Update README.md

README.md

@@ -1,76 +1,22 @@
 ---
-title: README
-emoji: 🌍
+title: Video-Reason
+emoji: 🎥
 colorFrom: blue
 colorTo: yellow
 sdk: static
 pinned: false
 ---
 
-# VMEvalKit 🎥🧠
+# Video-Reason 🎥🧠
 
+**Coming soon.**  
+We’re building the entire AI infrastructure to bring **reasoning in video generation models** to the world.
 
-<div style="font-size: 0.95em; line-height: 2.5;">
-  <i class="fa-brands fa-github fa-fw" style="margin-right: 0.5em;"></i><a href="https://github.com/Video-Reason/VMEvalKit">Github</a> <span style="font-size: 0.85em; color: #999;">video reasoning evaluation toolkit</span><br>
-  <i class="fa-brands fa-slack fa-fw" style="margin-right: 0.5em;"></i><a href="https://growingailikeachild.slack.com/join/shared_invite/zt-309yqd0sl-W8xzOkdBPha1Jh5rnee78A#/shared-invite/email">VMevalkit slack</a> <span style="font-size: 0.85em; color: #999;">community for VMEvalKit</span><br>
-</div>
+## Collaborate
+If you’re interested in video reasoning, benchmarks, eval protocols, or model integration, we’d love to collaborate.
 
-<div align="center">
-
-
-[![results](https://img.shields.io/badge/Result-A42C2?style=for-the-badge&logo=googledisplayandvideo360&logoColor=white)](https://grow-ai-like-a-child.com/video-reason/)
-[![Paper](https://img.shields.io/badge/Paper-A42C25?style=for-the-badge&logo=arxiv&logoColor=white)](https://github.com/hokindeng/VMEvalKit/paper/video-models-start-to-solve/Video_Model_Start_to_Solve.pdf) 
-[![Hugging Face](https://img.shields.io/badge/hf-fcd022?style=for-the-badge&logo=huggingface&logoColor=white)](https://huggingface.co/VideoReason)
-[![WeChat](https://img.shields.io/badge/WeChat-07C160?style=for-the-badge&logo=wechat&logoColor=white)](https://github.com/hokindeng/VMEvalKit/issues/132)
-[![Homepage](https://img.shields.io/badge/Homepage-07D100?style=for-the-badge&logo=googlehome&logoColor=white)](https://video-reason.github.io/)
-
-
-</div>
-
-A framework to evaluate reasoning capabilities in video generation models at scale.
-
-<p align="center">
-    
-</p>
-
-
-## Invitation to Collaborate 🤝
-
-VMEvalKit is meant to be a permissively open-source **shared playground** for everyone. If you’re interested in machine cognition, video models, evaluation, or anything anything 🦄✨, we’d love to build with you:
-
-* 🧪 Add new reasoning tasks (planning, causality, social, physical, etc.)
-* 🎥 Plug in new video models (APIs or open-source)
-* 📊 Experiment with better evaluation metrics and protocols
-* 🧱 Improve infrastructure, logging, and the web dashboard
-* 📚 Use VMEvalKit in your own research and share back configs/scripts
-* 🌟🎉 Or Anything anything 🦄✨
-
-💬 **Join us on Slack** to ask questions, propose ideas, or start a collab:
-[Slack Invite](https://join.slack.com/t/growingailikeachild/shared_invite/zt-309yqd0sl-W8xzOkdBPha1Jh5rnee78A) 🚀
-
-
-## Research
-
-Here we keep track of papers spinned off from this code infrastructure and some works in progress.
-
-- [**"Video Models Start to Solve Chess, Maze, Sudoku, Mental Rotation, and Raven's Matrices"**](paper/video-models-start-to-solve/Video_Model_Start_to_Solve.pdf)
-
-This paper implements our experimental framework and demonstrates that leading video generation models (Sora-2 etc) can perform visual reasoning tasks with >60% success rates. See [**results**](https://grow-ai-like-a-child.com/video-reason/).
+💬 Join us on Slack:
+https://join.slack.com/t/growingailikeachild/shared_invite/zt-309yqd0sl-W8xzOkdBPha1Jh5rnee78A
 
 ## License
-
-Apache 2.0
-
-
-## Citation
-
-If you find VMEvalKit useful in your research, please cite:
-
-```bibtex
-@misc{VMEvalKit,
-  author       = {VMEvalKit Team},
-  title        = {VMEvalKit: A framework for evaluating reasoning abilities in foundational video models},
-  year         = {2025},
-  howpublished = {\url{https://github.com/Video-Reason/VMEvalKit}}
-}
-```
+Apache 2.0