We work on developing artificially intelligent systems
that are able to reason about the visual world. Our research brings together the fields of
computer vision,
machine learning,
human-computer interaction,
cognitive science, as well as
fairness, accountability, and
transparency.
We are interested in a diverse range of topics, including building computer vision systems, understanding the
underlying learning paradigms, studying how computer vision systems can effectively collaborate with humans,
and ensuring the fairness of the vision systems with respect to people of all backgrounds by
improving dataset design, algorithmic methodology, measurement metrics and model interpretability.
RECENT TIMELINE
-
-
Sunnie S. Y. Kim, Jennifer Wortman Vaughan, Q. Vera Liao, Tania Lombrozo, Olga Russakovsky
-
arXiv 2025Xindi Wu*, Hee Seung Hwang*, Polina Kirichenko, et al. (* = equal contribution)
-
Salma Abdel Magid
-
ACM Conference on Human Factors in Computing Systems 2025 , Extended Abstract TrackAllison Chen, Sunnie S. Y. Kim, Amaya Dharmasiri, et al. To additionally appear in the Proceedings of CogSci 2025
-
CVPR 2025Yongqi Yang, Zhihao Qian, Ye Zhu, et al.
-
"Interactivity x Explainability: Toward Understanding How Interactivity Can Improve Computer Vision Explanations" accepted.ACM Conference on Human Factors in Computing Systems 2025 , Extended Abstract TrackIndu Panigrahi, Sunnie S. Y. Kim*, Amna Liaqat*, et al. (* = equal contribution)
-
Computer Vision and Pattern Recognition 2025Aaron Serianni, Tyler Zhu, Olga Russakovsky, et al.
-
-
ICML 2025Jihoon Chung*, Tyler Zhu*, Max Gonzalez Saez-Diez, et al.
-
CHI 2025Sunnie S. Y. Kim, Jennifer Wortman Vaughan, Q. Vera Liao, et al.
-
arXiv 2024Xindi Wu, Mengzhou Xia, Rulin Shao, et al.
-
Patterns 2024Angelina Wang, Aaron Hertzmann, Olga Russakovsky
-
Sunnie S. Y. Kim
-
-
Best Paper Award at ECCV workshopXindi Wu, Byron Zhang, Zhiwei Deng, Olga Russakovsky
-
Princeton SEAS Award for ExcellenceJihoon Chung
-
Sunnie S. Y. Kim
-
NeurIPS 2024 , Datasets and Benchmarks TrackXindi Wu*, Dingli Yu*, Yangsibo Huang*, et al.
-
TMLR 2024Xindi Wu, Byron Zhang, Zhiwei Deng, et al.
ACKNOWLEDGEMENTS
We are very grateful to the National Science Foundation, Amazon, Adobe, Open Philanthropy, Meta, Princeton School of Engineering and Applied Sciences, Princeton Alliance for Collaborative Research and Innovation, Princeton Language and Intelligence Initiative and Princeton Precision Health Initiative (current/ongoing) as well as to KAUST, Samsung, Google, Microsoft, Cisco and Princeton Center for Statistics and Machine Learning (past) for generous support of our research.