🦜 VideoChat Family: Ask-Anything 中文 README 及 中文交流群 | Paper ⭐️: We are also working on a updated version, stay tuned! :fire: Updates 2026/07/17: 🚀🚀 We release VideoChat3, a fully open, efficient 4B Video MLLM for general, long-form, and streaming video understanding. VideoChat3 improves 18/19 offline and 10/11 streaming metrics over Qwen3-VL-4B. We release the model weights, code, training recipes, and complete…
⭐️: We are also working on a updated version, stay tuned!
:fire: Updates
2026/07/17: 🚀🚀 We release VideoChat3, a fully open, efficient 4B Video MLLM for general, long-form, and streaming video understanding. VideoChat3 improves 18/19 offline and 10/11 streaming metrics over Qwen3-VL-4B. We release the model weights, code, training recipes, and complete datasets. Check out our paper and homepage!
2025/01/18: We release videochat-flash and videochat-tpo to extend MLLMs’ capabilities on both long and accurate video understanding. videochat-flash sets new records in mutiple video benchmarks (for both short and long videos), improving code usability by leveaging LLaVA and others. videochat-tpo exploits classical vision task annotations (e.g. tracking) to optimize MLLMs in a DPO manner, enhancing MLLMs’ performance and enabling capabilities in tracking, segmentation, and more.
2024/06/19: 🎉🎉 Our VideoChat2 achieves the best performances among the open-sourced VideoLLMs on MLVU, a multi-task long video understanding benchmark.
2024/06/13: Fix some bug and give testing scripts/
:warning: We replace some repeated (~30) QAs in MVBench, which may only affect the results by 0.5%.
2024/06/07: :fire::fire::fire: We release VideoChat2_HD, which is fine-tuned with high-resolution data and is capable of handling more diverse tasks. It showcases better performance on different benchmarks, especially for detailed captioning. Furthermore, it achieves 54.8% on Video-MME, the best score among 7B MLLMs. Have a try! 🏃🏻♀️🏃🏻
2024/06/06: We release VideoChat2_phi3, a faster model with robust performaces.
2024/05/22: We release VideoChat2_mistral, which shows better capacity on diverse tasks (60.4% on MVBench, 78.6% on NExT-QA, 63.8% on STAR, 46.4% on TVQA, 54.4% on EgoSchema-full and 80.5% on IntentQA). More details have been updated in the paper.
2024/04/05 MVBench is selected as Poster (Highlight)!
MiniGPT-4 for video: Implicit communication with Vicuna. Not sensitive with time. (Simple extension of MiniGPT-4, which will be improved in the future.)
If you find this project useful in your research, please consider cite:
@article{2023videochat,
title={VideoChat: Chat-Centric Video Understanding},
author={KunChang Li, Yinan He, Yi Wang, Yizhuo Li, Wenhai Wang, Ping Luo, Yali Wang, Limin Wang, and Yu Qiao},
journal={arXiv preprint arXiv:2305.06355},
year={2023}
}
@inproceedings{li2024mvbench,
title={Mvbench: A comprehensive multi-modal video understanding benchmark},
author={Li, Kunchang and Wang, Yali and He, Yinan and Li, Yizhuo and Wang, Yi and Liu, Yi and Wang, Zun and Xu, Jilan and Chen, Guo and Luo, Ping and others},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={22195--22206},
year={2024}
}
🌤️ Discussion Group
If you have any questions during the trial, running or deployment, feel free to join our WeChat group discussion! If you have any ideas or suggestions for the project, you are also welcome to join our WeChat group discussion!
We are hiring researchers, engineers and interns in General Vision Group, Shanghai AI Lab. If you are interested in working with us, please contact Yi Wang ([email protected]).
[VideoChat-7B-8Bit] End2End ChatBOT for video and image.
评论