Vchitect

non-profit

https://vchitect.intern-ai.org.cn/

Vchitect

Activity Feed Request to join this org

AI & ML interests

generative models, video generation

Recent Activity

Ziqi authored a paper about 13 hours ago

Exploring MLLM-Diffusion Information Transfer with MetaCanvas

Ziqi authored a paper about 13 hours ago

WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World

Ziqi authored a paper about 13 hours ago

BabyVision: Visual Reasoning Beyond Language

View all activity

Papers

Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark

View all Papers

Vchitect 's models 9

Vchitect/LongVie2

Image-to-Video • Updated 22 days ago • 25

Vchitect/ShotVL-7B

Image-Text-to-Text • 8B • Updated Sep 19, 2025 • 153 • 15

Vchitect/SEINE

Image-to-Video • Updated Jul 29, 2025 • 15

Vchitect/ShotVL-3B

Image-Text-to-Text • 4B • Updated Jul 7, 2025 • 25 • 8

Vchitect/VBench-2.0_models

Updated Jun 12, 2025 • 1

Vchitect/Vchitect-2.0-2B

Text-to-Video • Updated Mar 25, 2025 • 1 • 39

Vchitect/RepVideo

Text-to-Video • Updated Jan 17, 2025 • 4

Vchitect/Vlogger

Updated Jan 19, 2024 • 8

Vchitect/LaVie

Text-to-Video • Updated Dec 4, 2023 • 20