Wenxuan Wang

9

Papers

166

Total Citations

Papers (9)

Boosting Adversarial Transferability by Block Shuffle and Rotation

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

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

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

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

Off-policy Reinforcement Learning with Model-based Exploration Augmentation

NeurIPS 2025arXiv

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

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

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