Qiying Yu's picture

6 8 15

Qiying Yu

qiying

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 25 days ago

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

updated a dataset 2 months ago

BytedTsinghua-SIA/DAPO-Math-17k

authored a paper 3 months ago

DAPO: An Open-Source LLM Reinforcement Learning System at Scale

View all activity

Organizations

New activity in CausalLM/miniG 10 months ago

About the Data Generation Method

#4 opened 10 months ago by

New activity in MMInstruction/ArxivQA about 1 year ago

How do you use the rationales and answers in your training?

#1 opened about 1 year ago by