MVP Lab

AI & ML interests

multi-modal foundation models

Recent Activity

xiangan  updated a dataset about 8 hours ago

mvp-lab/IceFrog

xiangan  authored a paper 2 days ago

Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model

oliveryanzuolu  updated a bucket 2 days ago

mvp-lab/crafter-trajectories-bucket

View all activity

Papers

RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO

View all Papers

Team members 25