Update README.md

README.md

@@ -25,9 +25,9 @@ This organization contains models, datasets, benchmarks and code released with t
   - [ViDoRe Leaderboard](https://huggingface.co/spaces/vidore/vidore-leaderboard)
 
 - **Benchmarks:**
-  - ViDoRe V1 ([blogpost](https://huggingface.co/blog/manu/colpali), [dataset collection](https://huggingface.co/collections/vidore/vidore-benchmark))
-  - ViDoRe V2 ([blogpost](https://huggingface.co/blog/manu/vidore-v2), [dataset collection](https://huggingface.co/collections/vidore/vidore-benchmark-v2))
-  - ViDoRe V3 ([blogpost](https://huggingface.co/blog/QuentinJG/introducing-vidore-v3), [dataset collection](https://hf.co/collections/vidore/vidore-benchmark-v3))
+  - ViDoRe V1 ([paper](https://arxiv.org/abs/2407.01449), [blogpost](https://huggingface.co/blog/manu/colpali), [dataset collection](https://huggingface.co/collections/vidore/vidore-benchmark))
+  - ViDoRe V2 ([paper](https://arxiv.org/abs/2505.17166), [blogpost](https://huggingface.co/blog/manu/vidore-v2), [dataset collection](https://huggingface.co/collections/vidore/vidore-benchmark-v2))
+  - ViDoRe V3 ([paper](https://arxiv.org/abs/2601.08620), [blogpost](https://huggingface.co/blog/QuentinJG/introducing-vidore-v3), [dataset collection](https://hf.co/collections/vidore/vidore-benchmark-v3))
 
 - **Models:**
   - ColPali ([latest: v1.3](https://huggingface.co/vidore/colpali-v1.3))
@@ -40,6 +40,8 @@ This organization contains models, datasets, benchmarks and code released with t
 
 # 👷‍♂️ ViDoRe V3: A comprehensive evaluation of Retrieval for enterprise use-cases
 
+[![arXiv](https://img.shields.io/badge/arXiv-2601.08620-b31b1b.svg?style=for-the-badge)](https://arxiv.org/abs/2601.08620)
+
 <img src="https://cdn-uploads.huggingface.co/production/uploads/66e16a677c2eb2da5109fb5c/-zqFfhdtsC1VzQH-rLkLa.png" width="1300" style="display: block; margin-left: auto; margin-right: auto;" />
 
 ILLUIN Technology is proud to release the **ViDoRe V3 benchmark**, designed and developed with contributions from NVIDIA. ViDoRe V3 is our latest benchmark, engineered to set a new industry gold standard for multi-modal, enterprise document retrieval evaluation. It addresses a critical challenge in production RAG systems: retrieving accurate information from complex, visually-rich documents.
@@ -93,6 +95,16 @@ If you use any datasets or models from this organization in your research, pleas
       primaryClass={cs.IR},
       url={https://arxiv.org/abs/2505.17166}, 
 }
+
+@misc{loison2026vidorev3comprehensiveevaluation,
+      title={ViDoRe V3: A Comprehensive Evaluation of Retrieval Augmented Generation in Complex Real-World Scenarios}, 
+      author={António Loison and Quentin Macé and Antoine Edy and Victor Xing and Tom Balough and Gabriel Moreira and Bo Liu and Manuel Faysse and Céline Hudelot and Gautier Viaud},
+      year={2026},
+      eprint={2601.08620},
+      archivePrefix={arXiv},
+      primaryClass={cs.AI},
+      url={https://arxiv.org/abs/2601.08620}, 
+}
 ```
 
 ---