Mingjia Shi

5

Papers

38

Total Citations

Papers (5)

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

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

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

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

NeurIPS 2025arXiv

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