Tianzhu Ye 叶天竺

About Me

My research focuses on building more capable and generalizable AI foundation models. I work as a research intern with GenAI group at Microsoft Research Asia, mentored by Li Dong.

Email: yetianzhu2022@gmail.com

Google Scholar: GS

Selected Publications

• Differential Transformer
  Tianzhu Ye*, Li Dong*, Yuqing Xia*, Yutao Sun*, Yi Zhu, Gao Huang, Furu Wei
  International Conference on Learning Representations (ICLR), 2025 (Oral)
  Paper | Code

• Agent Attention: On the Integration of Softmax and Linear Attention
  Dongchen Han*, Tianzhu Ye*, Yizeng Han, Zhuofan Xia, Siyuan Pan, Pengfei Wan, Shiji Song, Gao Huang
  European Conference on Computer Vision (ECCV), 2024
  Paper | Code

• Slide-Transformer: Hierarchical Vision Transformer with Local Self-Attention
  Xuran Pan*, Tianzhu Ye*, Zhuofan Xia, Shiji Song, Gao Huang
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
  Paper | Code

• Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers
  Siyuan Wei*, Tianzhu Ye*, Shen Zhang, Yao Tang, Jiajun Liang
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
  Paper | Code

Education

• Undergrauate student, Tsinghua University (2020 - 2024)

Internship

• Research intern, GenAI at Microsoft Research Asia, mentored by Li Dong (2023 - )
• Research intern, Megvii Technology (2022 - 2023)