iVideoGPT (Pre-trained on Open X-Embodiment, 64x64 resolution, action-free)
Pre-trained model introduced in the paper iVideoGPT: Interactive VideoGPTs are Scalable World Models .
See https://github.com/thuml/iVideoGPT for examples for using this model.
Citation
@article{wu2024ivideogpt,
title={iVideoGPT: Interactive VideoGPTs are Scalable World Models},
author={Jialong Wu and Shaofeng Yin and Ningya Feng and Xu He and Dong Li and Jianye Hao and Mingsheng Long},
journal={arXiv preprint arXiv:2405.15223},
year={2024},
}
- Downloads last month
- 0