liyaxuan's picture

7

liyaxuan

lllyx

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 3 days ago

Your Group-Relative Advantage Is Biased

upvoted an article 11 days ago

Re-understanding KL Approximation from an RL-for-LLM Lens: Notes on “Approximating KL Divergence”

upvoted a paper 15 days ago

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

View all activity

Organizations

None yet

lllyx 's Spaces 1

ML Patch

Submit data for inference and view results