Link the arXiv paper instead of OpenReview

README.md

@@ -16,7 +16,7 @@ datasets:
 Pretrained weights for **NAMVIS** (NeurIPS 2026), a diffusion-free, geometry-conditioned
 next-scale autoregressive model for sparse-view novel view synthesis.
 
-- 📄 Paper: [OpenReview](https://openreview.net/forum?id=dTzafRJOTR)
+- 📄 Paper: [arXiv:2610.04722](https://arxiv.org/abs/2610.04722)
 - 🌐 Project page: https://corl-team.github.io/namvis
 - 💻 Code: https://github.com/corl-team/namvis
 - 🗂️ Training data: [Part 1](https://huggingface.co/datasets/smileyenot983/objaversexl_sketchfab_pmap) · [Part 2](https://huggingface.co/datasets/smileyenot983/objaversexl_github6.5_pmap)
@@ -47,10 +47,13 @@ Inference, evaluation, and fine-tuning commands are in the
 
 ```bibtex
 @inproceedings{khafizov2026namvis,
-  title     = {{NAMVIS}: Next-Scale Autoregressive Multi-View Image Synthesis},
-  author    = {Khafizov, Ramil and Statsenko, Ilya and Rakhimov, Ruslan and Komarichev, Artem and Wonka, Peter and Burnaev, Evgeny},
-  booktitle = {Advances in Neural Information Processing Systems},
-  year      = {2026},
-  url       = {https://openreview.net/forum?id=dTzafRJOTR}
+  title         = {{NAMVIS}: Next-Scale Autoregressive Multi-View Image Synthesis},
+  author        = {Khafizov, Ramil and Statsenko, Ilya and Rakhimov, Ruslan and Komarichev, Artem and Wonka, Peter and Burnaev, Evgeny},
+  booktitle     = {Advances in Neural Information Processing Systems},
+  year          = {2026},
+  eprint        = {2610.04722},
+  archivePrefix = {arXiv},
+  primaryClass  = {cs.CV},
+  url           = {https://arxiv.org/abs/2610.04722}
 }
 ```