoregressive-image-generation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/insighttok-improving-text-and-face-fidelity-in-discrete-tokenization-for-autoregressive-image-generation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization","slug":"flash-grpo-efficient-alignment-for-video-diffusion-via-one-step-policy-optimization","published_at":"2026-05-19T04:19:50+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/flash-grpo-efficient-alignment-for-video-diffusion-via-one-step-policy-optimization","url":"https://share.transistor.fm/s/48be6e53","duration_seconds":1264,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/flash-grpo-efficient-alignment-for-video-diffusion-via-one-step-policy-optimization/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/flash-grpo-efficient-alignment-for-video-diffusion-via-one-step-policy-optimization.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR","slug":"nudging-beyond-the-comfort-zone-efficient-strategy-guided-exploration-for-rlvr","published_at":"2026-05-19T04:19:28+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/nudging-beyond-the-comfort-zone-efficient-strategy-guided-exploration-for-rlvr","url":"https://share.transistor.fm/s/7f34b019","duration_seconds":1267,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/nudging-beyond-the-comfort-zone-efficient-strategy-guided-exploration-for-rlvr/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/nudging-beyond-the-comfort-zone-efficient-strategy-guided-exploration-for-rlvr.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling","slug":"achieving-gold-medal-level-olympiad-reasoning-via-simple-and-unified-scaling","published_at":"2026-05-16T04:26:32+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/achieving-gold-medal-level-olympiad-reasoning-via-simple-and-unified-scaling","url":"https://share.transistor.fm/s/08cf43f7","duration_seconds":1370,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/achieving-gold-medal-level-olympiad-reasoning-via-simple-and-unified-scaling/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/achieving-gold-medal-level-olympiad-reasoning-via-simple-and-unified-scaling.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation","slug":"causal-forcing-scalable-few-step-autoregressive-diffusion-distillation-for-real-time-interactive-video-generation","published_at":"2026-05-16T04:26:11+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/causal-forcing-scalable-few-step-autoregressive-diffusion-distillation-for-real-time-interactive-video-generation","url":"https://share.transistor.fm/s/f653d882","duration_seconds":1410,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/causal-forcing-scalable-few-step-autoregressive-diffusion-distillation-for-real-time-interactive-video-generation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/causal-forcing-scalable-few-step-autoregressive-diffusion-distillation-for-real-time-interactive-video-generation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Self-Distilled Agentic Reinforcement Learning","slug":"self-distilled-agentic-reinforcement-learning","published_at":"2026-05-16T04:25:49+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/self-distilled-agentic-reinforcement-learning","url":"https://share.transistor.fm/s/896103fd","duration_seconds":1491,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/self-distilled-agentic-reinforcement-learning/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/self-distilled-agentic-reinforcement-learning.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models","slug":"memlens-benchmarking-multimodal-long-term-memory-in-large-vision-language-models","published_at":"2026-05-16T04:25:28+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/memlens-benchmarking-multimodal-long-term-memory-in-large-vision-language-models","url":"https://share.transistor.fm/s/25b78099","duration_seconds":1617,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/memlens-benchmarking-multimodal-long-term-memory-in-large-vision-language-models/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/memlens-benchmarking-multimodal-long-term-memory-in-large-vision-language-models.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer","slug":"sana-wm-efficient-minute-scale-world-modeling-with-hybrid-linear-diffusion-transformer","published_at":"2026-05-16T04:25:06+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/sana-wm-efficient-minute-scale-world-modeling-with-hybrid-linear-diffusion-transformer","url":"https://share.transistor.fm/s/ab72c767","duration_seconds":1332,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/sana-wm-efficient-minute-scale-world-modeling-with-hybrid-linear-diffusion-transformer/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/sana-wm-efficient-minute-scale-world-modeling-with-hybrid-linear-diffusion-transformer.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory","slug":"memeye-a-visual-centric-evaluation-framework-for-multimodal-agent-memory","published_at":"2026-05-16T04:24:45+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/memeye-a-visual-centric-evaluation-framework-for-multimodal-agent-memory","url":"https://share.transistor.fm/s/88be608c","duration_seconds":1370,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/memeye-a-visual-centric-evaluation-framework-for-multimodal-agent-memory/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/memeye-a-visual-centric-evaluation-framework-for-multimodal-agent-memory.