{"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":792,"summary":"Cut through the noise. We curate and break down the most important AI papers so you don’t have to.","last_synced_at":"2026-07-23T12:18:34.511243+00:00","page_url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006"},"episode":{"title":"Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference","slug":"reject-resample-repeat-understanding-parallel-reasoning-in-language-model-inference","published_at":"2026-07-19T18:09:13+00:00","page_url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006/reject-resample-repeat-understanding-parallel-reasoning-in-language-model-inference","show_page_url":"https://stenobird.com/podcast/best-ai-papers-explained-7258006","url":"https://podcasters.spotify.com/pod/show/ehwkang/episodes/Reject--Resample--Repeat-Understanding-Parallel-Reasoning-in-Language-Model-Inference-e3m9d27","audio_url":"https://anchor.fm/s/1026675f8/podcast/play/123040263/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2026-6-19%2F83425851-19b9-90d4-889c-5c83c3eea5a8.m4a","summary":"This research paper investigates Sequential Monte Carlo (SMC) and other particle filtering algorithms as a theoretical framework for improving large language model (LLM) inference. The authors introduce a principled approach to analyze inference-time interventions, such as parallel reasoning and pruning, by utilizing process reward models to steer generation. Their findings establish non-asymptotic guarantees for SMC based on criteria like bounded action-level coverage and divergence between true and approximate reward distributions. To address limitations in standard SMC, they propose SMC with Rejection Sampling (SMC-RS), which maintains high accuracy even when reward models are nearly perfect. Empirically, the study demonstrates that SMC consistently outperforms Best-of-N sampling on complex mathematical reasoning tasks and benchmarks. Ultimately, the work bridges the gap between ad hoc sampling heuristics and rigorous statistical theory to optimize the accuracy-cost tradeoff in AI inference.","meta_description":"This research paper investigates Sequential Monte Carlo (SMC) and other particle filtering algorithms as a theoretical framework for improving large langu…","key_points":[],"chapters":[],"topics":[],"duration_seconds":1350,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/best-ai-papers-explained-7258006/episodes/reject-resample-repeat-understanding-parallel-reasoning-in-language-model-inference/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/reject-resample-repeat-understanding-parallel-reasoning-in-language-model-inference.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}