Mingjia Shi
5 papers · 2023–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot (4) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (16) π§ Keyword Pioneer π£ Hot Topic Early Bird
π
Cross-Pollinator
(15)
Conferences
CVPR (2)
ACL (1)
ICCV (1)
NIPS (1)
Top co-authors
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
GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning
ACL 2025
Ferret: An Efficient Online Continual Learning Framework under Varying Memory Constraints
CVPR 2025
A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training
CVPR 2025
PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learning.
NIPS 2023
Communication-efficient Federated Learning with Single-Step Synthetic Features Compressor for Faster Convergence
ICCV 2023