MVP Lab

community

https://mvp-lab.ai

AI & ML interests

multi-modal foundation models

Recent Activity

oliveryanzuolu updated a dataset 3 days ago

mvp-lab/yz_data

WinKawaks updated a collection 8 days ago

EarlVLM initial checkpoints

WinKawaks updated a model 8 days ago

mvp-lab/earl-vlm-qwen35-35b-a3b-vit-pretrained-l40-gdn30-gqa10-e256-k8-s42-bf16

View all activity

Papers

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

View all Papers

updated a dataset 3 days ago

mvp-lab/yz_data

Preview • Updated 3 days ago • 520

updated a collection 8 days ago

EarlVLM initial checkpoints

Versioned EarlVLM initialization artifacts with pretrained ViT and seeded random projector/LLM. • 1 item • Updated 8 days ago

updated a model 8 days ago

mvp-lab/earl-vlm-qwen35-35b-a3b-vit-pretrained-l40-gdn30-gqa10-e256-k8-s42-bf16

Image-Text-to-Text • 35B • Updated 8 days ago • 33

published a model 8 days ago

mvp-lab/earl-vlm-qwen35-35b-a3b-vit-pretrained-l40-gdn30-gqa10-e256-k8-s42-bf16

Image-Text-to-Text • 35B • Updated 8 days ago • 33

updated 2 datasets about 2 months ago

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

Updated Aug 31 • 96.4k • 4

mvp-lab/LLaVA-OneVision-2-Data

Viewer • Updated Aug 30 • 24 • 137k • 47

in mvp-lab/MiniMax-H3-RAVEN-Streaming-LoRA 2 months ago

pruned ??

#1 opened 2 months ago by

davoodkharmanzar

updated 2 models 2 months ago

mvp-lab/MiniMax-H3-RAVEN-Streaming-LoRA

Text-to-Video • Updated Aug 20 • • 92

mvp-lab/RAVEN

Text-to-Video • Updated Aug 19 • 6

authored a paper 2 months ago

StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding

Paper • 2608.16320 • Published Aug 17 • 10

submitted a paper to Daily Papers 2 months ago

StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding

Paper • 2608.16320 • Published Aug 17 • 10

updated a collection 2 months ago

RAVEN

Real-time Autoregressive Video Extrapolation with Consistency-model GRPO • 3 items • Updated Aug 18

published a model 2 months ago

mvp-lab/MiniMax-H3-RAVEN-Streaming-LoRA

Text-to-Video • Updated Aug 20 • • 92

updated a collection 2 months ago

RAVEN

Real-time Autoregressive Video Extrapolation with Consistency-model GRPO • 3 items • Updated Aug 18

submitted a paper to Daily Papers 2 months ago

AVA-Encoder: Towards Agent-Native Video Representation Learning

Paper • 2608.12313 • Published Aug 12 • 43

updated a collection 3 months ago

LLaVA-OneVision-2

5 items • Updated Aug 2 • 7

authored a paper 3 months ago

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

Paper • 2607.24904 • Published Jul 27 • 39

updated a dataset 3 months ago

mvp-lab/Timelens_Video_temperal_grounding

Updated Jul 21 • 8 • 1