Mingjia Shi

29 papers A* 4B 2Journal 21Unranked 2
YearRankTypeTitle / Venue / Authors
2026 J jnl
IAPO: Information-Aware Policy Optimization for Token-Efficient Reasoning.
CoRR
Yinhan He, Yaochen Zhu, Mingjia Shi, Wendy Zheng, Lin Su, Xiaoqing Wang, Qi Guo, Jundong Li
2026 J jnl
Saliency-Aware Multi-Route Thinking: Revisiting Vision-Language Reasoning.
CoRR
Mingjia Shi, Yinhan He, Yaochen Zhu, Jundong Li
2025 A* conf
A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training.
CVPR
Kai Wang, Mingjia Shi, Yukun Zhou, Zekai Li, Zhihang Yuan, Yuzhang Shang, Xiaojiang Peng, Hanwang Zhang, Yang You
2025 J jnl
DD-Ranking: Rethinking the Evaluation of Dataset Distillation.
CoRR
Zekai Li, Xinhao Zhong, Samir Khaki, Zhiyuan Liang, Yuhao Zhou, Mingjia Shi, Ziqiao Wang, Xuanlei Zhao, Wangbo Zhao, Ziheng Qin, Mengxuan Wu, Pengfei Zhou, Haonan Wang, David Junhao Zhang, Jia-Wei Liu, Shaobo Wang, Dai Liu, Linfeng Zhang, Guang Li, Kun Wang, Zheng Zhu, Zhiheng Ma, Joey Tianyi Zhou, Jiancheng Lv, Yaochu Jin, Peihao Wang, Kaipeng Zhang, Lingjuan Lyu, Yiran Huang, Zeynep Akata, Zhiwei Deng, Xindi Wu, George Cazenavette, Yuzhang Shang, Justin Cui, Jindong Gu, Qian Zheng, Hao Ye, Shuo Wang, Xiaobo Wang, Yan Yan, Angela Yao, Mike Zheng Shou, Tianlong Chen, Hakan Bilen, Baharan Mirzasoleiman, Manolis Kellis, Konstantinos N. Plataniotis, Zhangyang Wang, Bo Zhao, Yang You, Kai Wang
2025 J jnl
Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights.
CoRR
Zhiyuan Liang, Dongwen Tang, Yuhao Zhou, Xuanlei Zhao, Mingjia Shi, Wangbo Zhao, Zekai Li, Peihao Wang, Konstantin Schürholt, Damian Borth, Michael M. Bronstein, Yang You, Zhangyang Wang, Kai Wang
2025 J jnl
E-3SFC: Communication-Efficient Federated Learning With Double-Way Features Synthesizing.
IEEE Trans. Neural Networks Learn. Syst.
Yuhao Zhou, Yuxin Tian, Mingjia Shi, Yuanxi Li, Yanan Sun, Qing Ye, Jiancheng Lv
2025 J jnl
E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing.
CoRR
Yuhao Zhou, Yuxin Tian, Mingjia Shi, Yuanxi Li, Yanan Sun, Qing Ye, Jiancheng Lv
2025 B conf
FedSH: Tackling Staleness By Scheduling High-order Approximation in Asynchronous Federated Learning.
IJCNN
Haixin Gao, Mingjia Shi, Yuhao Zhou, Deng Xiong, Qing Ye, Jiancheng Lv
2025 A* conf
Ferret: An Efficient Online Continual Learning Framework under Varying Memory Constraints.
CVPR
Yuhao Zhou, Yuxin Tian, Jindi Lv, Mingjia Shi, Yuanxi Li, Qing Ye, Shuhao Zhang, Jiancheng Lv
2025 J jnl
Ferret: An Efficient Online Continual Learning Framework under Varying Memory Constraints.
CoRR
Yuhao Zhou, Yuxin Tian, Jindi Lv, Mingjia Shi, Yuanxi Li, Qing Ye, Shuhao Zhang, Jiancheng Lv
2025 — conf
GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning.
ACL (Findings)
Sifan Zhou, Shuo Wang, Zhihang Yuan, Mingjia Shi, Yuzhang Shang, Dawei Yang
2025 J jnl
GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning.
CoRR
Sifan Zhou, Shuo Wang, Zhihang Yuan, Mingjia Shi, Yuzhang Shang, Dawei Yang
2025 J jnl
Make Optimization Once and for All with Fine-grained Guidance.
