collaborators

5 papers

cs.CV2026

Pretrain Where? Investigating How Pretraining Data Diversity Impacts Geospatial Foundation Model Performance

Amandeep Kaur, Mirali Purohit, Gedeon Muhawenayo +2

New geospatial foundation models introduce a new model architecture and pretraining dataset, often sampled using different notions of data diversity. Performance differences are la…

cs.CV2026

MOMO: Mars Orbital Model Foundation Model for Mars Orbital Applications

Mirali Purohit, Bimal Gajera, Irish Mehta +8

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…

cs.CV2025

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

Mirali Purohit, Bimal Gajera, Vatsal Malaviya +6

Foundation models have enabled rapid progress across many specialized domains by leveraging large-scale pre-training on unlabeled data, demonstrating strong generalization to a var…

cs.LG2025

How Does the Spatial Distribution of Pre-training Data Affect Geospatial Foundation Models?

Mirali Purohit, Gedeon Muhawenayo, Esther Rolf +1

Foundation models have made rapid advances in many domains including Earth observation, where Geospatial Foundation Models (GFMs) can help address global challenges such as climate…

cs.CL2024

Beyond Performance: Quantifying and Mitigating Label Bias in LLMs

Yuval Reif, Roy Schwartz

Large language models (LLMs) have shown remarkable adaptability to diverse tasks, by leveraging context prompts containing instructions, or minimal input-output examples. However,…