Xiaowei Huang

Affiliations

University of Liverpool

papers

404

total citations

papers (17)

Spatial Uncertainty-Aware Semi-Supervised Crowd Counting

ICCV 2021arXiv

102

citations

SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model

CVPR 2025arXiv

citations

GNS: Solving Plane Geometry Problems by Neural-Symbolic Reasoning with Multi-Modal LLMs

AAAI 2025

citations

FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model

NEURIPS 2025arXiv

citations

Training Verification-Friendly Neural Networks via Neuron Behavior Consistency

AAAI 2025arXiv

citations

Position: Building Guardrails for Large Language Models Requires Systematic Design

ICML 2024

citations

A Black-Box Evaluation Framework for Semantic Robustness in Bird’s Eye View Detection

AAAI 2025arXiv

citations

Adversarial Label Poisoning Attack on Graph Neural Networks via Label Propagation

ECCV 2022

citations

Adversarial Training for Probabilistic Robustness

ICCV 2025

citations

Towards Better Robustness Against Natural Corruptions in Document Tampering Localization

AAAI 2025

citations

How does Weight Correlation Affect Generalisation Ability of Deep Neural Networks?

NEURIPS 2020

citations

Xiaowei Huang

Affiliations

papers (17)

Spatial Uncertainty-Aware Semi-Supervised Crowd Counting

SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model

Enhancing Adversarial Training With Second-Order Statistics of Weights

Randomized Adversarial Training via Taylor Expansion

SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretability

MathAttack: Attacking Large Language Models towards Math Solving Ability

Regression of Instance Boundary by Aggregated CNN and GCN

Towards Fairness-Aware Adversarial Learning

GNS: Solving Plane Geometry Problems by Neural-Symbolic Reasoning with Multi-Modal LLMs

FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model

Training Verification-Friendly Neural Networks via Neuron Behavior Consistency

Position: Building Guardrails for Large Language Models Requires Systematic Design

A Black-Box Evaluation Framework for Semantic Robustness in Bird’s Eye View Detection

Adversarial Label Poisoning Attack on Graph Neural Networks via Label Propagation

Adversarial Training for Probabilistic Robustness

Towards Better Robustness Against Natural Corruptions in Document Tampering Localization

How does Weight Correlation Affect Generalisation Ability of Deep Neural Networks?

papers (17)

Spatial Uncertainty-Aware Semi-Supervised Crowd Counting

SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model

Enhancing Adversarial Training With Second-Order Statistics of Weights

Randomized Adversarial Training via Taylor Expansion

SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretability

MathAttack: Attacking Large Language Models towards Math Solving Ability

Regression of Instance Boundary by Aggregated CNN and GCN

Towards Fairness-Aware Adversarial Learning

GNS: Solving Plane Geometry Problems by Neural-Symbolic Reasoning with Multi-Modal LLMs

FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model

Training Verification-Friendly Neural Networks via Neuron Behavior Consistency

Position: Building Guardrails for Large Language Models Requires Systematic Design

A Black-Box Evaluation Framework for Semantic Robustness in Bird’s Eye View Detection

Adversarial Label Poisoning Attack on Graph Neural Networks via Label Propagation

Adversarial Training for Probabilistic Robustness

Towards Better Robustness Against Natural Corruptions in Document Tampering Localization

How does Weight Correlation Affect Generalisation Ability of Deep Neural Networks?