Zikun Li
zikun-li
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 23 hours ago
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
upvoted
a
paper
2 days ago
Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting
Organizations
None yet