Xintao Wu
Affiliation confirmed via AI analysis of OpenAlex, ORCID, and web sources.
Professor
Also affiliated: University of North Carolina at Charlotte (2002–2014); University of Vermont (2015–2016); New Jersey Institute of Technology (2017); North Carolina State University (2005); Baylor University (2026); Chongqing University (2021); George Mason University (1999–2001); Hefei University of Technology (2015); University of Oregon (2019); University of Arkansas System (2017); Charlotte School of Law (2012); East China Normal University (2025); Beijing University of Chemical Technology (2023–2024); Zhejiang University (2024–2025); Shanghai Maritime University (2024)
Research Areas
Biomedical Subjects
Biography and Research Information
OverviewAI-generated summary
Xintao Wu's research focuses on developing and applying advanced computational methods, particularly in machine learning and artificial intelligence, to address complex problems in areas such as data privacy, fairness in algorithms, and threat detection. His work has led to the development of techniques like LogBERT for log anomaly detection and FairGAN for fairness-aware generative adversarial networks. Wu also investigates methods for preserving differential privacy in deep learning models, such as the Adaptive Laplace Mechanism, and explores causal frameworks to identify and mitigate discrimination within data.
He has received significant federal funding from the National Science Foundation (NSF) for his work on counterfactually fair machine learning through causal modeling and towards fair regression under sample selection bias. With a substantial publication record of 357 papers and an h-index of 41, Wu is recognized as a highly cited researcher. His collaborations include numerous shared publications with researchers at the University of Arkansas at Fayetteville, such as Minh-Hao Van, Alycia N. Carey, Aneesh Komanduri, and Prateek Verma. Wu leads an active research group and maintains a lab website to disseminate his work.
Metrics
- h-index: 41
- Publications: 376
- Citations: 6,361
Positions
-
Professor 2023–presentUniversity of Arkansas Department of Electrical Engineering and Computer Science ORCID
Selected Publications
-
A Framework for Automated Tracking of Morphologically Distinct Cell Populations in Time-Lapse Microscopy (2026)
-
StraightDP: Geometry-Aware Differential Privacy for Rectified-Flow Transformers (2026)arXiv (Cornell University) OpenAlex
-
StraightDP: Geometry-Aware Differential Privacy for Rectified-Flow Transformers (2026)
-
MIITA: Memory-Induced Inference-Time Adaptation for Continual Learning with Small Language Models (2026)arXiv (Cornell University) OpenAlex
-
Coupled Hierarchical Search over Topology and Execution for Agentic Workflow Synthesis (2026)arXiv (Cornell University) OpenAlex
-
Coupled Hierarchical Search over Topology and Execution for Agentic Workflow Synthesis (2026)
-
SAFE-Cascade: Cost-Adaptive Vision-Language Routing for Chart Question Answering (2026)arXiv (Cornell University) OpenAlex
-
Property Prediction of Stacked Bilayer Materials: A Multimodal Learning Approach (2026)arXiv (Cornell University) OpenAlex
-
Leveraging Foundation Models for Causal Generative Modeling (2026)
-
Leveraging Foundation Models for Causal Generative Modeling (2026)
-
How Does Differential Privacy Affect Social Bias in LLMs? A Systematic Evaluation (2026)
-
How Does Differential Privacy Affect Social Bias in LLMs? A Systematic Evaluation (2026)
-
Vision language models for scientific image analysis: an evaluation highlighting opportunities and challenges (2026)
-
Class-Domain Incremental Learning on Graphs via Disentangled Knowledge Distillation (2026)
-
LLM-Enhanced Energy Contrastive Learning for Out-of-Distribution Detection in Text-Attributed Graphs (2026)arXiv (Cornell University) OpenAlex
Federal Grants 2 $634,828 total
III:Small: Counterfactually Fair Machine Learning through Causal Modeling
Collaboration Network
Top Collaborators
- LogBERT: Log Anomaly Detection via BERT
- FairGAN: Fairness-aware Generative Adversarial Networks
- Deep learning for insider threat detection: Review, challenges and opportunities
- One-Class Adversarial Nets for Fraud Detection
- SNE: Signed Network Embedding
Showing 5 of 33 shared publications
- FairGAN: Fairness-aware Generative Adversarial Networks
- A Causal Framework for Discovering and Removing Direct and Indirect Discrimination
- Achieving Causal Fairness through Generative Adversarial Networks
- Counterfactual Fairness: Unidentification, Bound and Algorithm
- Achieving Non-Discrimination in Data Release
Showing 5 of 23 shared publications
- A Causal Framework for Discovering and Removing Direct and Indirect Discrimination
