activity
20242026
collaborators

9 papers

cs.CV2026

A Woman with a Knife or A Knife with a Woman? Measuring Directional Bias Amplification in Image Captions

Rahul Nair, Bhanu Tokas, Hannah Kerner

When we train models on biased datasets, they not only reproduce data biases, but can worsen them at test time - a phenomenon called bias amplification. Many of the current bias am…

cs.LG2025

Application-Driven Innovation in Machine Learning

David Rolnick, Alan Aspuru-Guzik, Sara Beery +8

In this position paper, we argue that application-driven research has been systemically under-valued in the machine learning community. As applications of machine learning prolifer…

cs.CV2025

OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observation

Henry Herzog, Favyen Bastani, Yawen Zhang +23

Earth observation data presents a unique challenge: it is spatial like images, sequential like video or text, and highly multimodal. We present OlmoEarth: a multimodal, spatio-temp…

cs.CV2025

DPA: A one-stop metric to measure bias amplification in classification datasets

Bhanu Tokas, Rahul Nair, Hannah Kerner

Most ML datasets today contain biases. When we train models on these datasets, they often not only learn these biases but can worsen them -- a phenomenon known as bias amplificatio…

cs.LG2025

Deploying Geospatial Foundation Models in the Real World: Lessons from WorldCereal

Christina Butsko, Kristof Van Tricht, Gabriel Tseng +6

The increasing availability of geospatial foundation models has the potential to transform remote sensing applications such as land cover classification, environmental monitoring,…

cs.CV2025

Galileo: Learning Global & Local Features of Many Remote Sensing Modalities

Gabriel Tseng, Anthony Fuller, Marlena Reil +7

We introduce a highly multimodal transformer to represent many remote sensing modalities - multispectral optical, synthetic aperture radar, elevation, weather, pseudo-labels, and m…