{"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":1967,"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":"2026-06-14T04:17:49.264124+00:00","page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649"},"episodes":[{"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."}]}]}