Improve model card and add metadata

Hi, I'm Niels from the community science team at Hugging Face.

This PR improves the model card for DecQ. Key changes include:
- Added the `image-to-image` pipeline tag to the metadata.
- Included links to the research paper and the official GitHub repository.
- Added a brief description of the model and its architecture.
- Added a sample usage section with instructions for image reconstruction.
- Added a BibTeX citation.

README.md

@@ -1,3 +1,45 @@
 ---
 license: apache-2.0
+pipeline_tag: image-to-image
 ---
+
+# DecQ: Detail-Condensing Queries for Enhanced Reconstruction and Generation in Representation Autoencoders
+
+This repository contains the weights for **DecQ**, a framework that introduces lightweight detail-condensing queries into Representation Autoencoders (RAEs). DecQ improves spatial reconstruction capacity while preserving the pretrained semantic space of vision foundation models (VFMs), facilitating high-quality image reconstruction and faster convergence in latent diffusion models.
+
+- **Paper:** [DecQ: Detail-Condensing Queries for Enhanced Reconstruction and Generation in Representation Autoencoders](https://huggingface.co/papers/2605.22777)
+- **Repository:** [GitHub - Tianhang-Wang/DecQ](https://github.com/Tianhang-Wang/DecQ)
+
+## Overview
+
+DecQ addresses the reconstruction–generation trade-off in RAEs by using detail-condensing queries to extract fine-grained information from intermediate VFM features through condenser modules. These queries are incorporated into the decoder to support reconstruction and are jointly generated with patch tokens during generative modeling.
+
+Key features:
+- **Lightweight:** Only 8 additional queries and 3.9% extra computation.
+- **Improved Reconstruction:** Significant PSNR improvement over frozen DINOv2-based RAEs.
+- **Faster Convergence:** Achieves 3.3× faster convergence in generative modeling.
+
+This repository currently contains the **Stage 1 tokenizer weights**.
+
+## Sample Usage
+
+To perform image reconstruction using the Stage 1 autoencoder, you can use the sampling script provided in the [official repository](https://github.com/Tianhang-Wang/DecQ):
+
+```bash
+python src/stage1_sample.py \
+  --config <config_path> \
+  --image <input_image_path>
+```
+
+Refer to the GitHub repository for environment setup and configuration files.
+
+## Citation
+
+```bibtex
+@article{wang2026decq,
+  title={DecQ: Detail-Condensing Queries for Enhanced Reconstruction and Generation in Representation Autoencoders},
+  author={Wang, Tianhang and Chen, Yitong and Song, Wei and Wu, Zuxuan and Li, Min and Wang, Jiaqi},
+  journal={arXiv preprint arXiv:2605.22777},
+  year={2026}
+}
+```