Yilin Chen

This study shows that concurrent uncertainty during decision-making is represented in the parietal cortex but not computed within the same circuit as perceptual evidence accumulation.

SLAE learns all-atom protein representations from local atomic neighborhoods, achieving state-of-the-art performance in downstream tasks through transfer learning.

Protpardelle-1c is a protein structure generative model that improves motif scaffolding and multi-chain complex generation, achieving higher scores and faster sampling than existing models.

The paper assesses clustering of missense variants in neurodevelopmental disorders and cancer, identifying proteins with significant variation patterns in each condition.

The paper develops an optimal policy model to study how uncertainty is estimated concurrently with decision making, showing that uncertainty responses are influenced by motion coherence and individual variations.