Dehao Huang
red0orange
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
10 days ago
Unsupervised Post-Training for Multi-Modal LLM Reasoning via GRPO
upvoted
a
paper
10 days ago
Advancing Multimodal Reasoning via Reinforcement Learning with Cold
Start
Organizations
Collections
1
models
0
None public yet
datasets
0
None public yet