Towards Reasoning in Video Generation Models!
We build open-source tools to generate, evaluate, and understand reasoning in video models.
Very Big Video Reasoning (VBVR) is a research initiative investigating whether video generation models can perform genuine reasoning — solving chess puzzles, navigating mazes, completing Sudoku, mental rotation, and Raven's matrices — purely through visual generation. VBVR-DataFactory is a highly efficient, serverless data-generation engine powered by AWS Lambda — capable of producing millions of puzzle instances in minutes with 300+ generators, near-linear horizontal scaling, and minimal infrastructure cost. VBVR-EvalKit implements unified inference across 37 commercial and open-source video models, and deterministic evaluation with 100+ rule-based benchmarks. All tools are open-source under Apache 2.0.
For all generators, checkout https://github.com/VBVR-DataFactory
For documentation, benchmarks, and project updates, see: https://video-reason.com/
VBVR-EvalKit — Evaluation Toolkit
Unified inference and evaluation across 37 video generation models.
VBVR-DataFactory — Scalable Data Generation
Distributed data generation system built on AWS Lambda with 300+ generators.
Awesome-Video-Reasoning — Paper Collection
A curated list of research papers on reasoning with video generation models
- Website: video-reason.com
- Slack: Join our workspace
- HuggingFace: Video-Reason
- Contact: hokinxqdeng@gmail.com
If you use VBVR in your research, please cite:
@article{vbvr2026,
title = {A Very Big Video Reasoning Suite},
author = {Wang, Maijunxian and Wang, Ruisi and Lin, Juyi and Ji, Ran and
Wiedemer, Thaddäus and Gao, Qingying and Luo, Dezhi and
Qian, Yaoyao and Huang, Lianyu and Hong, Zelong and Ge, Jiahui and
Ma, Qianli and He, Hang and Zhou, Yifan and Guo, Lingzi and
Mei, Lantao and Li, Jiachen and Xing, Hanwen and Zhao, Tianqi and
Yu, Fengyuan and Xiao, Weihang and Jiao, Yizheng and
Hou, Jianheng and Zhang, Danyang and Xu, Pengcheng and
Zhong, Boyang and Zhao, Zehong and Fang, Gaoyun and Kitaoka, John and
Xu, Yile and Xu, Hua and Blacutt, Kenton and Nguyen, Tin and
Song, Siyuan and Sun, Haoran and Wen, Shaoyue and He, Linyang and
Wang, Runming and Wang, Yanzhi and Yang, Mengyue and Ma, Ziqiao and
Millière, Raphaël and Shi, Freda and Vasconcelos, Nuno and
Khashabi, Daniel and Yuille, Alan and Du, Yilun and Liu, Ziming and
Lin, Dahua and Liu, Ziwei and Kumar, Vikash and Li, Yijiang and
Yang, Lei and Cai, Zhongang and Deng, Hokin},
year = {2026}
}