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning","slug":"darwin-family-mri-trust-weighted-evolutionary-merging-for-training-free-scaling-of-language-model-reasoning","published_at":"2026-05-16T04:24:23+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/darwin-family-mri-trust-weighted-evolutionary-merging-for-training-free-scaling-of-language-model-reasoning","url":"https://share.transistor.fm/s/0f4c1b96","duration_seconds":1402,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/darwin-family-mri-trust-weighted-evolutionary-merging-for-training-free-scaling-of-language-model-reasoning/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/darwin-family-mri-trust-weighted-evolutionary-merging-for-training-free-scaling-of-language-model-reasoning.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems","slug":"beyond-individual-intelligence-surveying-collaboration-failure-attribution-and-self-evolution-in-llm-based-multi-agent-systems","published_at":"2026-05-16T04:24:02+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/beyond-individual-intelligence-surveying-collaboration-failure-attribution-and-self-evolution-in-llm-based-multi-agent-systems","url":"https://share.transistor.fm/s/88a6b0fa","duration_seconds":1312,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/beyond-individual-intelligence-surveying-collaboration-failure-attribution-and-self-evolution-in-llm-based-multi-agent-systems/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/beyond-individual-intelligence-surveying-collaboration-failure-attribution-and-self-evolution-in-llm-based-multi-agent-systems.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?","slug":"stale-can-llm-agents-know-when-their-memories-are-no-longer-valid","published_at":"2026-05-16T04:23:40+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/stale-can-llm-agents-know-when-their-memories-are-no-longer-valid","url":"https://share.transistor.fm/s/ad2fff7b","duration_seconds":1411,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/stale-can-llm-agents-know-when-their-memories-are-no-longer-valid/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/stale-can-llm-agents-know-when-their-memories-are-no-longer-valid.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation","slug":"wildclawbench-a-benchmark-for-real-world-long-horizon-agent-evaluation","published_at":"2026-05-16T04:23:19+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/wildclawbench-a-benchmark-for-real-world-long-horizon-agent-evaluation","url":"https://share.transistor.fm/s/e8cb6ecf","duration_seconds":1473,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/wildclawbench-a-benchmark-for-real-world-long-horizon-agent-evaluation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/wildclawbench-a-benchmark-for-real-world-long-horizon-agent-evaluation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"MinT: Managed Infrastructure for Training and Serving Millions of LLMs","slug":"mint-managed-infrastructure-for-training-and-serving-millions-of-llms","published_at":"2026-05-15T05:02:19+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/mint-managed-infrastructure-for-training-and-serving-millions-of-llms","url":"https://share.transistor.fm/s/a9dd0ae7","duration_seconds":1432,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/mint-managed-infrastructure-for-training-and-serving-millions-of-llms/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/mint-managed-infrastructure-for-training-and-serving-millions-of-llms.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image","slug":"multabench-benchmarking-multimodal-tabular-learning-with-text-and-image","published_at":"2026-05-15T05:01:57+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/multabench-benchmarking-multimodal-tabular-learning-with-text-and-image","url":"https://share.transistor.fm/s/0c7a3b1e","duration_seconds":1453,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/multabench-benchmarking-multimodal-tabular-learning-with-text-and-image/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/multabench-benchmarking-multimodal-tabular-learning-with-text-and-image.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation","slug":"anyflow-any-step-video-diffusion-model-with-on-policy-flow-map-distillation","published_at":"2026-05-15T05:01:36+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/anyflow-any-step-video-diffusion-model-with-on-policy-flow-map-distillation","url":"https://share.transistor.fm/s/ac4e4aa7","duration_seconds":1410,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/anyflow-any-step-video-diffusion-model-with-on-policy-flow-map-distillation/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/anyflow-any-step-video-diffusion-model-with-on-policy-flow-map-distillation.