MVP Lab

community

https://mvp-lab.ai

AI & ML interests

multi-modal foundation models

Recent Activity

xiangan updated a dataset about 4 hours ago

mvp-lab/LLaVA-OneVision-2-Data-Part2

xiangan updated a collection 4 days ago

LLaVA-OneVision-2

xiangan updated a collection 4 days ago

LLaVA-OneVision-2

View all activity

Papers

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

View all Papers

mvp-lab 's models 3

mvp-lab/Qwen3-VL-8B-Base-woDS-stage0

Image-Text-to-Text • 9B • Updated May 21 • 5

mvp-lab/RAVEN

Text-to-Video • Updated May 15 • 4

mvp-lab/LLaVA-OneVision-1.5-8B-RL

9B • Updated Dec 3, 2025 • 12 • 3