Laurent Itti

Cross-Modal Benchmarking of Acoustic Prosody and Ventral Striatal BOLD for Depression-Related Anhedonia Classification: A Pre-Registered Study with the ClinicalWhisper Pipeline

This paper benchmarks acoustic prosody and fMRI data for classifying depression-related anhedonia using pre-registered pipelines, finding comparable but modest performance in both modalities.

Interactions of encoding and decoding problems to understand motor control

This paper develops a deep learning-based encoding model to synthesize neural data from kinematics, improving decoding performance in brain-computer interfaces.