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context","slug":"training-long-context-vision-language-models-effectively-with-generalization-beyond-128k-context","published_at":"2026-05-15T05:01:15+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/training-long-context-vision-language-models-effectively-with-generalization-beyond-128k-context","url":"https://share.transistor.fm/s/fab16fc9","duration_seconds":1385,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/training-long-context-vision-language-models-effectively-with-generalization-beyond-128k-context/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/training-long-context-vision-language-models-effectively-with-generalization-beyond-128k-context.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"EVA-Bench: A New End-to-end Framework for Evaluating Voice Agents","slug":"eva-bench-a-new-end-to-end-framework-for-evaluating-voice-agents","published_at":"2026-05-15T05:00:54+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/eva-bench-a-new-end-to-end-framework-for-evaluating-voice-agents","url":"https://share.transistor.fm/s/3a90cf54","duration_seconds":1519,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/eva-bench-a-new-end-to-end-framework-for-evaluating-voice-agents/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/eva-bench-a-new-end-to-end-framework-for-evaluating-voice-agents.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling","slug":"predicting-decisions-of-ai-agents-from-limited-interaction-through-text-tabular-modeling","published_at":"2026-05-15T05:00:32+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/predicting-decisions-of-ai-agents-from-limited-interaction-through-text-tabular-modeling","url":"https://share.transistor.fm/s/3a7cb92e","duration_seconds":1499,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/predicting-decisions-of-ai-agents-from-limited-interaction-through-text-tabular-modeling/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/predicting-decisions-of-ai-agents-from-limited-interaction-through-text-tabular-modeling.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Qwen-Image-VAE-2.0 Technical Report","slug":"qwen-image-vae-2-0-technical-report","published_at":"2026-05-15T05:00:11+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/qwen-image-vae-2-0-technical-report","url":"https://share.transistor.fm/s/12f43ae7","duration_seconds":1462,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/qwen-image-vae-2-0-technical-report/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/qwen-image-vae-2-0-technical-report.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking","slug":"trackcraft3r-repurposing-video-diffusion-transformers-for-dense-3d-tracking","published_at":"2026-05-15T04:59:50+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/trackcraft3r-repurposing-video-diffusion-transformers-for-dense-3d-tracking","url":"https://share.transistor.fm/s/7a4f5ed0","duration_seconds":1406,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/trackcraft3r-repurposing-video-diffusion-transformers-for-dense-3d-tracking/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/trackcraft3r-repurposing-video-diffusion-transformers-for-dense-3d-tracking.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling","slug":"edit-compass-editreward-compass-a-unified-benchmark-for-image-editing-and-reward-modeling","published_at":"2026-05-15T04:59:29+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/edit-compass-editreward-compass-a-unified-benchmark-for-image-editing-and-reward-modeling","url":"https://share.transistor.fm/s/46539574","duration_seconds":1418,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/edit-compass-editreward-compass-a-unified-benchmark-for-image-editing-and-reward-modeling/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/edit-compass-editreward-compass-a-unified-benchmark-for-image-editing-and-reward-modeling.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Many-Shot CoT-ICL: Making In-Context Learning Truly Learn","slug":"many-shot-cot-icl-making-in-context-learning-truly-learn","published_at":"2026-05-15T04:59:08+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/many-shot-cot-icl-making-in-context-learning-truly-learn","url":"https://share.transistor.fm/s/8b97cdae","duration_seconds":1440,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/many-shot-cot-icl-making-in-context-learning-truly-learn/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/many-shot-cot-icl-making-in-context-learning-truly-learn.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents","slug":"memprivacy-privacy-preserving-personalized-memory-management-for-edge-cloud-agents","published_at":"2026-05-14T04:34:02+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/memprivacy-privacy-preserving-personalized-memory-management-for-edge-cloud-agents","url":"https://share.transistor.fm/s/7e697f9d","duration_seconds":1467,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/memprivacy-privacy-preserving-personalized-memory-management-for-edge-cloud-agents/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/memprivacy-privacy-preserving-personalized-memory-management-for-edge-cloud-agents.