Mobile Vision Perception Lab

community

https://github.com/mvp-ai-lab

AI & ML interests

multi-modal foundation models

Recent Activity

xiangan authored a paper 10 days ago

OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence

yiyexy submitted a paper 11 days ago

OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence

xiangan authored a paper 16 days ago

ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder

View all activity

Collections 1

spaces 4

70113 ImgGen Diffusion SD15xSDXL

70113 ImgGen Diffusion SDXLxFLUX

70113 ImgGen Diffusion ControlNetxLoRA

Transform your images into styled artwork using control patterns

70113 Test

Generate high-quality images from text prompts in seconds

models 1

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

9B • Updated Dec 3, 2025 • 26 • 2

datasets 6

mvp-lab/LLaVA-OneVision-1.5-RL-Data

Viewer • Updated Jan 6 • 69.2k • 384 • 6

mvp-lab/LLaVA-OneVision-1.5-Mid-Training-85M

Viewer • Updated Nov 24, 2025 • 91.5M • 155k • 59

mvp-lab/LLaVA-OneVision-1.5-Instruct-Data

Viewer • Updated Nov 21, 2025 • 21.9M • 66.8k • 65

mvp-lab/LLaVA-558K-Webdataset

Updated Oct 21, 2025 • 406 • 4

mvp-lab/LLaVA-NeXT-780k-webdataset

Updated Oct 11, 2025 • 967

mvp-lab/LLaVA-OneVision-1.5-Mid-Training-Webdataset-Quick-Start-3M

Updated Sep 20, 2025 • 6.38k • 2