Update model card

README.md

@@ -19,14 +19,14 @@ Sapiens2 is a family of high-resolution vision transformers pretrained on **1 bi
 
 This repository contains the **1B parameter pretrained backbone**. It produces dense per-patch features suitable for fine-tuning downstream task heads.
 
-- 📄 **Paper:** [OpenReview (ICLR 2026)](https://openreview.net/pdf?id=IVAlYCqdvW)
+- 📄 **Paper:** [arXiv:2604.21681](https://arxiv.org/pdf/2604.21681)
 - 🌐 **Project Page:** [rawalkhirodkar.github.io/sapiens2](https://rawalkhirodkar.github.io/sapiens2)
 - 💻 **Code:** [github.com/facebookresearch/sapiens2](https://github.com/facebookresearch/sapiens2)
 
 ## Model Details
 
 - **Developed by:** Meta
-- **Model type:** Vision Transformer (RoPE, GQA, SwiGLU, RMSNorm, QK-norm)
+- **Model type:** Vision Transformer
 - **License:** [Sapiens2 License](https://github.com/facebookresearch/sapiens2/blob/main/LICENSE.md)
 - **Task:** pretrain
 - **Format:** safetensors
@@ -92,10 +92,10 @@ Released under the [Sapiens2 License](https://github.com/facebookresearch/sapien
 ## Citation
 
 ```bibtex
-@inproceedings{khirodkar2026sapiens2,
+@article{khirodkarsapiens2,
   title={Sapiens2},
-  author={Khirodkar, Rawal and Wen, He and Martinez, Julieta and Dong, Yuan and Zhaoen, Su and Saito, Shunsuke},
-  booktitle={International Conference on Learning Representations (ICLR)},
+  author={Khirodkar, Rawal and Wen, He and Martinez, Julieta and Dong, Yuan and Su, Zhaoen and Saito, Shunsuke},
+  journal={arXiv preprint arXiv:2604.21681},
   year={2026}
 }
 ```