Improve model card: Add metadata, links, abstract, and usage for Concerto

This PR enhances the model card for the Concerto model by:
- Adding key metadata: `pipeline_tag: graph-ml`, `library_name: pytorch`, `license: apache-2.0`, and descriptive `tags`.
- Updating the paper link to the Hugging Face paper page.
- Including direct links to the official project page and the GitHub repository for easy access to code and further details.
- Adding the paper abstract to provide comprehensive context about the model.
- Guiding users to the GitHub repository for detailed installation, training, and inference instructions, adhering to the guidelines of not making up code snippets.

Please review and merge this PR.

README.md

@@ -1 +1,42 @@
-Model weights for [Concerto](arxiv.org/abs/2510.23607)
+---
+pipeline_tag: graph-ml
+library_name: pytorch
+license: apache-2.0
+tags:
+- 3d
+- point-cloud
+- self-supervised-learning
+---
+
+# Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations
+
+This repository contains the model weights for **Concerto**, a novel approach for learning robust spatial representations presented in the paper [Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations](https://huggingface.co/papers/2510.23607).
+
+- **Paper:** [Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations](https://huggingface.co/papers/2510.23607)
+- **Project Page:** [https://pointcept.github.io/Concerto/](https://pointcept.github.io/Concerto/)
+- **Codebase:** [https://github.com/Pointcept/Pointcept](https://github.com/Pointcept/Pointcept)
+
+## Abstract
+Humans learn abstract concepts through multisensory synergy, and once formed, such representations can often be recalled from a single modality. Inspired by this principle, we introduce Concerto, a minimalist simulation of human concept learning for spatial cognition, combining 3D intra-modal self-distillation with 2D-3D cross-modal joint embedding. Despite its simplicity, Concerto learns more coherent and informative spatial features, as demonstrated by zero-shot visualizations. It outperforms both standalone SOTA 2D and 3D self-supervised models by 14.2% and 4.8%, respectively, as well as their feature concatenation, in linear probing for 3D scene perception. With full fine-tuning, Concerto sets new SOTA results across multiple scene understanding benchmarks (e.g., 80.7% mIoU on ScanNet). We further present a variant of Concerto tailored for video-lifted point cloud spatial understanding, and a translator that linearly projects Concerto representations into CLIP's language space, enabling open-world perception. These results highlight that Concerto emerges spatial representations with superior fine-grained geometric and semantic consistency.
+
+## Usage
+For detailed installation, data preparation, training, and testing instructions, please refer to the [official GitHub repository](https://github.com/Pointcept/Pointcept).
+
+## Citation
+If you find Concerto or the Pointcept codebase useful in your research, please cite the following papers:
+
+```bibtex
+@misc{pointcept2023,
+    title={Pointcept: A Codebase for Point Cloud Perception Research},
+    author={Pointcept Contributors},
+    howpublished = {\url{https://github.com/Pointcept/Pointcept}},
+    year={2023}
+}
+
+@article{zhang2025concerto,
+  title={Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations},
+  author={Zhang, Yujia and Wu, Xiaoyang and Lao, Yixing and Wang, Chengyao and Tian, Zhuotao and Wang, Naiyan and Zhao, Hengshuang},
+  journal={Conference on Neural Information Processing Systems},
+  year={2025},
+}
+```