Add model card

README.md

@@ -1,3 +1,34 @@
----
-license: cc-by-4.0
----
+---
+license: cc-by-4.0
+pipeline_tag: any-to-any
+---
+
+# ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body
+
+ViBES (Voice in Behavioral Expression and Synchrony) is a speech-language-behavior (SLB) model with a mixture-of-modality-experts (MoME) architecture. It is a conversational 3D agent that jointly plans language and movement and executes dialogue-conditioned body actions, enabling controllable and socially competent 3D interaction.
+
+- **Paper:** [ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body](https://huggingface.co/papers/2512.14234)
+- **Project Page:** [https://ai.stanford.edu/~juze/ViBES/](https://ai.stanford.edu/~juze/ViBES/)
+- **GitHub Repository:** [https://github.com/Juzezhang/ViBES](https://github.com/Juzezhang/ViBES)
+
+## Usage
+
+To run the inference for conversational behavior of facial expressions, please follow the environment setup instructions in the [official repository](https://github.com/Juzezhang/ViBES) and then use the following command:
+
+```bash
+python inference/inference_a2m_face.py --user_text "If you had a superpower for one day, what would you choose?"
+```
+
+## Citation
+
+If you find this work useful in your research, please consider citing:
+
+```bibtex
+@inproceedings{
+      zhang2026vibes,
+        title={ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body},
+      author={Juze Zhang and Changan Chen and Xin Chen and Heng Yu and Tiange Xiang and Ali Sartaz Khan and Shrinidhi Kowshika Lakshmikanth and Ehsan Adeli},
+      booktitle={CVPR},
+      year={2026},
+}
+```