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture","slug":"sensenova-u1-unifying-multimodal-understanding-and-generation-with-neo-unify-architecture","published_at":"2026-05-14T04:33:40+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/sensenova-u1-unifying-multimodal-understanding-and-generation-with-neo-unify-architecture","url":"https://share.transistor.fm/s/d8453b62","duration_seconds":1532,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/sensenova-u1-unifying-multimodal-understanding-and-generation-with-neo-unify-architecture/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/sensenova-u1-unifying-multimodal-understanding-and-generation-with-neo-unify-architecture.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"$δ$-mem: Efficient Online Memory for Large Language Models","slug":"mem-efficient-online-memory-for-large-language-models","published_at":"2026-05-14T04:33:18+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/mem-efficient-online-memory-for-large-language-models","url":"https://share.transistor.fm/s/979c7e38","duration_seconds":1471,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/mem-efficient-online-memory-for-large-language-models/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/mem-efficient-online-memory-for-large-language-models.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards","slug":"rubricem-meta-rl-with-rubric-guided-policy-decomposition-beyond-verifiable-rewards","published_at":"2026-05-14T04:32:56+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/rubricem-meta-rl-with-rubric-guided-policy-decomposition-beyond-verifiable-rewards","url":"https://share.transistor.fm/s/99f378e6","duration_seconds":1357,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/rubricem-meta-rl-with-rubric-guided-policy-decomposition-beyond-verifiable-rewards/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/rubricem-meta-rl-with-rubric-guided-policy-decomposition-beyond-verifiable-rewards.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics","slug":"do-enterprise-systems-need-learned-world-models-the-importance-of-context-to-infer-dynamics","published_at":"2026-05-14T04:32:34+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/do-enterprise-systems-need-learned-world-models-the-importance-of-context-to-infer-dynamics","url":"https://share.transistor.fm/s/b3c915cd","duration_seconds":1361,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/do-enterprise-systems-need-learned-world-models-the-importance-of-context-to-infer-dynamics/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/do-enterprise-systems-need-learned-world-models-the-importance-of-context-to-infer-dynamics.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"World Action Models: The Next Frontier in Embodied AI","slug":"world-action-models-the-next-frontier-in-embodied-ai","published_at":"2026-05-14T04:32:12+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/world-action-models-the-next-frontier-in-embodied-ai","url":"https://share.transistor.fm/s/679ec15d","duration_seconds":1483,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/world-action-models-the-next-frontier-in-embodied-ai/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/world-action-models-the-next-frontier-in-embodied-ai.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Beyond the Last Layer: Multi-Layer Representation Fusion for Visual Tokenization","slug":"beyond-the-last-layer-multi-layer-representation-fusion-for-visual-tokenization","published_at":"2026-05-14T04:31:50+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/beyond-the-last-layer-multi-layer-representation-fusion-for-visual-tokenization","url":"https://share.transistor.fm/s/f342417e","duration_seconds":1520,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/beyond-the-last-layer-multi-layer-representation-fusion-for-visual-tokenization/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/beyond-the-last-layer-multi-layer-representation-fusion-for-visual-tokenization.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Efficient Pre-Training with Token Superposition","slug":"efficient-pre-training-with-token-superposition","published_at":"2026-05-14T04:31:28+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/efficient-pre-training-with-token-superposition","url":"https://share.transistor.fm/s/4aff0510","duration_seconds":1475,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/efficient-pre-training-with-token-superposition/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/efficient-pre-training-with-token-superposition.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward","slug":"alphagrpo-unlocking-self-reflective-multimodal-generation-in-umms-via-decompositional-verifiable-reward","published_at":"2026-05-14T04:31:06+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/alphagrpo-unlocking-self-reflective-multimodal-generation-in-umms-via-decompositional-verifiable-reward","url":"https://share.transistor.fm/s/ee158ab8","duration_seconds":1439,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/alphagrpo-unlocking-self-reflective-multimodal-generation-in-umms-via-decompositional-verifiable-reward/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/alphagrpo-unlocking-self-reflective-multimodal-generation-in-umms-via-decompositional-verifiable-reward.