Xiaojun Xu
12 papers · 2018–2025 · 6 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 ↓+4 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (32)
π§¬
Topic Evolution
π
Triple Crown
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(62)
Top co-authors
Research topics
Machine Learning
(11)
Artificial Intelligence
(9)
Core AI Β· Artificial Intelligence
(8)
Learning Types Β· Machine Learning
(6)
Application Areas
(5)
Optimization & Theory
(5)
Deep Learning
(4)
Learning Types Β· Deep Learning
(3)
Core Methods
(2)
Computer Science
(1)
Computer Vision
(1)
Reinforcement Learning
(1)
Applications
(1)
Architectures
(1)
Core AI Β· Computer Vision
(1)
Keywords
adversarial example
(3)
adversarial attack
(3)
adversarial robustness
(2)
large language model
(2)
certified robustness
(2)
query efficiency
(2)
model alignment
(2)
black-box attack
(2)
gradient estimation
(2)
ensemble learning
(1)
data augmentation
(1)
attention mechanism
(1)
multimodal learning
(1)
machine unlearning
(1)
domain generalization
(1)
semi-supervised learning
(1)
model robustness
(1)
reinforcement learning from human feedback
(1)
visual question answering
(1)
harmful content
(1)
Papers
BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning
ICML 2025
Robust Multi-bit Text Watermark with LLM-based Paraphrasers
ICML 2025
Toward Optimal LLM Alignments Using Two-Player Games
EMNLP 2025
Effective and Efficient Federated Tree Learning on Hybrid Data
ICLR 2024
Large Language Model Unlearning
NeurIPS 2024
Adversarially Robust Models may not Transfer Better: Sufficient Conditions for Domain Transferability from the View of Regularization
ICML 2022
LOT: Layer-wise Orthogonal Training on Improving l2 Certified Robustness
NeurIPS 2022
On the Certified Robustness for Ensemble Models and Beyond
ICLR 2022
Nonlinear Projection Based Gradient Estimation for Query Efficient Blackbox Attacks
AISTATS 2021
TRS: Transferability Reduced Ensemble via Promoting Gradient Diversity and Model Smoothness
NeurIPS 2021
QEBA: Query-Efficient Boundary-Based Blackbox Attack
CVPR 2020
Fooling Vision and Language Models Despite Localization and Attention Mechanism
CVPR 2018