{"podcast":{"title":"Best AI papers explained","slug":"best-ai-papers-explained-7258006","podcast_index_feed_id":7258006,"rss_url":"https://anchor.fm/s/1026675f8/podcast/rss","website_url":"https://podcasters.spotify.com/pod/show/ehwkang","image_url":"https://d3t3ozftmdmh3i.cloudfront.net/staging/podcast_uploaded_nologo/43252366/43252366-1744500070152-e62b760188d8.jpg","author":"Enoch H. Kang","episode_count":789,"summary":"Cut through the noise. We curate and break down the most important AI papers so you don’t have to.","last_synced_at":"2026-07-19T16:17:08.576018+00:00","page_url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006"},"episodes":[{"title":"From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning","slug":"from-reasoning-traces-to-reusable-modules-understanding-compositional-generalization-in-language-model-reasoning","published_at":"2026-07-18T16:23:16+00:00","page_url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/from-reasoning-traces-to-reusable-modules-understanding-compositional-generalization-in-language-model-reasoning","url":"https://podcasters.spotify.com/pod/show/ehwkang/episodes/From-Reasoning-Traces-to-Reusable-Modules-Understanding-Compositional-Generalization-in-Language-Model-Reasoning-e3m89j9","duration_seconds":1118,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/best-ai-papers-explained-7258006/episodes/from-reasoning-traces-to-reusable-modules-understanding-compositional-generalization-in-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/best-ai-papers-explained-7258006/from-reasoning-traces-to-reusable-modules-understanding-compositional-generalization-in-language-model-reasoning.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Position: Interpretability can be actionable","slug":"position-interpretability-can-be-actionable","published_at":"2026-07-17T16:53:06+00:00","page_url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/position-interpretability-can-be-actionable","url":"https://podcasters.spotify.com/pod/show/ehwkang/episodes/Position-Interpretability-can-be-actionable-e3m7963","duration_seconds":1482,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/best-ai-papers-explained-7258006/episodes/position-interpretability-can-be-actionable/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/position-interpretability-can-be-actionable.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"High-accuracy sampling for diffusion models and log-concave distributions","slug":"high-accuracy-sampling-for-diffusion-models-and-log-concave-distributions","published_at":"2026-07-17T02:23:28+00:00","page_url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/high-accuracy-sampling-for-diffusion-models-and-log-concave-distributions","url":"https://podcasters.spotify.com/pod/show/ehwkang/episodes/High-accuracy-sampling-for-diffusion-models-and-log-concave-distributions-e3m6fc4","duration_seconds":1349,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/best-ai-papers-explained-7258006/episodes/high-accuracy-sampling-for-diffusion-models-and-log-concave-distributions/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/high-accuracy-sampling-for-diffusion-models-and-log-concave-distributions.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Causal Inference with Video Features as Treatments","slug":"causal-inference-with-video-features-as-treatments","published_at":"2026-07-15T17:37:45+00:00","page_url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/causal-inference-with-video-features-as-treatments","url":"https://podcasters.spotify.com/pod/show/ehwkang/episodes/Causal-Inference-with-Video-Features-as-Treatments-e3m4i2f","duration_seconds":1333,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/best-ai-papers-explained-7258006/episodes/causal-inference-with-video-features-as-treatments/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/causal-inference-with-video-features-as-treatments.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"What Does Thompson Sampling Optimize?","slug":"what-does-thompson-sampling-optimize","published_at":"2026-07-15T00:33:57+00:00","page_url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/what-does-thompson-sampling-optimize","url":"https://podcasters.spotify.com/pod/show/ehwkang/episodes/What-Does-Thompson-Sampling-Optimize-e3m3i4n","duration_seconds":1338,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/best-ai-papers-explained-7258006/episodes/what-does-thompson-sampling-optimize/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/what-does-thompson-sampling-optimize.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Globally Convergent Offline Reinforcement Learning with Smoothed Bellman Residual Minimization","slug":"globally-convergent-offline-reinforcement-learning-with-smoothed-bellman-residual-minimization","published_at":"2026-07-13T17:35:57+00:00","page_url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/globally-convergent-offline-reinforcement-learning-with-smoothed-bellman-residual-minimization","url":"https://podcasters.spotify.com/pod/show/ehwkang/episodes/Globally-Convergent-Offline-Reinforcement-Learning-with-Smoothed-Bellman-Residual-Minimization-e3m1h8c","duration_seconds":745,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/best-ai-papers-explained-7258006/episodes/globally-convergent-offline-reinforcement-learning-with-smoothed-bellman-residual-minimization/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/globally-convergent-offline-reinforcement-learning-with-smoothed-bellman-residual-minimization.