Versioned EarlVLM initialization artifacts with pretrained ViT and seeded random projector/LLM.
MVP Lab
community
AI & ML interests
multi-modal foundation models
Recent Activity
Papers
View all Papersdatasets 15
mvp-lab/Spatial4D
Updated • 4.65k • 2
mvp-lab/yz_data
Preview • Updated • 145
mvp-lab/LLaVA-OneVision-2-Data-Part2
Updated • 29.2k • 4
mvp-lab/LLaVA-OneVision-2-Data
Viewer • Updated • 24 • 52.7k • 51
mvp-lab/Timelens_Video_temperal_grounding
Updated • 236 • 1
mvp-lab/LLaVA-OneVision-1.5-Mid-Training-85M
Preview • Updated • 694k • 111
mvp-lab/LLaVA-OneVision-1.5-Instruct-Data
Viewer • Updated • 21.9M • 61.6k • 91
mvp-lab/mvp-engine-vlm-dev-data
Preview • Updated • 21
mvp-lab/mvp-engine-llm-dev-data
Preview • Updated • 18
mvp-lab/mvp-engine-minimal-vlm-data
Viewer • Updated • 503 • 142