diff --git a/taochenxin/TaoChenxin.md b/taochenxin/TaoChenxin.md
index 90d4a9a..deb8520 100644
--- a/taochenxin/TaoChenxin.md
+++ b/taochenxin/TaoChenxin.md
@@ -16,6 +16,17 @@ PhD Students
 <a href="https://scholar.google.com/citations?user=sXHFIBkAAAAJ&hl=zh-CN">Google Scholar</a>
 
 ### Publications
+#### HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding
+<a href="https://arxiv.org/pdf/2412.16158">paper</a>
+<a href="https://huggingface.co/OpenGVLab/HoVLE">model</a>
+
+Bib: Chenxin Tao*, Shiqian Su*, Xizhou Zhu*, Chenyu Zhang, Zhe Chen, Jiawen Liu, Wenhai Wang, Lewei Lu, Gao Huang, Yu Qiao, Jifeng Dai.
+IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
+
+Tags: Multi-modal Models
+
+![HoVLE](./assets/HoVLE.png)
+
 #### Learning 1D Causal Visual Representation with De-focus Attention Networks
 <a href="https://arxiv.org/pdf/2406.04342">paper</a>
 <a href="https://github.com/OpenGVLab/De-focus-Attention-Networks">code</a>
diff --git a/taochenxin/assets/HoVLE.png b/taochenxin/assets/HoVLE.png
new file mode 100644
index 0000000..d4ce83d
Binary files /dev/null and b/taochenxin/assets/HoVLE.png differ