[ACM MM 2026] HeatTok: Enhancing Remote Sensing Image Understanding via Thermodiffusion-based Tokenization

This repository provides the VRSBench checkpoint of HeatTok-Qwen2.5-VL-7B.

πŸ”— Quick Links

πŸ“Œ Citation

If you find HeatTok useful in your research, please cite our paper:

@inproceedings{yan2026heatok,
    title={HeatTok: Enhancing Remote Sensing Image Understanding via Thermodiffusion-based Tokenization},
    author={Yingying Yan and Jiaqi Tang and Wei Wei and Qianzhou Wang and Jinjian Wu and Botong Geng and Jianmin Chen and Yuyang Xia and Lei Zhang},
    booktitle={Proceedings of the 34th ACM International Conference on Multimedia},
    year={2026},
    publisher={ACM},
    address={Rio de Janeiro, Brazil},
    doi={10.1145/3767308.3835640}
}
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Paper for Yingying11/HeatTok-VRSBench-7B