Hossein Adeli

This study shows that lateral recurrence in neural networks enhances identity separability in trained domains through dynamic refinement of representational geometry.

This study investigates how superior colliculus neurons integrate target guidance and behavioral history signals during visual search, finding evidence for mixed, dynamic, and pure selectivity patterns.

The paper uses time-series PID to compare integration models in SC neurons during visual search, finding diverse integration strategies.

This paper introduces a model that uses object reconstruction to improve object recognition by integrating top-down attention, achieving better performance and aligning with human behavior on noisy datasets.

This paper uses a transformer model to predict human brain activity from images, achieving a challenge score of 63.5229 and demonstrating the effectiveness of self-supervised transformer features.

The paper shows that saccadic eye movements during reading are guided by midbrain visuo-motor principles rather than cognitive processes.