Utkarsh Mall
Assistant Professor of Computer Vision
Research Interests
Professor Mall's research lies in primarily in computer vision. He builds computer vision tools to enable automatic discovery from large-scale data. His research builds large-scale multimodal foundation models for domains with annotation/data constraints. His research also improves these foundation models making them more suitable for discovery, such as better interpretability or uncertainty estimates. In interdisciplinary collaboration with domain experts from climate scientists, crop scientists to fashion anthropologists, he also applies these methods to a diverse set of real-world scientific problems.
Prior to joining MBZUAI, Professor Mall was a postdoctoral research scientist in Computer Science at Columbia University, where he developed interpretable, reliable, and data-efficient methods to enable novel scientific discoveries from visual data. His work has been applied across diverse fields including agriculture, anthropology, archaeology, urban planning, public health, and climate science. He earned his PhD from Cornell University, focusing on building label-efficient foundation models for scientific domains and leveraging them for unsupervised discovery. Professor Mall also co-organizes the CVPR workshop Computer Vision for Science (CV4Science), and his doctoral research was recognized at the WACV 2022 and CVPR 2023 Doctoral Consortium.
- Postdoctoral Research Scientist, Columbia University
- Ph.D. in Computer Science from Cornell University
- Bachelor's in Computer Science and Engineering, Indian Institute of Technology
- Workshop organizer at CVPR 2025, Computer Vision for Science
- Workshop organizer at AGU 2024
- Selected for the Doctoral Consortium, CVPR 2023 and WACV 2022
- Outstanding Reviewer, CVPR 2021
- Program committee member for top-tier conferences like CVPR, ICCV, ECCV, NeurIPS, and ICLR
- DiSciPLE: Learning Interpretable Programs for Scientific Visual Discovery; Utkarsh Mall, Cheng Perng Phoo, Mia Chiquier, Bharath Hariharan, Kavita Bala, Carl Vondrick; CVPR 2025
- Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment; Utkarsh Mall, Cheng Perng Phoo, Meilin Kelsey Liu, Carl Vondrick, Bharath Hariharan, Kavita Bala; ICLR 2024
- How Video Meetings Change Your Expression; Sumit Sarin, Utkarsh Mall, Purva Tendulkar, Carl Vondrick; ECCV 2024
- Evolving Interpretable Visual Classifiers with Large Language Models; Mia Chiquier, Utkarsh Mall, Carl Vondrick; ECCV 2024
- Change-Aware Contrastive Learning for Satellite Images; Utkarsh Mall, Bharath Hariharan, Kavita Bala; CVPR 2023
- Change Event Dataset for Discovery from Spatio-temporal Remote Sensing Imagery; Utkarsh Mall, Bharath Hariharan, Kavita Bala; Neurips Datasets and Benchmarks Track (Featured) 2022
- Field-Guide-Inspired Zero-Shot Learning; Utkarsh Mall, Bharath Hariharan, Kavita Bala; ICCV 2021
- PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering; Jang Hyun Cho, Utkarsh Mall, Kavita Bala, Bharath Hariharan; CVPR 2021
- GeoStyle: Discovering Fashion Trends and Events; Utkarsh Mall, Kevin Matzen, Bharath Hariharan, Noah Snavely, Kavita Bala; ICCV 2019