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
-
"Robustness of Internal Signals for Hallucination Detection in Vision-Language Models" accepted.Neural Information Processing Systems 2026 , Evaluations & Datasets TrackAllison Chen, William Yang, Salma Abdel Magid, et al.
-
"D2D: Detector-to-Differentiable Critic for Improved Numeracy in Text-to-Image Generation" accepted.Neural Information Processing Systems 2026Nobline Yoo, Olga Russakovsky, Ye Zhu
-
Neural Information Processing Systems 2026Hee Seung Hwang*, Xindi Wu*, Sanghyuk Chun, et al. (* = equal contribution)
-
Neural Information Processing Systems 2026Sanghyuk Chun, William Yang, Amaya Dharmasiri, et al.
-
Neural Information Processing Systems 2026Xindi Wu, Sven Elflein, James Lucas, et al.
-
"In-Context Learning Can Help Vision Language Models Overcome Training Prior" accepted.Neural Information Processing Systems 2026Kun Wang, Xindi Wu, Sanghyuk Chun, et al.
-
" BodyBench: Evaluating Adversarial Image Defenses Against AI Nudification Inpainting" accepted.Neural Information Processing Systems 2026 , Evaluations & Datasets TrackQiwei Li*, Salma Abdel Magid*, Olga Russakovsky, et al. (* = equal contribution)
-
Xindi Wu, Olga Russakovsky
-
-
"Image Enhancement: A Necessity for Effective Underwater Object Detection?" accepted.Engineering Applications of Artificial Intelligence 2026Lujun Zhai, Ye Zhu, Olga Russakovsky, et al.
-
European Conference on Computer Vision 2026Max Gonzalez Saez-Diez*, Jihoon Chung*, Adam D. Wolsky, et al. (* = equal contribution)
-
Outstanding Reviewer AwardSanghyuk Chun
-
Trends in Cognitive Sciences 2026Huili Chen, Stephen R. Grimm, Olga Russakovsky, et al.
-
International Conference on Machine Learning 2026Xindi Wu, Despoina Paschalidou, Jun Gao, et al.
-
International Conference on Machine Learning 2026Ye Zhu, Kaleb S. Newman, Johannes F. Lutzeyer, et al.
-
International Conference on Machine Learning 2026Jonathan Williams, Esin Tureci, Olga Russakovsky
-
International Conference on Machine Learning 2026Sanghyuk Chun, Olga Russakovsky
-
Hee Seung Hwang, Xindi Wu, Sanghyuk Chun, Olga Russakovsky
-
arXiv 2026Kaleb Newman, Tyler Zhu, Olga Russakovsky
-
Computer Vision and Pattern Recognition 2026William Yang, Xindi Wu, Zhiwei Deng, et al.
-
Computer Vision and Pattern Recognition 2026Salma Abdel Magid, Grace Guo, Esin Tureci, et al.
-
International Conference on Learning Representations 2026Xindi Wu*, Hee Seung Hwang*, Polina Kirichenko, et al. (* = equal contribution)
-
International Conference on Learning Representations 2026Asher J. Hancock, Xindi Wu, Lihan Zha, et al.
-
ACM Conference on Human Factors in Computing Systems 2026Allison Chen, Sunnie S. Y. Kim, Angel Franyutti, et al.
-
arXiv 2025Ye Zhu, Yu Wu, Duo Xu, et al.
ACKNOWLEDGEMENTS
We are very grateful to the National Science Foundation, Solidigm, Amazon, Apple, Princeton Natural and Artificial Minds Initiative, Princeton Presidential Postdoctoral Fellowship, and Princeton School of Engineering and Applied Sciences (current/ongoing) as well as to Adobe, Cisco, Google, KAUST, Meta, Microsoft, Open Philanthropy, Samsung, Princeton Alliance for Collaborative Research and Innovation, Princeton Center for Statistics and Machine Learning, Princeton Language and Intelligence Initiative and Princeton Precision Health Initiative (past) for generous support of our research.