Anwar O. Núñez-Elizalde

This study shows optimizing language model embeddings for individual brain voxels improves prediction accuracy of brain activity during reading.

This paper fine-tunes language models with bilingual brain data to improve multilingual understanding, showing better performance in brain encoding and NLP tasks across multiple languages.

This paper introduces banded ridge regression for feature-space selection in brain recordings, improving prediction accuracy and interpretability by adapting regularization per feature space.

This study shows that functional ultrasound signals correlate with neural firing rates in awake mice, revealing a direct relationship between hemodynamic signals and neuronal activity.

This paper introduces Tikhonov regression for fMRI data modeling, showing it can improve predictive models by using non-spherical Gaussian priors instead of spherical ridge regression.