Update README.md

README.md

@@ -11,15 +11,13 @@ library_name: pytorch
 <sup>1</sup> Westlake University,
 <sup>2</sup> Institute of Automation, Chinese Academy of Sciences
 
-[![arXiv](https://img.shields.io/badge/arXiv-2503.10568-A42C25?style=flat&logo=arXiv)](https://arxiv.org/abs/2503.10568) [![Project](https://img.shields.io/badge/Project-Page-green?style=flat&logo=Google%20chrome&logoColor=green)](https://hp-l33.github.io/projects/arpg) [![HuggingFace](https://img.shields.io/badge/HuggingFace-Model-blue?style=flat&logo=HuggingFace)](https://huggingface.co/hp-l33/ARPG)
-
 ## News
 * **2025-03-14**: The paper and code are released!
 
 ## Introduction
 We introduce a novel autoregressive image generation framework named **ARPG**. This framework is capable of conducting **BERT-style masked modeling** by employing a **GPT-style causal architecture**. Consequently, it is able to generate images in parallel following a random token order and also provides support for the KV cache. 
 * 💪 **ARPG** achieves an FID of **1.94**
-* 🚀 **ARPG** delivers throughput **26 times faster** than [LlamaGen](https://github.com/FoundationVision/LlamaGen)—nearly matching [VAR](https://github.com/FoundationVision/VAR)
+* 🚀 **ARPG** delivers throughput **26 times faster** than [LlamaGen](https://github.com/FoundationVision/LlamaGen).
 * ♻️ **ARPG** reducing memory consumption by over **75%** compared to [VAR](https://github.com/FoundationVision/VAR).
 * 🔍 **ARPG** supports **zero-shot inference** (e.g., inpainting and outpainting).
 * 🛠️ **ARPG** can be easily extended to **controllable generation**.