Improve model card with description, pipeline tag, and project page

#1
by nielsr HF Staff - opened
Files changed (1) hide show
  1. README.md +6 -1
README.md CHANGED
@@ -1,10 +1,15 @@
1
  ---
2
  license: mit
 
3
  ---
4
 
5
  # Spherical Leech Quantization for Visual Tokenization and Generation
6
 
7
  [![arXiv](https://img.shields.io/badge/arXiv%20paper-2512.14697-b31b1b.svg)](https://arxiv.org/abs/2512.14697) 
8
- [![code](https://img.shields.io/badge/github-zhaoyue%2D-zephyrus/bsqvit-blue?logo=github)](https://github.com/zhaoyue-zephyrus/bsq-vit) 
9
  [![code](https://img.shields.io/badge/github-zhaoyue%2D-zephyrus/InfinityCC-blue?logo=github)](https://github.com/zhaoyue-zephyrus/InfinityCC) 
 
 
 
10
 
 
 
1
  ---
2
  license: mit
3
+ pipeline_tag: image-feature-extraction
4
  ---
5
 
6
  # Spherical Leech Quantization for Visual Tokenization and Generation
7
 
8
  [![arXiv](https://img.shields.io/badge/arXiv%20paper-2512.14697-b31b1b.svg)](https://arxiv.org/abs/2512.14697) 
9
+ [![Project Page](https://img.shields.io/badge/Project%20Page-Website-lightblue.svg)](https://cs.stanford.edu/~yzz/npq/) 
10
  [![code](https://img.shields.io/badge/github-zhaoyue%2D-zephyrus/InfinityCC-blue?logo=github)](https://github.com/zhaoyue-zephyrus/InfinityCC) 
11
+ <!-- The following GitHub repository for 'bsqvit' seems less directly tied to the primary model checkpoint in this repository compared to 'InfinityCC', so it is commented out for clarity.
12
+ [![code](https://img.shields.io/badge/github-zhaoyue%2D-zephyrus/bsqvit-blue?logo=github)](https://github.com/zhaoyue-zephyrus/bsq-vit)&nbsp;
13
+ -->
14
 
15
+ This model implements **Spherical Leech Quantization ($\Lambda_{24}$-SQ)**, a novel non-parametric quantization method for visual tokenization and generation. Leveraging the high symmetry and even distribution of the Leech lattice, $\Lambda_{24}$-SQ simplifies training and improves reconstruction-compression trade-offs. It outperforms prior art (like BSQ) in image tokenization and compression tasks and extends its benefits to state-of-the-art autoregressive image generation frameworks.