SOURCE-LINKED INTELLIGENCE

Where Should Experience Live? Hierarchical Hebbian Memory for Continual Vision Transformers

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Vision Transformers provide strong visual representations but typically rely on slowly updated parameters, limiting their ability to organize newly acquired information across different memory timescales. This work proposes \textit{Hierarchical Hebbian Memory}, a three-level memory architecture composed of rapid Working Memory, persistent Routed Episodic Memory, and slower Semantic Memory. A learned controller regulates memory contribution, read and write routing, plasticity, retention, and consolidation. A causal read-before-write lifecycle ensures that the current outcome cannot influence th

Read original source ↗ Open in workspace

recordType

paper

region

Global