---
library_name: transformers
license: apache-2.0
---

# Model Card for LISA-RS
We fine-tune [LISA](https://github.com/dvlab-research/LISA) reasoning segmentation model with dataset from AVS training dataset from [AVS-Bench](https://huggingface.co/datasets/derektan95/avs-bench).

For more information on usage, please refer to the [LISA-AVS Github repository here](https://github.com/marmotlab/LISA-AVS).

## Citation
```
@inproceedings{tan2025searchtta,
  title     = {Search-TTA: A Multimodal Test-Time Adaptation Framework for Visual Search in the Wild},
  author    = {Derek Ming Siang Tan, Shailesh, Boyang Liu, Alok Raj, Qi Xuan Ang, Weiheng Dai, Tanishq Duhan, Jimmy Chiun, Yuhong Cao, Florian Shkurti, Guillaume Sartoretti},
  booktitle = {Conference on Robot Learning},
  year      = {2025},
  url       = {https://arxiv.org/abs/2505.11350}
}

@article{lai2023lisa,
  title={LISA: Reasoning Segmentation via Large Language Model},
  author={Lai, Xin and Tian, Zhuotao and Chen, Yukang and Li, Yanwei and Yuan, Yuhui and Liu, Shu and Jia, Jiaya},
  journal={arXiv preprint arXiv:2308.00692},
  year={2023}
}
```