Dachuan Shi

I am a first-year CS Ph.D. student at Georgia Tech, working with Prof. Wenke Lee. Previously, I received my M.S. and B.S. in CS with honors from Tsinghua University.

Email / Google Scholar / Github / LinkedIn

Research

I do research in (M)LLM post-training, including reasoning, efficiency, and safety.

	LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models Dachuan Shi, Yonggan Fu, Xiangchi Yuan, Zhongzhi Yu, Haoran You, Sixu Li, Xin Dong, Jan Kautz, Pavlo Molchanov, Yingyan Celine Lin ICML, 2025 [Paper] [ArXiv] [Code]
	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]

Experience

Research Intern @ Microsoft, Redmond, WA, USA, 2025
Research Intern @ Shanghai AILab, Shanghai, CN, 2022-24

Services

TA @ CS4476 Computer Vision, Gerogia Tech, Spring 2025
Reviewer @ ICML 20-[24,25], NeurIPS 20-[23,24], ICLR 20-[24,25], CVPR 20-[24,25], ICCV 2025, ECCV 2024, and ACL ARR 2025

Template Credits