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"LLM-as-a-Verifier: A General-Purpose Verification Framework","slug":"llm-as-a-verifier-a-general-purpose-verification-framework","published_at":"2026-07-10T04:06:20+00:00","page_url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/llm-as-a-verifier-a-general-purpose-verification-framework","url":"https://podcasters.spotify.com/pod/show/ehwkang/episodes/LLM-as-a-Verifier-A-General-Purpose-Verification-Framework-e3lt3rr","duration_seconds":1202,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/best-ai-papers-explained-7258006/episodes/llm-as-a-verifier-a-general-purpose-verification-framework/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/llm-as-a-verifier-a-general-purpose-verification-framework.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"How Much Do Language Models Memorize?","slug":"how-much-do-language-models-memorize","published_at":"2026-07-09T05:52:54+00:00","page_url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/how-much-do-language-models-memorize","url":"https://podcasters.spotify.com/pod/show/ehwkang/episodes/How-Much-Do-Language-Models-Memorize-e3lrl61","duration_seconds":1432,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/best-ai-papers-explained-7258006/episodes/how-much-do-language-models-memorize/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/how-much-do-language-models-memorize.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Position: Uncertainty Quantification in LLMs is Just Unsupervised Clustering","slug":"position-uncertainty-quantification-in-llms-is-just-unsupervised-clustering","published_at":"2026-07-07T17:12:39+00:00","page_url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/position-uncertainty-quantification-in-llms-is-just-unsupervised-clustering","url":"https://podcasters.spotify.com/pod/show/ehwkang/episodes/Position-Uncertainty-Quantification-in-LLMs-is-Just-Unsupervised-Clustering-e3lpdao","duration_seconds":1307,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/best-ai-papers-explained-7258006/episodes/position-uncertainty-quantification-in-llms-is-just-unsupervised-clustering/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/position-uncertainty-quantification-in-llms-is-just-unsupervised-clustering.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Position: Agents Should Invoke External Tools ONLY When Epistemically Necessary","slug":"position-agents-should-invoke-external-tools-only-when-epistemically-necessary","published_at":"2026-07-06T21:50:23+00:00","page_url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/position-agents-should-invoke-external-tools-only-when-epistemically-necessary","url":"https://podcasters.spotify.com/pod/show/ehwkang/episodes/Position-Agents-Should-Invoke-External-Tools-ONLY-When-Epistemically-Necessary-e3lo7do","duration_seconds":728,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/best-ai-papers-explained-7258006/episodes/position-agents-should-invoke-external-tools-only-when-epistemically-necessary/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/position-agents-should-invoke-external-tools-only-when-epistemically-necessary.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"From conversations to mechanisms: aligning advertiser Incentives in ai-powered product recommendations","slug":"from-conversations-to-mechanisms-aligning-advertiser-incentives-in-ai-powered-product-recommendations","published_at":"2026-07-05T20:05:01+00:00","page_url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/from-conversations-to-mechanisms-aligning-advertiser-incentives-in-ai-powered-product-recommendations","url":"https://podcasters.spotify.com/pod/show/ehwkang/episodes/From-conversations-to-mechanisms-aligning-advertiser-Incentives-in-ai-powered-product-recommendations-e3lmips","duration_seconds":1322,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/best-ai-papers-explained-7258006/episodes/from-conversations-to-mechanisms-aligning-advertiser-incentives-in-ai-powered-product-recommendations/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/from-conversations-to-mechanisms-aligning-advertiser-incentives-in-ai-powered-product-recommendations.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Is one layer enough? Training a single transformer layer can match full-parameter RL training","slug":"is-one-layer-enough-training-a-single-transformer-layer-can-match-full-parameter-rl-training","published_at":"2026-07-04T18:08:30+00:00","page_url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/is-one-layer-enough-training-a-single-transformer-layer-can-match-full-parameter-rl-training","url":"https://podcasters.spotify.com/pod/show/ehwkang/episodes/Is-one-layer-enough--Training-a-single-transformer-layer-can-match-full-parameter-RL-training-e3llfe8","duration_seconds":1385,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/best-ai-papers-explained-7258006/episodes/is-one-layer-enough-training-a-single-transformer-layer-can-match-full-parameter-rl-training/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/is-one-layer-enough-training-a-single-transformer-layer-can-match-full-parameter-rl-training.