CV

Education

• Ph.D candidate in University of Virginia, 2025-
• M.E. in Sichuan University University, 2021-2024
• B.E. in Sichuan University University, 2015-2019

Work experience

• Winter 2025: Intern Researcher
  • HoumoAI
  • DUties includes: Research on Resource Preserving Data Application
• Winter 2023: Intern Researcher
  • Lenovo Reasearch in Beijing
  • Duties includes: Research on Resource Preserving Data Application, Decentralized Data Analyses
• Winter 2022: Intern Student
  • NUS HPC Lab
  • Duties includes: Research on Resource Preserving Data Application
• Summer 2018: Intern Researcher
  • Lenovo Reasearch in Chengdu
  • Duties included: Decentralized Data Analyses

Publications

Pruning-Robust Mamba with Asymmetric Multi-Scale Scanning Paths

Pruning-Robust Mamba with Asymmetric Multi-Scale Scanning Paths. NeurIPS 2025. J. Lv, Y. Zhou, M. Shi, Z. Liang, P. Zhang, X. Peng, W. Zhao, Z. Zhu, J. Lv, Q. Ye, K. Wang

Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights

Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights. NeurIPS 2025. Z. Liang, D. Tang, Y. Zhou, X. Zhao, M. Shi, W. Zhao, Z. Li, P. Wang, K. Schürholt, D. Borth, M. M. Bronstein, Y. You, Z. Wang, K. Wang

A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training

A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training. CVPR 2025. K. Wang*, M. Shi*, Y. Zhou*,Z. Yuan, Y. Shang, X. Peng, H. Zhang, Y. You

Ferret: An Efficient Online Continual Learning Framework under Varying Memory Constraints

Ferret: An Efficient Online Continual Learning Framework under Varying Memory Constraints. CVPR 2025. Y. Zhou, Y. Tian, J. Lv, M. Shi, Y. Li, Q. Ye, S. Zhang, J. Lv

REPA Works Until It Doesn’t: Early-Stopped, Holistic Alignment Supercharges Diffusion Training

REPA Works Until It Does not: Early-Stopped, Holistic Alignment Supercharges Diffusion Training. NeurIPS 2025. Z. Wang, W. Zhao, Y. Zhou, Z. Li, Z. Liang, M. Shi, X. Zhao, P. Zhou, K. Zhang, Z. Wang, K. Wang, Y. You

DD-ranking: Rethinking the evaluation of dataset distillation

DD-ranking: Rethinking the evaluation of dataset distillation. Arxiv. Z. Li, X. Zhong, S. Khaki, Z. Liang, Y. Zhou, M. Shi, Z. Wang, X. Zhao, W. Zhao, Z. Qin, M. Wu, P. Zhou, H. Wang, D. J. Zhang, J. Liu, S. Wang, D. Liu, L. Zhang, G. Li, K. Wang, Z. Zhu, Z. Ma, J. T. Zhou, J. Lv, Y. Jin, P. Wang, K. Zhang, L. Lyu, Y. Huang, Z. Akata, Z. Deng, X. Wu, G. Cazenavette, Y. Shang, J. Cui, J. Gu, Q. Zheng, H. Ye, S. Wang, X. Wang, Y. Yan, A. Yao, M. Z. Shou, T. Chen, H. Bilen, B. Mirzasoleiman, M. Kellis, K. N. Plataniotis, Z. Wang, B. Zhao, Y. You, K. Wang

Make Optimization Once and for All with Fine-grained Guidance

Make Optimization Once and for All with Fine-grained Guidance. Arxiv. M. Shi, R. Lin, X. Chen, Y. Zhou, Z. Ding, P. Li, T. Wang, K. Wang, Z. Wang, J. Zhang, T. Chen.

GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning

GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning. Arxiv. S. Zhou*, S. Wang*, Z. Yuan*, M. Shi, Y. Shang, D. Yang.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training. Arxiv. M. Shi*, Y. Zhou*, R. Yu, Z. Li, Z. Liang, X. Zhao, X. Peng, T Rajpurohit, R. Vedantam, W. Zhao, K. Wang, Y. You.

Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformation

Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformation. NeurIPS 2025. X. Wu, J. Niu, X. Liu, M. Shi, G. Zhu, S. Tang.

Federated CINN Clustering for Accurate Clustered Federated Learning

Federated CINN Clustering for Accurate Clustered Federated Learning. ICASSP 2024. Y. Zhou, M. Shi, Y. Tian, Y. Li, Q. Ye, J. Lv

DeFTA: A Plug-and-Play Peer-to-Peer Decentralized Federated Learning Framework

DeFTA: A Plug-and-Play Peer-to-Peer Decentralized Federated Learning Framework. InfoSci. Y. Zhou, M. Shi, Y. Tian, Q. Ye, J. Lv

PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learning

PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learning. NeurIPS 2023. M. Shi, Y. Zhou, K. Wang, H. Zhang, S. Huang, Q. Ye, J. Lv

Unconstrained Feature Model and Its General Geometric Patterns in Federated Learning: Local Subspace Minority Collapse

Unconstrained Feature Model and Its General Geometric Patterns in Federated Learning: Local Subspace Minority Collapse. ICONIP 2023. M. Shi, Y. Zhou, Q. Ye, J. Lv

Communication-efficient Federated Learning with Single-Step Synthetic Features Compressor for Faster Convergence.

Communication-efficient Federated Learning with Single-Step Synthetic Features Compressor for Faster Convergence. ICCV 2023. Y. Zhou, M. Shi, Y. Li, Y. Sun, Q. Ye, J. Lv

DLB: a dynamic load balance strategy for distributed training of deep neural networks

DLB: a dynamic load balance strategy for distributed training of deep neural networks. Trans.ETCI. Q. Ye, Y. Zhou, M. Shi, Y. Sun, J. Lv

FLSGD: free local SGD with parallel synchronization

FLSGD: free local SGD with parallel synchronization. JoSc. Q. Ye, Y. Zhou, M. Shi, J. Lv