Dachuan Shi

I received my Master's degree in Computer Technology and Bachelor's degree in Computer Science from Tsinghua University, advised by Prof. Chun Yuan and Prof. Linmin Tao. I interned at Shanghai AI Laboratory, working with Dr. Jiaqi Wang.

My main research interest is efficient deep learning, particularly for large models.

Email  /  Google Scholar  /  Github  /  LinkedIn

profile photo
Selected Research

CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers
Dachuan Shi, Chaofan Tao, Anyi Rao, Zhendong Yang, Chun Yuan, Jiaqi Wang
ICML, 2024
[Paper] [ArXiv] [Code]
UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers
Dachuan Shi, Chaofan Tao, Ying Jin, Zhendong Yang, Chun Yuan, Jiaqi Wang
ICML, 2023
[Paper] [ArXiv] [Code] [Website] [Blog] [博客]
Heuristic Dropout: An Efficient Regularization Method for Medical Image Segmentation Models
Dachuan Shi, Ruiyang Liu, Linmi Tao, Chun Yuan
ICASSP, 2022
[Paper] [Code]
Multi-Encoder Parse-Decoder Network for Sequential Medical Image Segmentation
Dachuan Shi, Ruiyang Liu, Linmi Tao, Zuoxiang He, Li Huo
ICIP, 2021
[Paper] [Code]
Selected Awards
  • Tsinghua Outstanding Master's Thesis, 2024
  • Tsinghua Comprehensive Excellence Scholarship, 2022
  • Tsinghua Outstanding Bachelor's Thesis, 2021
Services
Reviewer of ICML 2024, ICLR 2024, NeurIPS 20-[23,24], CVPR 2024, and ECCV 2024.

Modified from Jon Barron's Template