HuggingFace 每日AI论文速递

【周末特辑】10月第4周最火AI论文 | 内部概率+投票剪尾,RPC省样本提精度

本期的 5 篇论文如下:

[00:29] TOP1(🔥135) | 🧠 A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning(大模型推理中内部概率与自洽性桥接的理论研究)

[03:02] TOP2(🔥104) | 🚀 Efficient Long-context Language Model Training by Core Attention Disaggregation(通过核心注意力拆解实现高效长上下文语言模型训练)

[05:29] TOP3(🔥100) | 🧠 LightMem: Lightweight and Efficient Memory-Augmented Generation(LightMem:轻量高效的记忆增强生成框架)

[07:33] TOP4(🔥90) | 🧠 Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning(每一种注意力都重要:面向长上下文推理的高效混合架构)

[10:18] TOP5(🔥79) | 🤖 DeepAnalyze: Agentic Large Language Models for Autonomous Data Science(DeepAnalyze:面向自主数据科学的智能体大模型)

【关注我们】

您还可以在以下平台找到我们,获得播客内容以外更多信息

小红书: AI速递