CoRR
Mingjia Shi, Ruihan Lin, Xuxi Chen, Yuhao Zhou, Zezhen Ding, Pingzhi Li, Tong Wang, Kai Wang, Zhangyang Wang, Jiheng Zhang, Tianlong Chen
2025 J jnl
Mano Report.
CoRR
Tianyu Fu, Anyang Su, Chenxu Zhao, Hanning Wang, Minghui Wu, Zhe Yu, Fei Hu, Mingjia Shi, Wei Dong, Jiayao Wang, Yuyang Chen, Ruiyang Yu, Siran Peng, Menglin Li, Nan Huang, Haitian Wei, Jiawei Yu, Yi Xin, Xilin Zhao, Kai Gu, Ping Jiang, Sifan Zhou, Shuo Wang
2025 J jnl
REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training.
CoRR
Ziqiao Wang, Wangbo Zhao, Yuhao Zhou, Zekai Li, Zhiyuan Liang, Mingjia Shi, Xuanlei Zhao, Pengfei Zhou, Kaipeng Zhang, Zhangyang Wang, Kai Wang, Yang You
2025 B conf
Towards Frame Rate Insensitive Video Object Segmentation.
IJCNN
Weitu Chong, Kaer Huang, Mingjia Shi, Jian Li, Hui Yang, Dan Zhang
2024 J jnl
A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training.
CoRR
Kai Wang, Yukun Zhou, Mingjia Shi, Zhihang Yuan, Yuzhang Shang, Xiaojiang Peng, Hanwang Zhang, Yang You
2024 J jnl
Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training.
CoRR
Mingjia Shi, Yuhao Zhou, Ruiji Yu, Zekai Li, Zhiyuan Liang, Xuanlei Zhao, Xiaojiang Peng, Tanmay Rajpurohit, Shanmukha Ramakrishna Vedantam, Wangbo Zhao, Kai Wang, Yang You
2024 J jnl
Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformation.
CoRR
Xinghao Wu, Jianwei Niu, Xuefeng Liu, Mingjia Shi, Guogang Zhu, Shaojie Tang
2023 A* conf
Communication-efficient Federated Learning with Single-Step Synthetic Features Compressor for Faster Convergence.
ICCV
Yuhao Zhou, Mingjia Shi, Yuanxi Li, Yanan Sun, Qing Ye, Jiancheng Lv
2023 J jnl
Communication-efficient Federated Learning with Single-Step Synthetic Features Compressor for Faster Convergence.
CoRR
Yuhao Zhou, Mingjia Shi, Qing Ye, Yanan Sun, Jiancheng Lv
2023 J jnl
DLB: A Dynamic Load Balance Strategy for Distributed Training of Deep Neural Networks.
IEEE Trans. Emerg. Top. Comput. Intell.
Qing Ye, Yuhao Zhou, Mingjia Shi, Yanan Sun, Jiancheng Lv
2023 A* conf
PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learning.
NeurIPS
Mingjia Shi, Yuhao Zhou, Kai Wang, Huaizheng Zhang, Shudong Huang, Qing Ye, Jiancheng Lv
2023 J jnl
PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learning.
CoRR
Mingjia Shi, Yuhao Zhou, Kai Wang, Huaizheng Zhang, Shudong Huang, Qing Ye, Jiangcheng Lv
2023 — conf
Unconstrained Feature Model and Its General Geometric Patterns in Federated Learning: Local Subspace Minority Collapse.
ICONIP (8)
Mingjia Shi, Yuhao Zhou, Qing Ye, Jiancheng Lv
2022 J jnl
Correction to: FLSGD: free local SGD with parallel synchronization.
J. Supercomput.
Qing Ye, Yuhao Zhou, Mingjia Shi, Jiancheng Lv
2022 J jnl
FLSGD: free local SGD with parallel synchronization.
J. Supercomput.
Qing Ye, Yuhao Zhou, Mingjia Shi, Jiancheng Lv
2022 J jnl
Personalized Federated Learning with Hidden Information on Personalized Prior.
CoRR
Mingjia Shi, Yuhao Zhou, Qing Ye, Jiancheng Lv
2020 J jnl
DBS: Dynamic Batch Size For Distributed Deep Neural Network Training.
CoRR
Qing Ye, Yuhao Zhou, Mingjia Shi, Yanan Sun, Jiancheng Lv