{"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"},"episode":{"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","show_page_url":"https://stenobird.com/podcast/daily-paper-cast-7079649","url":"https://share.transistor.fm/s/3596cc0f","audio_url":"https://media.transistor.fm/3596cc0f/71730fee.mp3","summary":"🤗 Upvotes: 71 | cs.LG, cs.AI, cs.CL Authors: Guobin Shen, Xiang Cheng, Chenxiao Zhao, Lei Huang, Jindong Li, Dongcheng Zhao, Xing Yu Title: Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information Arxiv: http://arxiv.org/abs/2605.11609v1 Abstract: On-policy self-distillation, where a student is pulled toward a copy of itself conditioned on privileged context (e.g., a verified solution or feedback), offers a promising direction for advancing reasoning capability without a stronger external teacher. Yet in math reasoning the gains are inconsistent, even when the same approach succeeds elsewhere. A pointwise mutual information analysis traces the failure to the privileged context itself: it inflates the teacher's confidence on tokens already implied by the solution (structural connectives, verifiable claims) and deflates it on deliberation tokens (\"Wait\", \"Let\", \"Maybe\") that drive multi-step search. We propose Anti-Self-Distillation (AntiSD), which ascends a divergence between student and teacher rather than descending it: this reverses the per-token sign and yields a naturally bounded advantage in one step. An entropy-triggered gate disables the term once the teacher entropy collapses, completing a drop-in replacement for default self-distillation. Across five models from 4B to 30B parameters on math reasoning benchmarks, AntiSD reaches the GRPO baseline's accuracy in 2 to 10x fewer training steps and improves final accuracy by up to 11.5 points. AntiSD opens a path to scalable self-improvement, where a language model bootstraps its own reasoning through its training signal.","meta_description":"🤗 Upvotes: 71 | cs.LG, cs.AI, cs.CL Authors: Guobin Shen, Xiang Cheng, Chenxiao Zhao, Lei Huang, Jindong Li, Dongcheng Zhao, Xing Yu Title: Anti-Self-Dist…","key_points":[],"chapters":[],"topics":[],"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."}]}}