Umaa Rebbapragada — accepted AI-conference papers

2026

MOMO: Mars Orbital MOdel Foundation Model for Mars Orbital Applications

Mirali Purohit, Bimal Gajera, Irish Mehta, Bhanu Tokas, Jacob Adler, Steven Lu +5

CVPR 2026

We introduce MOMO, the first multi-sensor foundation model for Mars remote sensing. MOMO uses model merge to integrate representations learned independently from three key Martian sensors (HiRISE, CTX, and THEMIS), spanning resolutions from 0.25 m/pixel to 100 m/pixel. Central to our method is our n

Cited by 0 Source ↗code ↗Scholar ↗

2025

Mars-Bench: A Benchmark for Evaluating Foundation Models for Mars Science Tasks

Mirali Purohit, Bimal Gajera, Vatsal Malaviya, Irish Mehta, Kunal Sunil Kasodekar, Jacob Adler +3

NeurIPS 2025poster

Foundation models have enabled rapid progress across many specialized domains by leveraging large-scale pre-training on unlabeled data, demonstrating strong generalization to a variety of downstream tasks. While such models have gained significant attention in fields like Earth Observation, their ap…

Cited by 0 Source ↗code ↗Scholar ↗