garyzhang's picture

2 8 5

garyzhang

xiaoniqiu

·

garyzhang99

AI & ML interests

LLM, Agents

Recent Activity

updated a dataset 7 days ago

datajuicer/geometry_sft

published a dataset 7 days ago

datajuicer/geometry_sft

upvoted a paper 24 days ago

Group-Relative REINFORCE Is Secretly an Off-Policy Algorithm: Demystifying Some Myths About GRPO and Its Friends

View all activity

Organizations

commented 2 papers 2 months ago

On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting

Paper • 2508.11408 • Published Aug 15 • 8 •

On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting

Paper • 2508.11408 • Published Aug 15 • 8 •

New activity in shenzhi-wang/Llama3-8B-Chinese-Chat over 1 year ago

Add json mode inference for Llama3-8B-Chinese-Chat

#26 opened over 1 year ago by