Wenxuan Wang

Affiliations

The Chinese University of Hong Kong

papers

949

total citations

papers (16)

Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards

NEURIPS 2025arXiv

citations

Med-DANet: Dynamic Architecture Network for Efficient Medical Volumetric Segmentation

ECCV 2022arXiv

citations

SeCap: Self-Calibrating and Adaptive Prompts for Cross-view Person Re-Identification in Aerial-Ground Networks

CVPR 2025arXiv

citations

Improving the Transferability of Adversarial Attacks on Face Recognition with Diverse Parameters Augmentation

CVPR 2025arXiv

citations

LipsNet++: Unifying Filter and Controller into a Policy Network

ICML 2025

citations

Unveiling Parts Beyond Objects: Towards Finer-Granularity Referring Expression Segmentation

CVPR 2024

citations

FM2u-Net: Face Morphological Multi-Branch Network for Makeup-Invariant Face Verification

CVPR 2020

citations

Off-policy Reinforcement Learning with Model-based Exploration Augmentation

NEURIPS 2025arXiv

citations

Wenxuan Wang

Affiliations

papers (16)

GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

Improving Adversarial Transferability via Neuron Attribution-Based Attacks

Boosting Adversarial Transferability by Block Shuffle and Rotation

Delving into Data: Effectively Substitute Training for Black-box Attack

Improving the Transferability of Adversarial Samples by Path-Augmented Method

Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding

DST: Dynamic Substitute Training for Data-Free Black-Box Attack

EVEv2: Improved Baselines for Encoder-Free Vision-Language Models

Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards

Med-DANet: Dynamic Architecture Network for Efficient Medical Volumetric Segmentation

SeCap: Self-Calibrating and Adaptive Prompts for Cross-view Person Re-Identification in Aerial-Ground Networks

Improving the Transferability of Adversarial Attacks on Face Recognition with Diverse Parameters Augmentation

LipsNet++: Unifying Filter and Controller into a Policy Network

Unveiling Parts Beyond Objects: Towards Finer-Granularity Referring Expression Segmentation

FM2u-Net: Face Morphological Multi-Branch Network for Makeup-Invariant Face Verification

Off-policy Reinforcement Learning with Model-based Exploration Augmentation

papers (16)

GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

Improving Adversarial Transferability via Neuron Attribution-Based Attacks

Boosting Adversarial Transferability by Block Shuffle and Rotation

Delving into Data: Effectively Substitute Training for Black-box Attack

Improving the Transferability of Adversarial Samples by Path-Augmented Method

Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding

DST: Dynamic Substitute Training for Data-Free Black-Box Attack

EVEv2: Improved Baselines for Encoder-Free Vision-Language Models

Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards

Med-DANet: Dynamic Architecture Network for Efficient Medical Volumetric Segmentation

SeCap: Self-Calibrating and Adaptive Prompts for Cross-view Person Re-Identification in Aerial-Ground Networks

Improving the Transferability of Adversarial Attacks on Face Recognition with Diverse Parameters Augmentation

LipsNet++: Unifying Filter and Controller into a Policy Network

Unveiling Parts Beyond Objects: Towards Finer-Granularity Referring Expression Segmentation

FM2u-Net: Face Morphological Multi-Branch Network for Makeup-Invariant Face Verification

Off-policy Reinforcement Learning with Model-based Exploration Augmentation