Improve model card: Add metadata, links, overview, and citation

This PR enhances the model card by adding key metadata and comprehensive information:

- Adds `pipeline_tag: image-text-to-text` to correctly categorize the model for multimodal tasks.
- Adds `library_name: transformers` as the model architecture (`llava_llama` and `AnchorLlava`) and `transformers_version` in `config.json` indicate compatibility with the `transformers` library, enabling the "How to use" widget.
- Includes a direct link to the paper: [Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens](https://huggingface.co/papers/2511.19418).
- Provides links to the official project page (https://wakalsprojectpage.github.io/comt-website) and the GitHub repository (https://github.com/Wakals/CoMT) for easy access to more resources.
- Expands the "Model Description" with a detailed overview of CoVT's methodology and benefits, derived from the paper's abstract and the GitHub README.
- Embeds relevant demo images from the GitHub repository to visually illustrate the model's capabilities.
- Adds a BibTeX citation for the paper.

Please review and merge if these improvements align with your expectations.

README.md

@@ -1,8 +1,45 @@
 ---
 license: apache-2.0
+pipeline_tag: image-text-to-text
+library_name: transformers
 ---
-# CoVT Checkpoint (Segmentation, Depth, and DINO Aligned)
+
+# Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens
+
+[![Arixv](https://img.shields.io/badge/arxiv-A42C25?style=for-the-badge&logo=arxiv&logoColor=white)](https://huggingface.co/papers/2511.19418)
+[![Project Page](https://img.shields.io/badge/Project_Page-00CED1?style=for-the-badge&logoColor=white&logo=data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9IjAgMCAyNCAyNCIgZmlsbD0id2hpdGUiPjxwYXRoIGQ9Ik0xMCAyMHYtNmg0djZoNXYtOGgzTDEyIDMgMiAxMmgzdjh6Ii8+PC9zdmc+)](https://wakalsprojectpage.github.io/comt-website)
+[![Github Code](https://img.shields.io/badge/Github-Code-keygen.svg?logo=github&style=flat-square)](https://github.com/Wakals/CoMT)
 
 ## Model Description
 This CoVT checkpoint is aligned with **4 Depth tokens**, based on LLaVA-v1.5-13B.  
 These task-specific tokens are integrated into the model’s embedding space to enhance 3D-awareness.
+
+## Overview
+Vision-Language Models (VLMs) excel at reasoning in linguistic space but struggle with perceptual understanding that requires dense visual perception, *e.g.*, spatial reasoning and geometric awareness. This limitation stems from the fact that current VLMs have limited mechanisms to capture dense visual information across spatial dimensions.
+
+**Chain-of-Visual-Thought (CoVT)** is a framework that enables VLMs to reason not only in words but also through **continuous visual tokens** — compact latent representations that encode rich perceptual cues. Within a small budget of roughly **20 tokens**, CoVT distills knowledge from lightweight vision experts, capturing complementary properties such as **2D appearance, 3D geometry, spatial layout, and edge structure**. During training, the VLM with CoVT autoregressively predicts these visual tokens to reconstruct dense supervision signals (*e.g.*, depth, segmentation, edges, and DINO features). At inference, the model reasons directly in the continuous visual token space, preserving efficiency while optionally decoding dense predictions for interpretability. Evaluated across more than **ten diverse perception benchmarks**, integrating CoVT into strong VLMs such as Qwen2.5-VL and LLaVA consistently improves performance.
+
+These visual “thought chains” bridge language and vision, enabling fine-grained understanding, spatial precision, and geometric awareness beyond the reach of text-based reasoning.
+
+<div align="center">
+  <img src="https://github.com/Wakals/CoMT/raw/main/assets/DEMO.jpg" alt="CoVT Demo" style="width: 100%; margin: 10px 0;">
+  <img src="https://github.com/Wakals/CoMT/raw/main/assets/edit_demo.jpg" alt="CoVT Edit Demo" style="width: 100%; margin: 10px 0;">
+</div>
+
+For more details on evaluation, Gradio demo, and training CoVT, please refer to the [GitHub repository](https://github.com/Wakals/CoMT).
+
+## Citation
+If you use this work in your research, please cite:
+
+```bibtex
+@article{qin2025chainofvisualthought,
+  title={Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens},
+  author={Qin, Yiming and Wei, Bomin and Ge, Jiaxin and Kallidromitis, Konstantinos and Fu, Stephanie and Darrell, Trevor and Wang, Xudong},
+  journal={arXiv preprint arXiv:2511.19418},
+  year={2025},
+  eprint={2511.19418},
+  archivePrefix={arXiv},
+  primaryClass={cs.CV},
+  url={https://arxiv.org/abs/2511.19418},
+}
+```