Scholar

Shouwei Ruan (阮受炜)

Google Scholar ID: 1pggtuUAAAAJ

Institute of Artificial Intelligence, Beihang University

computer visionadversarial robustnessembodied intelligent

Citations & Impact

All-time

Citations

226

H-index

i10-index

Publications

Co-authors

list available

Contact

Publications

19 items

Browse publications on Google Scholar (top-right) ↗

Resume (English only)

Academic Achievements

Paper 'AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?' accepted by ICCV 2025
Paper 'When Lighting Deceives: Exposing Vision-Language Models' Illumination Vulnerability Through Illumination Transformation Attack' accepted by ICCV 2025
Paper 'Distributionally Location-Aware Transferable Adversarial Patches for Facial Images' accepted by IEEE TPAMI 2025
Paper 'Omniview-Tuning: Boosting Viewpoint Invariance of Vision-Language Pre-training Models' accepted by ECCV 2024 with Oral presentation
Awarded National Scholarship, Outstanding Graduate, and Innovation Model (Xidian University) in 2021

Background

4th-year Ph.D. student at the Institute of Artificial Intelligence, Beihang University (BUAA)
Member of ROSE Vision Lab, advised by Prof. Xingxing Wei (National-level Young Talent)
Currently a visiting student at TSAIL, Tsinghua University, jointly supervised by Prof. Hang Su and A/Prof. Yinpeng Dong
Research interests focus on vision-language models' applications and robustness in spatial perception (e.g., 3D relationships, viewpoint transformations)
Also interested in trustworthiness and security of Embodied AI systems and vision-language navigation tasks

Co-authors

9 total