Mingjia Shi
Orcid: 0000-0002-9988-3741
According to our database1,
Mingjia Shi
authored at least 24 papers
between 2020 and 2025.
Collaborative distances:
Collaborative distances:
Timeline
Legend:
Book In proceedings Article PhD thesis Dataset OtherLinks
On csauthors.net:
Bibliography
2025
E-3SFC: Communication-Efficient Federated Learning With Double-Way Features Synthesizing.
IEEE Trans. Neural Networks Learn. Syst., August, 2025
REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training.
CoRR, May, 2025
FedSH: Tackling Staleness By Scheduling High-order Approximation in Asynchronous Federated Learning.
Proceedings of the International Joint Conference on Neural Networks, 2025
Proceedings of the International Joint Conference on Neural Networks, 2025
Ferret: An Efficient Online Continual Learning Framework under Varying Memory Constraints.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025
A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025
GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning.
Proceedings of the Findings of the Association for Computational Linguistics, 2025
2024
Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformation.
CoRR, 2024
A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training.
CoRR, 2024
2023
DLB: A Dynamic Load Balance Strategy for Distributed Training of Deep Neural Networks.
IEEE Trans. Emerg. Top. Comput. Intell., August, 2023
PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learning.
CoRR, 2023
Communication-efficient Federated Learning with Single-Step Synthetic Features Compressor for Faster Convergence.
CoRR, 2023
PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learning.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023
Unconstrained Feature Model and Its General Geometric Patterns in Federated Learning: Local Subspace Minority Collapse.
Proceedings of the Neural Information Processing - 30th International Conference, 2023
Communication-efficient Federated Learning with Single-Step Synthetic Features Compressor for Faster Convergence.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023
2022
J. Supercomput., 2022
CoRR, 2022
2020