Project

Rethinking Workflow Optimization

Thinking as a Tool

Rubric as Reward, Self-Evolve, Continue Learning

Small Agents, Stronger Together

Coding

Reading

basic

LLM基础调研

大模型基础教材（赵鑫）

DeepSeek Tech Reports

扩散概率模型

PaLm-E: 谷歌的具象化多模态语言模型