Sanmi Koyejo

This paper improves genomic prediction accuracy by using synthetic traits derived from hyperspectral data, showing higher accuracy than single-trait models for leaf traits in sorghum.

This study examines how network structure and information content change during an artificial learning task, identifying three phases of network reconfiguration.

This paper uses a deep generative model to analyze brain structure variability across mouse brains and validates the model through structured perturbations.

The paper examines how neuromodulators shape a low-dimensional integrative core in the brain that supports diverse cognitive tasks through dynamic neural activity patterns.

MRIQC is a tool for predicting MRI image quality that generalizes across sites with 76% accuracy but struggles with site-specific artifacts.