Shizhe Diao
shizhediao2
AI & ML interests
LLM pre-training and reasoning
Recent Activity
upvoted
a
paper
9 days ago
PhyCritic: Multimodal Critic Models for Physical AI
upvoted
a
paper
about 1 month ago
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization