Deepti is an Assistant Professor in the Department of Computer Science in Boston University. Her research interests are in Computer Vision and Machine Learning, with a special focus improving the safety, interpretability, and robustness of machine learning systems. Previously she spent over an year as a researcher at Runway and over 5 years at Meta AI Research working on image and video understanding models, fair and inclusive computer vision models, and ML explainability. She obtained her PhD at the University of Texas at Austin in 2017 on perceptual image and video quality assessment for real-world content. She has served as a program chair for NeurIPS 2022 Dataset and Benchmarks track, AIMLsystems’23, and an area chair for several conferences such as IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Winter Conference on Applications of Computer Vision (WACV), Women in Machine Learning (WiML), and Association for the Advancement of Artificial Intelligence (AAAI). She organized several workshops on the topics of responsible and explainable computer vision at top-tier machine learning conferences.