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 PapersReal-time Autoregressive Video Extrapolation with Consistency-model GRPO
-
mvp-lab/LLaVA-OneVision-1.5-Instruct-Data
Viewer • Updated • 21.9M • 73.8k • 91 -
mvp-lab/LLaVA-OneVision-1.5-Mid-Training-85M
Preview • Updated • 762k • 111 -
lmms-lab/LLaVA-OneVision-1.5-8B-Instruct
Image-Text-to-Text • 9B • Updated • 4.93k • 68 -
lmms-lab/LLaVA-OneVision-1.5-4B-Instruct
Image-Text-to-Text • 5B • Updated • 905 • 17
Versioned EarlVLM initialization artifacts with pretrained ViT and seeded random projector/LLM.
mvp-engine
Real-time Autoregressive Video Extrapolation with Consistency-model GRPO
-
mvp-lab/LLaVA-OneVision-1.5-Instruct-Data
Viewer • Updated • 21.9M • 73.8k • 91 -
mvp-lab/LLaVA-OneVision-1.5-Mid-Training-85M
Preview • Updated • 762k • 111 -
lmms-lab/LLaVA-OneVision-1.5-8B-Instruct
Image-Text-to-Text • 9B • Updated • 4.93k • 68 -
lmms-lab/LLaVA-OneVision-1.5-4B-Instruct
Image-Text-to-Text • 5B • Updated • 905 • 17