activity
20242026
collaborators

5 papers

cs.RO2026

BIT-Nav: Brain-Inspired Trajectory Memory for Embodied Navigation

Rithvik Jonna, Aakash Gurram, Man Namgung +2

Vision-Language Models (VLMs) for embodied navigation rely on selecting a fixed number of frames from a growing trajectory history. As episodes extend, this selection grows increas…

q-bio.NC2026

Spectral-Stimulus Information for Self-Supervised Stimulus Encoding

Jared Deighton, Wyatt Mackey, Ioannis Schizas +2

Mammalian spatial navigation relies on specialized neurons, such as place and grid cells, which encode position based on self-motion and environmental cues. While extensive researc…

cs.LG2026

HiCL: Hippocampal-Inspired Continual Learning

Kushal Kapoor, Wyatt Mackey, Yiannis Aloimonos +1

We propose HiCL, a novel hippocampal-inspired dual-memory continual learning architecture designed to mitigate catastrophic forgetting by using elements inspired by the hippocampal…

cs.RO2025

EDEN: Entorhinal Driven Egocentric Navigation Toward Robotic Deployment

Mikolaj Walczak, Romina Aalishah, Wyatt Mackey +5

Deep reinforcement learning agents are often fragile while humans remain adaptive and flexible to varying scenarios. To bridge this gap, we present EDEN, a biologically inspired na…

cs.LG2024

Geometric sparsification in recurrent neural networks

Wyatt Mackey, Ioannis Schizas, Jared Deighton +2

A common technique for ameliorating the computational costs of running large neural models is sparsification, or the pruning of neural connections during training. Sparse models ar…