Huaiyu Dai
11 papers · 2020–2025 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π§ Keyword Pioneer π Cross-Pollinator (12) πΊοΈ Taxonomy Completionist (17) π Interdisciplinary Bridge
π
Conference Polyglot
(8)
π
Academic Marathon
(5)
π
Grand Slam
π
Keyword Champion
(2)
π
Century Club
(11)
Conferences
ICML (3)
AAAI (2)
CVPR (1)
EMNLP (1)
ICCV (1)
ICLR (1)
IJCAI (1)
NIPS (1)
Top co-authors
Keywords
federated learning
(6)
adversarial example
(2)
statistical heterogeneity
(2)
distributed learning
(1)
model aggregation
(1)
query efficiency
(1)
model pruning
(1)
distributed training
(1)
communication efficiency
(1)
bayesian optimization
(1)
adversarial attack
(1)
black-box attack
(1)
adaptive optimization
(1)
communication compression
(1)
decision boundary
(1)
edge device
(1)
parameter-efficient tuning
(1)
edge computing
(1)
non-iid datum
(1)
prompt tuning
(1)
Papers
NTK-DFL: Enhancing Decentralized Federated Learning in Heterogeneous Settings via Neural Tangent Kernel
ICML 2025
GSBA$^K$: $top$-$K$ Geometric Score-based Black-box Attack
ICLR 2025
Noisy SIGNSGD Is More Differentially Private Than You (Might) Think
ICML 2025
FedASMU: Efficient Asynchronous Federated Learning with Dynamic Staleness-Aware Model Update
AAAI 2024
Breaking the Communication-Privacy-Accuracy Tradeoff with $f$-Differential Privacy
NIPS 2023
Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimization
EMNLP 2023
CGBA: Curvature-aware Geometric Black-box Attack
ICCV 2023
Neural Tangent Kernel Empowered Federated Learning
ICML 2022
Efficient Device Scheduling with Multi-Job Federated Learning
AAAI 2022
FedDUAP: Federated Learning with Dynamic Update and Adaptive Pruning Using Shared Data on the Server
IJCAI 2022
GeoDA: A Geometric Framework for Black-Box Adversarial Attacks
CVPR 2020