Upload README.md with huggingface_hub

README.md

@@ -14,7 +14,7 @@ datasets:
 
 <p align="center"><img src="https://s41.ax1x.com/2026/06/25/pmtXRN4.png" width="100%" alt="GEAR"/></p>
 
-<p align="center"><a href="https://linb203.github.io/gear/">🏠 Homepage</a> &nbsp;|&nbsp; <a href="https://github.com/Tencent-Hunyuan/GEAR">💻 GitHub</a> &nbsp;|&nbsp; <a href="https://huggingface.co/collections/BinLin203">🤗 Models</a> &nbsp;|&nbsp; 📄 Paper (coming soon)</p>
+<p align="center"><a href="https://linb203.github.io/gear/">🏠 Homepage</a> &nbsp;|&nbsp; <a href="https://github.com/Tencent-Hunyuan/GEAR">💻 GitHub</a> &nbsp;|&nbsp; <a href="https://huggingface.co/collections/BinLin203">🤗 Models</a> &nbsp;|&nbsp; <a href="https://arxiv.org/abs/2606.32039">📄 Paper</a></p>
 
 
 ## This repository
@@ -46,7 +46,7 @@ standard LlamaGen backbone; train your own on a frozen GEAR tokenizer with the
 - 🏠 Project page: **https://linb203.github.io/gear/**
 - 💻 Code & full docs: **https://github.com/Tencent-Hunyuan/GEAR**
 - 🤗 All tokenizers: **https://huggingface.co/collections/BinLin203**
-- 📄 Paper: *coming soon*
+- 📄 Paper: **https://arxiv.org/abs/2606.32039**
 
 ## Released tokenizers
 
@@ -110,10 +110,14 @@ Open-MAGVIT2 and IBQ; please also respect those upstream licenses.
 ## Citation
 
 ```bibtex
-@article{gear,
-  title   = {GEAR: Guided End-to-End AutoRegression for Image Synthesis},
-  author  = {GEAR authors},
-  year    = {2026}
+@misc{lin2026gearguidedendtoendautoregression,
+  title         = {GEAR: Guided End-to-End AutoRegression for Image Synthesis},
+  author        = {Bin Lin and Zheyuan Liu and Chenguo Lin and Sixiang Chen and Yunyang Ge and Yunlong Lin and Jianwei Zhang and Miles Yang and Zhao Zhong and Liefeng Bo and Li Yuan},
+  year          = {2026},
+  eprint        = {2606.32039},
+  archivePrefix = {arXiv},
+  primaryClass  = {cs.CV},
+  url           = {https://arxiv.org/abs/2606.32039}
 }
 
 @article{ifsq_llamagenrepa,