Zhihe Yang's picture

3 5

Zhihe Yang

zhyang2226

·

AI & ML interests

Trustworthy RL & Offline RL

Recent Activity

upvoted a paper 15 days ago

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs

liked a dataset about 2 months ago

BytedTsinghua-SIA/DAPO-Math-17k

upvoted a paper 3 months ago

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key

View all activity

Organizations

models 2

zhyang2226/opadpo-lora_llava-v1.5-13b

zhyang2226/opadpo-lora_llava-v1.5-7b

datasets 0

None public yet