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training","slug":"rl-excursions-during-pre-training-re-examining-policy-optimization-for-llm-training","published_at":"2026-07-02T22:59:40+00:00","page_url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/rl-excursions-during-pre-training-re-examining-policy-optimization-for-llm-training","url":"https://podcasters.spotify.com/pod/show/ehwkang/episodes/RL-Excursions-during-Pre-Training-Re-examining-Policy-Optimization-for-LLM-training-e3lja5t","duration_seconds":1307,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/best-ai-papers-explained-7258006/episodes/rl-excursions-during-pre-training-re-examining-policy-optimization-for-llm-training/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/rl-excursions-during-pre-training-re-examining-policy-optimization-for-llm-training.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Language Generation with Feedback: Queries and Mistakes","slug":"language-generation-with-feedback-queries-and-mistakes","published_at":"2026-07-01T21:10:00+00:00","page_url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/language-generation-with-feedback-queries-and-mistakes","url":"https://podcasters.spotify.com/pod/show/ehwkang/episodes/Language-Generation-with-Feedback-Queries-and-Mistakes-e3lhnal","duration_seconds":1207,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/best-ai-papers-explained-7258006/episodes/language-generation-with-feedback-queries-and-mistakes/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/language-generation-with-feedback-queries-and-mistakes.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Quantifying Theoretical AI Alignment Guarantees: Receiver-Utility Bounds in Bayesian Persuasion","slug":"quantifying-theoretical-ai-alignment-guarantees-receiver-utility-bounds-in-bayesian-persuasion","published_at":"2026-07-01T03:27:27+00:00","page_url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/quantifying-theoretical-ai-alignment-guarantees-receiver-utility-bounds-in-bayesian-persuasion","url":"https://podcasters.spotify.com/pod/show/ehwkang/episodes/Quantifying-Theoretical-AI-Alignment-Guarantees-Receiver-Utility-Bounds-in-Bayesian-Persuasion-e3lgi9d","duration_seconds":1338,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/best-ai-papers-explained-7258006/episodes/quantifying-theoretical-ai-alignment-guarantees-receiver-utility-bounds-in-bayesian-persuasion/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/quantifying-theoretical-ai-alignment-guarantees-receiver-utility-bounds-in-bayesian-persuasion.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"SPIRAL: Learning to search and aggregate","slug":"spiral-learning-to-search-and-aggregate","published_at":"2026-06-29T19:54:26+00:00","page_url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/spiral-learning-to-search-and-aggregate","url":"https://podcasters.spotify.com/pod/show/ehwkang/episodes/SPIRAL-Learning-to-search-and-aggregate-e3lek6j","duration_seconds":1335,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/best-ai-papers-explained-7258006/episodes/spiral-learning-to-search-and-aggregate/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/spiral-learning-to-search-and-aggregate.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Qwen-AgentWorld: Language World Models for General Agents","slug":"qwen-agentworld-language-world-models-for-general-agents","published_at":"2026-06-27T20:03:10+00:00","page_url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/qwen-agentworld-language-world-models-for-general-agents","url":"https://podcasters.spotify.com/pod/show/ehwkang/episodes/Qwen-AgentWorld-Language-World-Models-for-General-Agents-e3lbu3b","duration_seconds":1244,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/best-ai-papers-explained-7258006/episodes/qwen-agentworld-language-world-models-for-general-agents/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/qwen-agentworld-language-world-models-for-general-agents.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning?","slug":"when-does-trajectory-level-supervision-permit-efficient-offline-reinforcement-learning","published_at":"2026-06-27T05:11:27+00:00","page_url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/when-does-trajectory-level-supervision-permit-efficient-offline-reinforcement-learning","url":"https://podcasters.spotify.com/pod/show/ehwkang/episodes/When-Does-Trajectory-Level-Supervision-Permit-Efficient-Offline-Reinforcement-Learning-e3lb91k","duration_seconds":1136,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/best-ai-papers-explained-7258006/episodes/when-does-trajectory-level-supervision-permit-efficient-offline-reinforcement-learning/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/when-does-trajectory-level-supervision-permit-efficient-offline-reinforcement-learning.