Xiaolei Liu
9 papers · 2020–2026 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π£ Hot Topic Early Bird π§ Keyword Pioneer π Conference Polyglot (5) π Academic Marathon (5) π Cross-Pollinator (6)
π
Renaissance Researcher
(5)
πΊοΈ
Taxonomy Completionist
(23)
π
Interdisciplinary Bridge
π
Keyword Champion
(2)
Conferences
AAAI (5)
ICCV (1)
IJCAI (1)
NIPS (1)
UAI (1)
Top co-authors
Keywords
second-order optimization
(3)
neural network training
(3)
fisher information matrix
(3)
natural gradient descent
(2)
adversarial attack
(2)
neural network optimization
(2)
knowledge distillation
(1)
self-supervised learning
(1)
representation learning
(1)
layer-wise learning rate
(1)
natural gradient
(1)
adaptive learning rate
(1)
kronecker product
(1)
black-box attack
(1)
backdoor attack
(1)
automatic speech recognition
(1)
stochastic gradient descent
(1)
deep neural network
(1)
transformer architecture
(1)
federated learning
(1)
Papers
DoBlock: Blocking Malicious Association Propagation for Backdoor-Robust Federated Learning Under Domain Skew
AAAI 2026
LoopLLM: Transferable Energy-Latency Attacks in LLMs via Repetitive Generation
AAAI 2026
KOEnsAttack: Towards Efficient Data-Free Black-Box Adversarial Attacks via Knowledge-Orthogonalized Substitute Ensembles
ICCV 2025
i$^2$VAE: Interest Information Augmentation with Variational Regularizers for Cross-Domain Sequential Recommendation
UAI 2025
A Layer-Wise Natural Gradient Optimizer for Training Deep Neural Networks
NIPS 2024
An Embarrassingly Simple Approach to Enhance Transformer Performance in Genomic Selection for Crop Breeding
IJCAI 2024
THOR, Trace-based Hardware-driven Layer-Oriented Natural Gradient Descent Computation
AAAI 2021
A Trace-restricted Kronecker-Factored Approximation to Natural Gradient
AAAI 2021
Weighted-Sampling Audio Adversarial Example Attack
AAAI 2020