VICtoR: Learning Hierarchical Vision-Instruction Correlation Rewards for Long-horizon Manipulation

This repository contains the source code for our work, "VICtoR: Learning Hierarchical Vision-Instruction Correlation Rewards for Long-horizon Manipulation," which has been accepted to ICLR 2025.

We are currently in the process of organizing the code and data, and we will update the repository as soon as possible. In the meantime, please feel free to open an issue if you have any questions about our work. We would be happy to provide additional details before the resources become available.

Citation

If you find our work helpful for your research, please consider citing our paper:

  @inproceedings{hung2025victor,
    title={VICtoR: Learning Hierarchical Vision-Instruction Correlation Rewards for Long-horizon Manipulation},
    author={Kuo-Han Hung and Pang-Chi Lo and Jia-Fong Yeh and Han-Yuan Hsu and Yi-Ting Chen and Winston H. Hsu},
    booktitle={The Thirteenth International Conference on Learning Representations (ICLR)},
    url={https://openreview.net/forum?id=UpQLu9bzAR},
    year={2025}