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"MCP-Cosmos: World Model-Augmented Agents for Complex Task Execution in MCP Environments","slug":"mcp-cosmos-world-model-augmented-agents-for-complex-task-execution-in-mcp-environments","published_at":"2026-05-14T04:30:44+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/mcp-cosmos-world-model-augmented-agents-for-complex-task-execution-in-mcp-environments","url":"https://share.transistor.fm/s/7379ec2d","duration_seconds":1304,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/mcp-cosmos-world-model-augmented-agents-for-complex-task-execution-in-mcp-environments/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/mcp-cosmos-world-model-augmented-agents-for-complex-task-execution-in-mcp-environments.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Qwen-Image-2.0 Technical Report","slug":"qwen-image-2-0-technical-report","published_at":"2026-05-13T04:34:33+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/qwen-image-2-0-technical-report","url":"https://share.transistor.fm/s/8130b403","duration_seconds":1383,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/qwen-image-2-0-technical-report/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/qwen-image-2-0-technical-report.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs","slug":"soohak-a-mathematician-curated-benchmark-for-evaluating-research-level-math-capabilities-of-llms","published_at":"2026-05-13T04:34:12+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/soohak-a-mathematician-curated-benchmark-for-evaluating-research-level-math-capabilities-of-llms","url":"https://share.transistor.fm/s/1d6bb954","duration_seconds":1439,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/soohak-a-mathematician-curated-benchmark-for-evaluating-research-level-math-capabilities-of-llms/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/soohak-a-mathematician-curated-benchmark-for-evaluating-research-level-math-capabilities-of-llms.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models","slug":"collabvr-collaborative-video-reasoning-with-vision-language-and-video-generation-models","published_at":"2026-05-13T04:33:51+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/collabvr-collaborative-video-reasoning-with-vision-language-and-video-generation-models","url":"https://share.transistor.fm/s/855e569e","duration_seconds":1526,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/collabvr-collaborative-video-reasoning-with-vision-language-and-video-generation-models/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/collabvr-collaborative-video-reasoning-with-vision-language-and-video-generation-models.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"TMAS: Scaling Test-Time Compute via Multi-Agent Synergy","slug":"tmas-scaling-test-time-compute-via-multi-agent-synergy","published_at":"2026-05-13T04:33:30+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/tmas-scaling-test-time-compute-via-multi-agent-synergy","url":"https://share.transistor.fm/s/3967f7ba","duration_seconds":1397,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/tmas-scaling-test-time-compute-via-multi-agent-synergy/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/tmas-scaling-test-time-compute-via-multi-agent-synergy.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents","slug":"paperfit-vision-in-the-loop-typesetting-optimization-for-scientific-documents","published_at":"2026-05-13T04:33:08+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/paperfit-vision-in-the-loop-typesetting-optimization-for-scientific-documents","url":"https://share.transistor.fm/s/2be242df","duration_seconds":1375,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/paperfit-vision-in-the-loop-typesetting-optimization-for-scientific-documents/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/paperfit-vision-in-the-loop-typesetting-optimization-for-scientific-documents.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Model Merging Scaling Laws in Large Language Models","slug":"model-merging-scaling-laws-in-large-language-models","published_at":"2026-05-13T04:32:47+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/model-merging-scaling-laws-in-large-language-models","url":"https://share.transistor.fm/s/dc79b8ed","duration_seconds":1304,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/model-merging-scaling-laws-in-large-language-models/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/model-merging-scaling-laws-in-large-language-models.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"SEIF: Self-Evolving Reinforcement Learning for Instruction Following","slug":"seif-self-evolving-reinforcement-learning-for-instruction-following","published_at":"2026-05-13T04:32:26+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/seif-self-evolving-reinforcement-learning-for-instruction-following","url":"https://share.transistor.fm/s/e7d9944e","duration_seconds":1287,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/seif-self-evolving-reinforcement-learning-for-instruction-following/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/seif-self-evolving-reinforcement-learning-for-instruction-following.