- Achieving Causal Fairness through Generative Adversarial Networks
- Counterfactual Fairness: Unidentification, Bound and Algorithm
- Achieving Non-Discrimination in Data Release
- Causal Modeling-Based Discrimination Discovery and Removal: Criteria, Bounds, and Algorithms
Showing 5 of 22 shared publications
- FairGAN: Fairness-aware Generative Adversarial Networks
- Fairness-aware Agnostic Federated Learning
- Achieving Causal Fairness through Generative Adversarial Networks
- Achieving Differential Privacy and Fairness in Logistic Regression
- DPNE: Differentially Private Network Embedding
Showing 5 of 14 shared publications
- One-Class Adversarial Nets for Fraud Detection
- Spectrum-based Deep Neural Networks for Fraud Detection
- Poisoning Attacks on Fair Machine Learning
- Analysis of Spectral Space Properties of Directed Graphs Using Matrix Perturbation Theory with Application in Graph Partition
- On spectral analysis of directed signed graphs
Showing 5 of 11 shared publications
- On Large Visual Language Models for Medical Imaging Analysis: An Empirical Study
- Poisoning Attacks on Fair Machine Learning
- Beyond Human Vision: The Role of Large Vision Language Models in Microscope Image Analysis
- Soft Prompting for Unlearning in Large Language Models
- A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools
Showing 5 of 10 shared publications
- One-Class Adversarial Nets for Fraud Detection
- Insider Threat Detection via Hierarchical Neural Temporal Point Processes
- SAFE: A Neural Survival Analysis Model for Fraud Early Detection
- Few-shot Insider Threat Detection
- Wikipedia Vandal Early Detection: From User Behavior to User Embedding
Showing 5 of 8 shared publications
- Fairness-aware Agnostic Federated Learning
- PC-Fairness: A Unified Framework for Measuring Causality-based Fairness
- Few-shot Insider Threat Detection
- InfoFair: Information-Theoretic Intersectional Fairness
- Attent: Active Attributed Network Alignment
Showing 5 of 8 shared publications
- Analysis of Spectral Space Properties of Directed Graphs Using Matrix Perturbation Theory with Application in Graph Partition
- On spectral analysis of directed signed graphs
- On Spectral Analysis of Signed and Dispute Graphs
- On Spectral Analysis of Signed and Dispute Graphs: Application to Community Structure
- Dynamic Anomaly Detection Using Vector Autoregressive Model
Showing 5 of 6 shared publications
- Fairness-aware Agnostic Federated Learning
- Removing Disparate Impact on Model Accuracy in Differentially Private Stochastic Gradient Descent
- Fair and Robust Classification Under Sample Selection Bias
- Robust Personalized Federated Learning under Demographic Fairness Heterogeneity
- Fairness-aware Agnostic Federated Learning
Showing 5 of 6 shared publications
- Achieving Counterfactual Fairness for Causal Bandit
- Achieving User-Side Fairness in Contextual Bandits
- SCM-VAE: Learning Identifiable Causal Representations via Structural Knowledge
- Fairness-aware Bandit-based Recommendation
- Transferable Contextual Bandits with Prior Observations
Showing 5 of 6 shared publications
- Using Randomized Response for Differential Privacy Preserving Data Collection
- oGBAC—A Group Based Access Control Framework for Information Sharing in Online Social Networks
- On digital image trustworthiness
- A Framework of Privacy Decision Recommendation for Image Sharing in Online Social Networks
- Security and privacy protocols for perceptual image hashing
- Differential Privacy Preservation for Deep Auto-Encoders: an Application of Human Behavior Prediction
- Adaptive Laplace Mechanism: Differential Privacy Preservation in Deep Learning
- Preserving differential privacy in convolutional deep belief networks
- Heterogeneous Gaussian Mechanism: Preserving Differential Privacy in Deep Learning with Provable Robustness
- Heterogeneous Randomized Response for Differential Privacy in Graph Neural Networks
- Adaptive Fairness-Aware Online Meta-Learning for Changing Environments
- Towards Fair Disentangled Online Learning for Changing Environments
- Algorithmic Fairness Generalization under Covariate and Dependence Shifts Simultaneously
- Dynamic Environment Responsive Online Meta-Learning with Fairness Awareness
- Class-Domain Incremental Learning on Graphs via Disentangled Knowledge Distillation
- A Two Phase Deep Learning Model for Identifying Discrimination from Tweets
- Incorporating pre-training in long short-term memory networks for tweet classification
- Wikipedia Vandal Early Detection: From User Behavior to User Embedding
- Task-specific word identification from short texts using a convolutional neural network1
Similar Researchers
Based on overlapping research topics