arxiv:2605.10434
Zuhao Yang
mwxely
AI & ML interests
Large Multimodal Models
Recent Activity
authored a paper about 20 hours ago
Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL authored a paper 2 days ago
WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors