Python
Update README: use arxiv for tech report
kangzhuoliangd90e6f7f107c
diff --git a/README.md b/README.mdindex 6092911..624b106 100644--- a/README.md+++ b/README.md@@ -7,7 +7,7 @@<div align="center" style="line-height: 1;"><a href='https://meituan-longcat.github.io/LongCat-Video/'><img src='https://img.shields.io/badge/Project-Page-green'></a>- <a href='https://github.com/meituan-longcat/LongCat-Video/blob/main/longcatvideo_tech_report.pdf'><img src='https://img.shields.io/badge/Technique-Report-red'></a>+ <a href='https://arxiv.org/abs/2510.22200'><img src='https://img.shields.io/badge/Technique-Report-red'></a><a href='https://huggingface.co/meituan-longcat/LongCat-Video'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Model-blue'></a></div>@@ -29,7 +29,7 @@ We introduce LongCat-Video, a foundational video generation model with 13.6B par- π **Efficient inference**: LongCat-Video generates $720p$, $30fps$ videos within minutes by employing a coarse-to-fine generation strategy along both the temporal and spatial axes. Block Sparse Attention further enhances efficiency, particularly at high resolutions- π **Strong performance with multi-reward RLHF**: Powered by multi-reward Group Relative Policy Optimization (GRPO), comprehensive evaluations on both internal and public benchmarks demonstrate that LongCat-Video achieves performance comparable to leading open-source video generation models as well as the latest commercial solutions.-For more detail, please refer to the comprehensive [***LongCat-Video Technical Report***](https://github.com/meituan-longcat/LongCat-Video/blob/main/longcatvideo_tech_report.pdf).+For more detail, please refer to the comprehensive [***LongCat-Video Technical Report***](https://arxiv.org/abs/2510.22200).## π₯ Teaser Videodiff --git a/longcatvideo_tech_report.pdf b/longcatvideo_tech_report.pdfdeleted file mode 100644index 119e0e5..0000000Binary files a/longcatvideo_tech_report.pdf and /dev/null differ