Add model card and pipeline tag

README.md

@@ -1,7 +1,45 @@
 ---
-license: apache-2.0
 datasets:
 - lmms-lab/RefCOCO
+license: apache-2.0
+pipeline_tag: image-segmentation
 tags:
 - multimodal
----
+- referring-image-segmentation
+---
+
+# TALENT: Target-aware Efficient Tuning for Referring Image Segmentation
+
+TALENT is a framework for Referring Image Segmentation (RIS) designed to address the "non-target activation" (NTA) issue in parameter-efficient tuning. It introduces a Rectified Cost Aggregator (RCA) to aggregate text-referred features and a Target-aware Learning Mechanism (TLM) to calibrate activation into accurate target localization.
+
+## Resources
+
+- **Paper:** [TALENT: Target-aware Efficient Tuning for Referring Image Segmentation](https://huggingface.co/papers/2604.00609)
+- **Repository:** [GitHub - Kimsure/TALENT](https://github.com/Kimsure/TALENT)
+
+## Usage
+
+To evaluate the model, follow the installation instructions in the [GitHub repository](https://github.com/Kimsure/TALENT) and run the following script:
+
+```bash
+bash run_scripts/test.sh
+```
+
+To visualize the results, you can set the `visualize` flag to `True` in the configuration file.
+
+## Acknowledgements
+
+The code for TALENT is based on [CRIS](https://github.com/DerrickWang005/CRIS.pytorch), [ETRIS](https://github.com/kkakkkka/ETRIS), and previous TALENT implementations. We thank the authors for their open-sourced code.
+
+## Citation
+
+If you find this work useful, please cite:
+
+```bibtex
+@article{talent2026,
+  title={TALENT: Target-aware Efficient Tuning for Referring Image Segmentation},
+  author={...},
+  journal={arXiv preprint arXiv:2604.00609},
+  year={2026}
+}
+```