Saved in:
Bibliographic Details
Main Authors: Zhang, Tianqiu, Lyu, Muyang, Liu, Xiao, Wu, Si
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.15733
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918503420788736
author Zhang, Tianqiu
Lyu, Muyang
Liu, Xiao
Wu, Si
author_facet Zhang, Tianqiu
Lyu, Muyang
Liu, Xiao
Wu, Si
contents Humans abstract experiences into structured representations to facilitate pattern inference and knowledge transfer. While the hippocampal-entorhinal (HPC-MEC) circuit is known to represent both spatial and conceptual spaces, the mechanisms for concurrently extracting abstract structures from continuous, high-dimensional dynamics remain poorly understood. We propose a brain-inspired hierarchical model that simultaneously infers latent transitions and constructs a predictive visual world model. Our architecture employs an inverse model for structural extraction alongside an HPC-MEC coupling model that dissociates relational structures (MEC) from integrated episodic scenes (HPC). Using primitive transformation dynamics as a benchmark, we demonstrate the model's capacity for structural abstraction. By leveraging velocity-driven path integration, the framework enables robust prediction and structural reuse across diverse contexts, thereby achieving structural generalization. This work provides a novel computational framework for understanding how brain-inspired, self-supervised learning of world models facilitates the acquisition of reusable abstract knowledge.
format Preprint
id arxiv_https___arxiv_org_abs_2605_15733
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Structure Abstraction and Generalization in a Hippocampal-Entorhinal Inspired World Model
Zhang, Tianqiu
Lyu, Muyang
Liu, Xiao
Wu, Si
Neural and Evolutionary Computing
Artificial Intelligence
Computer Vision and Pattern Recognition
Humans abstract experiences into structured representations to facilitate pattern inference and knowledge transfer. While the hippocampal-entorhinal (HPC-MEC) circuit is known to represent both spatial and conceptual spaces, the mechanisms for concurrently extracting abstract structures from continuous, high-dimensional dynamics remain poorly understood. We propose a brain-inspired hierarchical model that simultaneously infers latent transitions and constructs a predictive visual world model. Our architecture employs an inverse model for structural extraction alongside an HPC-MEC coupling model that dissociates relational structures (MEC) from integrated episodic scenes (HPC). Using primitive transformation dynamics as a benchmark, we demonstrate the model's capacity for structural abstraction. By leveraging velocity-driven path integration, the framework enables robust prediction and structural reuse across diverse contexts, thereby achieving structural generalization. This work provides a novel computational framework for understanding how brain-inspired, self-supervised learning of world models facilitates the acquisition of reusable abstract knowledge.
title Structure Abstraction and Generalization in a Hippocampal-Entorhinal Inspired World Model
topic Neural and Evolutionary Computing
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.15733