LMMs-Lab-Audio

AI & ML interests

Feeling and building the multimodal intelligence

Recent Activity

mwxely  authored a paper 3 days ago

Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL

mwxely  authored a paper 4 days ago

WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors

mwxely  authored a paper 11 days ago

Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling

View all activity

Team members 4