Update model card

README.md

@@ -1,12 +1,41 @@
 ---
-license: other
-tags: [robotics, image-to-image, video-generation]
+pipeline_tag: robotics
+tags:
+  - robotics
+  - human-to-robot
+  - video-generation
+  - inverse-dynamics
 ---
+
 # RoboTryOn
 
-Checkpoints for [RoboTryOn](https://github.com/ryan-seungyong-lee/RoboTryOn) ([paper](https://arxiv.org/abs/2611.05163)).
+Checkpoints for **Synthesizing Dexterous Robot Demonstrations from Human Videos via Virtual Try-On**.
+
+[Paper](https://arxiv.org/abs/2611.05163) · [Project page](https://ryan-seungyong-lee.github.io/RoboTryOn) · [Code](https://github.com/ryan-seungyong-lee/RoboTryOn)
 
-| Path | Model | Base |
+| Folder | Model | Base |
 |---|---|---|
-| `image/` | keyframe translation (LoRA + widened `x_embedder`) | [FLUX.2-klein-base-9B](https://huggingface.co/black-forest-labs/FLUX.2-klein-base-9B) |
-| `video/` | video synthesis (in-context LoRA) | [LTX-2.5-Diffusers](https://huggingface.co/Lightricks/LTX-2.5-Diffusers) |
+| `image/` | Keyframe translation (LoRA) | [FLUX.2-klein-base-9B](https://huggingface.co/black-forest-labs/FLUX.2-klein-base-9B) |
+| `video/` | Video synthesis (in-context LoRA) | [LTX-2.5-Diffusers](https://huggingface.co/Lightricks/LTX-2.5-Diffusers) |
+| `idm/` | Inverse dynamics model, shared by all embodiments | [Depth-Anything-V2-Large](https://huggingface.co/depth-anything/Depth-Anything-V2-Large-hf) |
+
+All models are trained on teleoperated episodes of OpenArm, RB-Y1 and GR-1.
+
+## Usage
+
+```bash
+hf download RyanL22/RoboTryOn --local-dir ckpt
+python scripts/run_pipeline.py --config configs/pipeline.yaml ... \
+    checkpoints.image=ckpt/image checkpoints.video=ckpt/video checkpoints.idm=ckpt/idm
+```
+
+## Citation
+
+```bibtex
+@article{lee2026robotryon,
+  title={Synthesizing Dexterous Robot Demonstrations from Human Videos via Virtual Try-On},
+  author={Lee, Seungyong and Jang, Suhyeok and Kim, Minyoung and Shin, Jinwoo},
+  journal={arXiv preprint arXiv:2611.05163},
+  year={2026}
+}
+```