Mingjia Shi

DD-Ranking: Rethinking the Evaluation of Dataset Distillation

CMQuant: A Quantization-Aware Parameter-Efficient Fine-Tuning Framework for 4-Bit Consistency Models

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

QuantGen: Parameter Generation for Controllable Model Quantization

Make Optimization Once and for All with Fine-grained Guidance

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

Pruning-Robust Mamba with Asymmetric Multi-Scale Scanning Paths

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

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

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

From Mismatch to Harmony: Resolving Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformation