alphaXiv 推荐两篇新综述：连续扩散语言模型与机制可解释性
Academia needs human-written literature surveys now more than ever.
摘要
alphaXiv 本周推荐两篇新综述：一篇由 Sophia Tang 等人撰写，聚焦连续扩散与流语言模型；另一篇由 Fazl Barez 和 Tony Wu 主导，聚焦机制可解释性。推文认为论文数量与噪声已超出 AI 有效梳理的范畴，因此人类撰写的文献综述比以往更重要，并称这两篇是了解上述领域的宝贵资源。
摘要由模型根据原文撰写，以原文为准。
正文 · 原文
Academia needs human-written literature surveys now more than ever.
There are simply too many papers and too much noise for AI to effectively contextualize it all. Thankfully, two excellent new surveys came out this week on continuous diffusion and mech interp!
On continuous diffusion & flow language models, from @_sophia_tang_ and collaborators:
https://www.alphaxiv.org/abs/2611.continuous-diffusion-flow-language-models
On mechanistic interpretability, led by @FazlBarez & @TonyWu1105: https://www.alphaxiv.org/abs/2611.08438
Super valuable resources for anyone looking to learn more about either of these fields!
来源：alphaXiv · x.com
引用原文
askalphaxiv. Academia needs human-written literature surveys now more than ever.[EB/OL]. (2026-11-10)[访问日期]. https://x.com/askalphaxiv/status/2120176655591252206.