shawnli

Intermediate
@shawnli

on-policy-distillation-research. On-Policy Distillation 调研资料：包含 ICLR 2024 论文、Hugging Face TRL 和 Thinking Machines Lab 的代码实现

25

on-policy-distillation. Implementation of On-Policy Distillation (GKD) for Language Models - ICLR 2024

21

world-model-research. 世界模型（World Model）调研项目：收集李飞飞、LeCun和Meta的最新世界模型开源代码和研究资料

19

agent-learning-early-experience. Implementation of Meta's 'Agent Learning via Early Experience' paper - 基于Meta论文的智能体早期经验学习实现

3

fatterchen. Python

2

FinanceResearchAI. 金融投研大模型训练系统 - 基于OpenManus的智能投资分析与自我迭代系统

1

planning-with-files. Claude Code skill implementing Manus-style persistent markdown planning — the workflow pattern behind the B acquisition.

1
7
Apply