diff --git a/_pages/publications.md b/_pages/publications.md
index 4b42497bfc5ea..1724ed06c92f5 100644
--- a/_pages/publications.md
+++ b/_pages/publications.md
@@ -7,7 +7,7 @@ author_profile: true
 
 
 <div style="display:inline-block; border:2px; margin:10px;">
- <img src="../images/paper_cover_image/ACCV2022.png" style="float:left;" width="300" alt="markdown" align="left" hspace="10px">
+ <img src="../images/paper_cover_image/ACCV2022.png" style="float:left;" width="350" alt="markdown" align="left" hspace="10px">
 <p><b>Caoyun Fan</b>, Wenqing Chen, Jidong Tian, Yitian Li, Hao He, Yaohui Jin. "MaxGNR: A Dynamic Weight Strategy via Maximizing Gradient-to-Noise Ratio for Multi-Task Learning", <b>ACCV-2022 (CCF-C)</b>. 
 <a href="https://arxiv.org/abs/2302.09352">[PDF]</a>,
 <i><b>TL,DR</b>: A Dynamic Weight Strategy via Maximizing Gradient-to-Noise Ratio in Multi-Task Learning. </i>