<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Writing on Yan Yan</title><link>https://chrisyany.com/posts/</link><description>Recent content in Writing on Yan Yan</description><generator>Hugo</generator><language>en-US</language><copyright>© 2026 Yan Yan</copyright><lastBuildDate>Tue, 25 Aug 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://chrisyany.com/posts/index.xml" rel="self" type="application/rss+xml"/><item><title>The Creator Flywheel: Notes on the Creation Problem</title><link>https://chrisyany.com/posts/creator-flywheel/</link><pubDate>Tue, 25 Aug 2026 00:00:00 +0000</pubDate><guid>https://chrisyany.com/posts/creator-flywheel/</guid><description>Turning viewers into creators, then growing creators into top creators: one flywheel, two engines, and three levers for thinking about where modeling fits in the creation problem on a short-video platform.</description></item><item><title>OPRO &amp; GR2: LLMs as Optimizers and Generative Reasoning Re-rankers</title><link>https://chrisyany.com/posts/opro-and-gr2/</link><pubDate>Fri, 10 Jul 2026 00:00:00 +0000</pubDate><guid>https://chrisyany.com/posts/opro-and-gr2/</guid><description>A close reading of OPRO, which uses meta-prompts to let LLMs iteratively optimize prompts, and GR2, which builds a recommendation re-ranker via semantic-ID mid-training, reasoning data generation, and DAPO RL.</description></item><item><title>Paper Notes, May 2026: Five Papers on Ranking, Training, and Retrieval</title><link>https://chrisyany.com/posts/may-2026-paper-notes/</link><pubDate>Fri, 05 Jun 2026 00:00:00 +0000</pubDate><guid>https://chrisyany.com/posts/may-2026-paper-notes/</guid><description>Notes on five papers: CrossDistil&amp;rsquo;s cross-task distillation, DMT&amp;rsquo;s topology-aware training, an enhanced twin-tower retriever, Pinterest&amp;rsquo;s DHEN for CVR prediction, and Xiaohongshu&amp;rsquo;s UniNote multimodal embedding.</description></item><item><title>Diffusion Models for Recommender Systems: A Reading Report</title><link>https://chrisyany.com/posts/diffusion-models-for-recsys/</link><pubDate>Fri, 27 Feb 2026 00:00:00 +0000</pubDate><guid>https://chrisyany.com/posts/diffusion-models-for-recsys/</guid><description>A close reading of DiffuRec, Flow Matching, and the learning dynamics of LLM finetuning, plus a survey of research directions, key papers, and open bottlenecks for diffusion in recommendation.</description></item><item><title>LLMs Meet Recommender Systems: A Map of 41 Papers (2022–2025)</title><link>https://chrisyany.com/posts/llm-recsys-landscape/</link><pubDate>Thu, 26 Feb 2026 00:00:00 +0000</pubDate><guid>https://chrisyany.com/posts/llm-recsys-landscape/</guid><description>A categorized reading report on 41 papers at the intersection of recommender systems and LLMs, spanning Semantic ID generative retrieval, two-tower cold start, ranking scaling, and diffusion models.</description></item></channel></rss>