ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Mingjia Shi

Mingjia Shi

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 1:13 AM AMS

7

papers

64

total citations

papers (7)

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

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

NEURIPS 2023arXiv

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

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

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

NEURIPS 2025arXiv

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

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

NEURIPS 2025arXiv