Hi, I'm Dachuan.

/DAH-chwahn/

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

Research [/]

My recent research focuses on LLMs/MLLMs reasoning, agents, and efficiency.

[ICLR 2026] SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs
Dachuan Shi, Abedelkadir Asi, Keying Li, Xiangchi Yuan, Leyan Pan, Wenke Lee, Wen Xiao
[Paper] [Code] [Website]

[ICML 2025] 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
[Paper] [Code]

[ICML 2024] CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers
Dachuan Shi, Chaofan Tao, Anyi Rao, Zhendong Yang, Chun Yuan, Jiaqi Wang
[Paper] [Code]

[ICML 2023] UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers
Dachuan Shi, Chaofan Tao, Ying Jin, Zhendong Yang, Chun Yuan, Jiaqi Wang
[Paper] [Code] [Website]

[Preprint 2026] Behavior Knowledge Merge in Reinforced Agentic Models
Xiangchi Yuan, Dachuan Shi, Chunhui Zhang, Zheyuan Liu, Shenglong Yao, Soroush Vosoughi, Wenke Lee
[Paper] [Code] [Website]

[CVPR 2026] Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding
Zhongxing Xu*, Zhonghua Wang*, Zhe Qian*, Dachuan Shi, Feilong Tang, Ming Hu, Shiyan Su, Xiaocheng Zou, Wei Feng, Dwarikanath Mahapatra, Yifan Peng, Mingquan Lin, Zongyuan Ge
[Paper] [Code] [Website]

[Preprint 2025] Mitigating Forgetting Between Supervised and Reinforcement Learning Yields Stronger Reasoners
Xiangchi Yuan, Xiang Chen, Tong Yu, Dachuan Shi, Can Jin, Wenke Lee, Saayan Mitra
[Paper]

[EMNLP 2025] Superficial Self-Improved Reasoners Benefit from Model Merging
Xiangchi Yuan, Chunhui Zhang, Zheyuan Liu, Dachuan Shi, Leyan Pan, Soroush Vosoughi, Wenke Lee
[Paper] [Code]

[Preprint 2024] Supervised Fine-tuning in turn Improves Visual Foundation Models
Xiaohu Jiang, Yixiao Ge, Yuying Ge, Dachuan Shi, Chun Yuan, Ying Shan
[Paper] [Code]

[ECCV 2022] Masked Generative Distillation
Zhendong Yang, Zhe Li, Mingqi Shao, Dachuan Shi, Zehuan Yuan, Chun Yuan
[Paper] [Code]

Experience [/]

Tsinghua

B.S. in CS

Tsinghua

M.S. in CS

Georgia Tech

Ph.D. in CS

2017–21

Tsinghua Outstanding Bachelor's Thesis

2021–24

Tsinghua Outstanding Master's Thesis

2024–

Shanghai AI Lab

Research Intern

Microsoft

Research Intern

2022–24

Multimodal LLMs, Inference Optimization

2025

Reasoning LLMs, Math & Coding