Jian Hu
jianh-nvidia
ยท
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 16 hours ago
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
upvoted
a
paper
about 1 month ago
Stabilizing Reinforcement Learning with LLMs: Formulation and Practices
new activity
about 2 months ago
nvidia/Nemotron-Research-Reasoning-Qwen-1.5B:Update README.md
Organizations
