Use the corresponding arXiv BibTeX citation

Update the repository card citation using the official arXiv export for 2607.23782.

README.md

@@ -53,6 +53,22 @@ contributes to the score. Object randomisation is +/-2-5 mm with no domain rando
 policy that ignores its cameras and its tactile sensors entirely can still score well. Use
 `scripts/probe_z_tactile_dependence.py` to measure the causal contribution yourself.
 
+## Citation
+
+If you use this model in your research, please cite the [N0-VTLA paper](https://arxiv.org/abs/2607.23782):
+
+```bibtex
+@misc{neoteaiteam2026n0vtlascalingvisiontactilelanguageactionmodel,
+      title={$N_0$-VTLA: Scaling Vision-Tactile-Language-Action Model with Latent Tactile Tokens},
+      author={NeoteAI Team and Fudan TEAI Team},
+      year={2026},
+      eprint={2607.23782},
+      archivePrefix={arXiv},
+      primaryClass={cs.RO},
+      url={https://arxiv.org/abs/2607.23782},
+}
+```
+
 ## License
 
 CC BY-SA 4.0, as the parent repository.