Cihang Xie

Cihang Xie is an Assistant Professor of Computer Science and Engineering at the University of California, Santa Cruz, where he conducts cutting-edge research at the intersection of computer vision and machine learning. He co-leads the Vision · Learning · Assured Autonomy (VLAA) Lab with Professor Yuyin Zhou, focusing on building human-level computer vision systems with robust performance under distribution shifts and developing deep representation learning with minimal supervision.

Dr. Xie received his Ph.D. from Johns Hopkins University under the supervision of Bloomberg Distinguished Professor Alan Yuille. During his doctoral studies, he gained valuable industry experience as a research intern at Facebook AI Research (FAIR) working with Kaiming He and Laurens van der Maaten, and at Google Brain with Quoc Le.

His research spans multiple critical areas including adversarial machine learning, vision-language models, 3D vision, and robust AI systems. Dr. Xie's work often bridges theoretical foundations with practical applications, particularly in developing methods that maintain performance under challenging conditions such as distribution shifts and adversarial attacks. His recent focus has expanded to include large language model safety evaluation, high-quality image editing datasets, and efficient transformer architectures.

Dr. Xie's publication record demonstrates consistent output across top-tier computer vision and machine learning venues including CVPR, ICCV, ECCV, NeurIPS, and ICML. His work shows a clear progression from foundational research in adversarial robustness to more recent explorations in vision-language alignment, 3D representation learning, and efficient model architectures.

Awards and Recognition

• 2020 Facebook Fellowship

Dr. Xie has advised numerous Ph.D. students at UC Santa Cruz and maintains collaborations with students from Johns Hopkins University and other institutions. His service to the academic community includes serving as Area Chair for major conferences including CVPR (2024/2023), ICLR (2024/2023/2022), ICML (2024/2023), ICCV (2023/2021), and NeurIPS (2024/2023/2022), as well as Senior Program Committee for AAAI 2022 and IJCAI 2021.

The VLAA Lab, which Dr. Xie co-leads, has multiple openings for summer interns and visiting students, indicating active growth and research momentum. Recent lab achievements include releasing Recap-DataComp-1B, HQ-Edit dataset, and D-iGPT with impressive ImageNet performance.