Andrew Luo

Our approach improves Vision Transformer Dense Representations via Self-Distillation

We meta-learn a transformer based in-context learning fMRI visual cortex encoder which can adapt to new human subjects without any fine-tuning

We built a transformer-based model to predict brain activity across the whole brain from visual input, then use this model to label the categoriacal selectivity of areas beyond the visual cortex to better understand higher-order visual processing.