Add Releases table to org card

README.md

@@ -1,6 +1,6 @@
 ---
 title: Video-Reason
-emoji: 🎬
+emoji: "\U0001F3AC"
 colorFrom: blue
 colorTo: purple
 sdk: static
@@ -33,6 +33,15 @@ Our flagship project, **VBVR (Very Big Video Reasoning)**, introduces an unprece
 - **Verifiable evaluation** via rule-based, human-aligned scorers (no model-based judging)
 - **Early signs of emergent generalization** to unseen reasoning tasks through large-scale scaling studies
 
+## Releases
+
+| Resource | Description | Link |
+|---|---|---|
+| VBVR-Wan2.2 | Strong baseline model fine-tuned from Wan2.2-I2V-A14B on the VBVR Dataset | [Model](https://huggingface.co/Video-Reason/VBVR-Wan2.2) |
+| VBVR-Dataset | 1M video reasoning training samples across 100 curated task generators (~310 GB) | [Dataset](https://huggingface.co/datasets/Video-Reason/VBVR-Dataset) |
+| VBVR-Bench-Data | Official benchmark test set (500 samples across in-domain and out-of-domain splits) | [Dataset](https://huggingface.co/datasets/Video-Reason/VBVR-Bench-Data) |
+| VBVR-Bench-Leaderboard | Public leaderboard for standardized model comparison | [Space](https://huggingface.co/spaces/Video-Reason/VBVR-Bench-Leaderboard) |
+
 ## Links
 
 - **Website**: https://video-reason.com  
@@ -66,4 +75,5 @@ If you use VBVR in your research, please cite:
   journal = {arXiv preprint arXiv:2602.20159},
   year    = {2026},
   url     = {https://arxiv.org/abs/2602.20159}
-}
+}
+```