collaborators

1 paper

cs.LG2025

VIBE: Video-Input Brain Encoder for fMRI Response Modeling

Daniel Carlström Schad, Shrey Dixit, Janis Keck +3

We present VIBE, a two-stage Transformer that fuses multi-modal video, audio, and text features to predict fMRI activity. Representations from open-source models (Qwen2.5, BEATs, W…