Mingjia Shi
5 papers · 2023–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🗺️
Taxonomy Completionist
(14)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Machine Learning
(5)
Application Areas
(4)
Artificial Intelligence
(3)
Deep Learning
(3)
Optimization & Theory · Machine Learning
(3)
Learning Paradigms · Artificial Intelligence
(2)
Learning Paradigms · Machine Learning
(2)
Learning Types · Deep Learning
(2)
Optimization & Theory · Deep Learning
(2)
Core AI
(1)
Learning Types · Machine Learning
(1)
Models
(1)
Keywords
federated learning
(2)
model quantization
(1)
sampling strategy
(1)
privacy preservation
(1)
neural network optimization
(1)
training optimization
(1)
bregman divergence
(1)
real-time learning
(1)
mirror descent
(1)
communication efficiency
(1)
convergence rate
(1)
gradient compression
(1)
memory efficiency
(1)
personalized model
(1)
client heterogeneity
(1)
pipeline parallelism
(1)
edge computing
(1)
model acceleration
(1)
online continual learning
(1)
error feedback
(1)
Papers
A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training
CVPR 2025
Ferret: An Efficient Online Continual Learning Framework under Varying Memory Constraints
CVPR 2025
GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning
ACL 2025
Communication-efficient Federated Learning with Single-Step Synthetic Features Compressor for Faster Convergence
ICCV 2023
PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learning.
NeurIPS 2023