Yihong Wu's picture

Yihong Wu

Yihong7788

·

AI & ML interests

None yet

Recent Activity

commentedon a paper about 1 month ago

It Takes Two: Your GRPO Is Secretly DPO

upvoted a paper 6 months ago

It Takes Two: Your GRPO Is Secretly DPO

upvoted a paper 6 months ago

On Predictability of Reinforcement Learning Dynamics for Large Language Models

View all activity

Organizations

None yet

Papers 1

arxiv:2311.01056

models 3

Yihong7788/qwen2.5-2wiki-kg-sft-300

Text Generation • 8B • Updated May 11, 2025 • 1

Yihong7788/qwen2.5-hotpotqa-sft-300

Text Generation • 8B • Updated May 10, 2025 • 7

Yihong7788/Llama-3.2-3B-Instruct_kg_sft_1k

Text Generation • 3B • Updated Mar 26, 2025 • 1

datasets 1

Yihong7788/Hard_Question_2WIKI_Train

Updated Apr 24, 2025 • 5