A single recurrent network trained on masked sensory prediction and motion develops co-emergent grid and place cells that qualitatively match multiple experimental observations without any spatial supervision.
Arslan Chaudhry, Marcus Rohrbach, Mohamed Elhoseiny, Thalaiyasingam Ajanthan, Puneet K
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
EVAF and test-retest protocol show selective parametric consolidation of high-valence experiences in GPT-2 and TinyLlama while preserving factual retrieval.
Hybrid ANN-CANN network for visual object tracking that operationalizes bias-variance complementarity to outperform baselines on nine benchmarks.
citing papers explorer
-
A simple model of co-emergence of grid and place fields
A single recurrent network trained on masked sensory prediction and motion develops co-emergent grid and place cells that qualitatively match multiple experimental observations without any spatial supervision.