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"SuperThoughts: Reasoning Tokens in Superposition","slug":"superthoughts-reasoning-tokens-in-superposition","published_at":"2026-06-26T19:42:52+00:00","page_url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/superthoughts-reasoning-tokens-in-superposition","url":"https://podcasters.spotify.com/pod/show/ehwkang/episodes/SuperThoughts-Reasoning-Tokens-in-Superposition-e3lasbo","duration_seconds":1140,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/best-ai-papers-explained-7258006/episodes/superthoughts-reasoning-tokens-in-superposition/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/superthoughts-reasoning-tokens-in-superposition.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"First-Explore PPO : Learning Meta-Exploration with Proximal Policy Optimization","slug":"first-explore-ppo-learning-meta-exploration-with-proximal-policy-optimization","published_at":"2026-06-25T16:09:50+00:00","page_url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/first-explore-ppo-learning-meta-exploration-with-proximal-policy-optimization","url":"https://podcasters.spotify.com/pod/show/ehwkang/episodes/First-Explore-PPO--Learning-Meta-Exploration-with-Proximal-Policy-Optimization-e3l998g","duration_seconds":1355,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/best-ai-papers-explained-7258006/episodes/first-explore-ppo-learning-meta-exploration-with-proximal-policy-optimization/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/first-explore-ppo-learning-meta-exploration-with-proximal-policy-optimization.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Self-Distillation for Data-Scarce Language Model Pretraining","slug":"self-distillation-for-data-scarce-language-model-pretraining","published_at":"2026-06-24T02:17:55+00:00","page_url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/self-distillation-for-data-scarce-language-model-pretraining","url":"https://podcasters.spotify.com/pod/show/ehwkang/episodes/Self-Distillation-for-Data-Scarce-Language-Model-Pretraining-e3l70q8","duration_seconds":1305,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/best-ai-papers-explained-7258006/episodes/self-distillation-for-data-scarce-language-model-pretraining/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/self-distillation-for-data-scarce-language-model-pretraining.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Meta-Harness for Agent-State Construction","slug":"meta-harness-for-agent-state-construction","published_at":"2026-06-21T15:02:16+00:00","page_url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/meta-harness-for-agent-state-construction","url":"https://podcasters.spotify.com/pod/show/ehwkang/episodes/Meta-Harness-for-Agent-State-Construction-e3l33v2","duration_seconds":1382,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/best-ai-papers-explained-7258006/episodes/meta-harness-for-agent-state-construction/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/meta-harness-for-agent-state-construction.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"ExpRL: Using Reference Solutions as Rewards for LLM Mid-Training","slug":"exprl-using-reference-solutions-as-rewards-for-llm-mid-training","published_at":"2026-06-21T05:28:10+00:00","page_url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/exprl-using-reference-solutions-as-rewards-for-llm-mid-training","url":"https://podcasters.spotify.com/pod/show/ehwkang/episodes/ExpRL-Using-Reference-Solutions-as-Rewards-for-LLM-Mid-Training-e3l2mpb","duration_seconds":1263,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/best-ai-papers-explained-7258006/episodes/exprl-using-reference-solutions-as-rewards-for-llm-mid-training/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/exprl-using-reference-solutions-as-rewards-for-llm-mid-training.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"Valid Inference with Synthetic Data via Task Exchangeability","slug":"valid-inference-with-synthetic-data-via-task-exchangeability","published_at":"2026-06-18T22:12:12+00:00","page_url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/valid-inference-with-synthetic-data-via-task-exchangeability","url":"https://podcasters.spotify.com/pod/show/ehwkang/episodes/Valid-Inference-with-Synthetic-Data-via-Task-Exchangeability-e3l00o8","duration_seconds":788,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/best-ai-papers-explained-7258006/episodes/valid-inference-with-synthetic-data-via-task-exchangeability/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/valid-inference-with-synthetic-data-via-task-exchangeability.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]},{"title":"GRPO is Secretly a Process Reward Model","slug":"grpo-is-secretly-a-process-reward-model","published_at":"2026-06-17T22:56:07+00:00","page_url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/grpo-is-secretly-a-process-reward-model","url":"https://podcasters.spotify.com/pod/show/ehwkang/episodes/GRPO-is-Secretly-a-Process-Reward-Model-e3kuhr6","duration_seconds":1233,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/best-ai-papers-explained-7258006/episodes/grpo-is-secretly-a-process-reward-model/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/grpo-is-secretly-a-process-reward-model.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}]}