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors","slug":"worldreasonbench-human-aligned-stress-testing-of-video-generators-as-future-world-state-predictors","published_at":"2026-05-13T04:32:05+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/worldreasonbench-human-aligned-stress-testing-of-video-generators-as-future-world-state-predictors","url":"https://share.transistor.fm/s/60f7d5d5","duration_seconds":1346,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/worldreasonbench-human-aligned-stress-testing-of-video-generators-as-future-world-state-predictors/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/worldreasonbench-human-aligned-stress-testing-of-video-generators-as-future-world-state-predictors.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models","slug":"memory-efficient-looped-transformer-decoupling-compute-from-memory-in-looped-language-models","published_at":"2026-05-13T04:31:39+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/memory-efficient-looped-transformer-decoupling-compute-from-memory-in-looped-language-models","url":"https://share.transistor.fm/s/51524a66","duration_seconds":1349,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/memory-efficient-looped-transformer-decoupling-compute-from-memory-in-looped-language-models/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/memory-efficient-looped-transformer-decoupling-compute-from-memory-in-looped-language-models.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers","slug":"mean-mode-screaming-mean-variance-split-residuals-for-1000-layer-diffusion-transformers","published_at":"2026-05-12T04:03:28+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/mean-mode-screaming-mean-variance-split-residuals-for-1000-layer-diffusion-transformers","url":"https://share.transistor.fm/s/a62deee0","duration_seconds":1313,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/mean-mode-screaming-mean-variance-split-residuals-for-1000-layer-diffusion-transformers/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/mean-mode-screaming-mean-variance-split-residuals-for-1000-layer-diffusion-transformers.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Flow-OPD: On-Policy Distillation for Flow Matching Models","slug":"flow-opd-on-policy-distillation-for-flow-matching-models","published_at":"2026-05-12T04:03:07+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/flow-opd-on-policy-distillation-for-flow-matching-models","url":"https://share.transistor.fm/s/56fff24a","duration_seconds":1575,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/flow-opd-on-policy-distillation-for-flow-matching-models/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/flow-opd-on-policy-distillation-for-flow-matching-models.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents","slug":"hypereyes-dual-grained-efficiency-aware-reinforcement-learning-for-parallel-multimodal-search-agents","published_at":"2026-05-12T04:02:45+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/hypereyes-dual-grained-efficiency-aware-reinforcement-learning-for-parallel-multimodal-search-agents","url":"https://share.transistor.fm/s/3d74d9c7","duration_seconds":1521,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/hypereyes-dual-grained-efficiency-aware-reinforcement-learning-for-parallel-multimodal-search-agents/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/hypereyes-dual-grained-efficiency-aware-reinforcement-learning-for-parallel-multimodal-search-agents.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Anisotropic Modality Align","slug":"anisotropic-modality-align","published_at":"2026-05-12T04:02:24+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/anisotropic-modality-align","url":"https://share.transistor.fm/s/3dadc4f5","duration_seconds":1374,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/anisotropic-modality-align/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/anisotropic-modality-align.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Beyond Retrieval: A Multitask Benchmark and Model for Code Search","slug":"beyond-retrieval-a-multitask-benchmark-and-model-for-code-search","published_at":"2026-05-12T04:02:02+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/beyond-retrieval-a-multitask-benchmark-and-model-for-code-search","url":"https://share.transistor.fm/s/7e0e20ae","duration_seconds":1274,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/beyond-retrieval-a-multitask-benchmark-and-model-for-code-search/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/beyond-retrieval-a-multitask-benchmark-and-model-for-code-search.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"MiA-Signature: Approximating Global Activation for Long-Context Understanding","slug":"mia-signature-approximating-global-activation-for-long-context-understanding","published_at":"2026-05-09T05:09:55+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649/mia-signature-approximating-global-activation-for-long-context-understanding","url":"https://share.transistor.fm/s/4af916c3","duration_seconds":710,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/mia-signature-approximating-global-activation-for-long-context-understanding/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/daily-paper-cast-7079649/mia-signature-approximating-global-activation-for-long-context-understanding.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}]}