Cite NeurIPS 2026 and load from mose3-tracker/MoSE3

README.md

@@ -17,7 +17,7 @@ monocular RGB video, generalizing across **rigid, articulated and deformable obj
 ```python
 from mose3.models.mose3 import MoSE3
 
-model = MoSE3.from_pretrained("JoannaCCCCCC/MoSE3", strict=True).cuda().eval()
+model = MoSE3.from_pretrained("mose3-tracker/MoSE3", strict=True).cuda().eval()
 ```
 
 The [code repository](https://github.com/mose3-tracker/MoSE3) has the full inference and visualization scripts.
@@ -30,13 +30,11 @@ The weights are released under [CC BY-NC 4.0](https://creativecommons.org/licens
 ## Citation
 
 ```bibtex
-@misc{cheng2026mose3learningworldspacese3,
-      title={MoSE3: Learning World-Space SE(3) at Every Pixel},
-      author={Jiahuan Cheng and Zhiyi Li and Tian Xia and Ruojin Cai and Yilun Du and Qianqian Wang},
-      year={2026},
-      eprint={2610.03716},
-      archivePrefix={arXiv},
-      primaryClass={cs.CV},
-      url={https://arxiv.org/abs/2610.03716},
+@inproceedings{cheng2026mose3,
+  title     = {{MoSE3}: Learning World-Space {SE(3)} at Every Pixel},
+  author    = {Cheng, Jiahuan and Li, Zhiyi and Xia, Tian and
+               Cai, Ruojin and Du, Yilun and Wang, Qianqian},
+  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
+  year      = {2026}
 }
 ```