<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>LLM Study on SincereCSL's Blog</title><link>https://sincerecsl.github.io/tags/llm-study/</link><description>Recent content in LLM Study on SincereCSL's Blog</description><generator>Hugo</generator><language>zh-CN</language><managingEditor>SincereCSL@163.com (SincereCSL)</managingEditor><webMaster>SincereCSL@163.com (SincereCSL)</webMaster><lastBuildDate>Thu, 25 Dec 2025 10:00:00 +0800</lastBuildDate><atom:link href="https://sincerecsl.github.io/tags/llm-study/index.xml" rel="self" type="application/rss+xml"/><item><title>转载：2025 我最喜欢的 LLM x AI 论文集</title><link>https://sincerecsl.github.io/llm-x-ai/</link><pubDate>Thu, 25 Dec 2025 10:00:00 +0800</pubDate><author>SincereCSL@163.com (SincereCSL)</author><guid>https://sincerecsl.github.io/llm-x-ai/</guid><description>&lt;h2 id="2025-我最喜欢的-llm-x-ai-论文集"&gt;2025 我最喜欢的 LLM x AI 论文集&lt;/h2&gt;
&lt;p&gt;2025年快过去了。&lt;/p&gt;
&lt;p&gt;这一年，我几乎每天都有坚持读论文和分享论文， 获益匪浅。&lt;/p&gt;
&lt;p&gt;下面是我整理的个人年度最喜欢论文集：&lt;/p&gt;
&lt;h3 id="1test-time-scaling"&gt;1、Test Time Scaling&lt;/h3&gt;
&lt;ul&gt;
&lt;li&gt;“Thinking” 到底是什么？&lt;/li&gt;
&lt;/ul&gt;
&lt;p&gt;&lt;a href="https://arxiv.org/pdf/2501.12948" target="_blank" rel="noopener noreffer "&gt;DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning&lt;/a&gt;&lt;/p&gt;</description></item></channel></rss>