Picture for Xingxing Wei

Xingxing Wei

Beijing Key Laboratory of Digital Media, School of Computer Science and Engineering, Beihang University, Beijing, China

Rethinking Multi-modal Object Detection from the Perspective of Mono-Modality Feature Learning

Add code
Mar 14, 2025
Viaarxiv icon

When Lighting Deceives: Exposing Vision-Language Models' Illumination Vulnerability Through Illumination Transformation Attack

Add code
Mar 10, 2025
Viaarxiv icon

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency

Add code
Jan 09, 2025
Figure 1 for Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency
Figure 2 for Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency
Figure 3 for Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency
Figure 4 for Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency
Viaarxiv icon

AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?

Add code
Dec 04, 2024
Figure 1 for AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?
Figure 2 for AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?
Figure 3 for AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?
Figure 4 for AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?
Viaarxiv icon

OODFace: Benchmarking Robustness of Face Recognition under Common Corruptions and Appearance Variations

Add code
Dec 03, 2024
Figure 1 for OODFace: Benchmarking Robustness of Face Recognition under Common Corruptions and Appearance Variations
Figure 2 for OODFace: Benchmarking Robustness of Face Recognition under Common Corruptions and Appearance Variations
Figure 3 for OODFace: Benchmarking Robustness of Face Recognition under Common Corruptions and Appearance Variations
Figure 4 for OODFace: Benchmarking Robustness of Face Recognition under Common Corruptions and Appearance Variations
Viaarxiv icon

Real-world Adversarial Defense against Patch Attacks based on Diffusion Model

Add code
Sep 14, 2024
Viaarxiv icon

TASAR: Transferable Attack on Skeletal Action Recognition

Add code
Sep 04, 2024
Viaarxiv icon

Benchmarking Trustworthiness of Multimodal Large Language Models: A Comprehensive Study

Add code
Jun 11, 2024
Figure 1 for Benchmarking Trustworthiness of Multimodal Large Language Models: A Comprehensive Study
Figure 2 for Benchmarking Trustworthiness of Multimodal Large Language Models: A Comprehensive Study
Figure 3 for Benchmarking Trustworthiness of Multimodal Large Language Models: A Comprehensive Study
Figure 4 for Benchmarking Trustworthiness of Multimodal Large Language Models: A Comprehensive Study
Viaarxiv icon

The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition

Add code
May 14, 2024
Figure 1 for The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition
Figure 2 for The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition
Figure 3 for The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition
Figure 4 for The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition
Viaarxiv icon

UniRGB-IR: A Unified Framework for Visible-Infrared Downstream Tasks via Adapter Tuning

Add code
Apr 26, 2024
Figure 1 for UniRGB-IR: A Unified Framework for Visible-Infrared Downstream Tasks via Adapter Tuning
Figure 2 for UniRGB-IR: A Unified Framework for Visible-Infrared Downstream Tasks via Adapter Tuning
Figure 3 for UniRGB-IR: A Unified Framework for Visible-Infrared Downstream Tasks via Adapter Tuning
Figure 4 for UniRGB-IR: A Unified Framework for Visible-Infrared Downstream Tasks via Adapter Tuning
Viaarxiv icon