Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.16039 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908600511758336 |
|---|---|
| author | Peng, Xiangyuan Dong, Xingsi Wu, Si |
| author_facet | Peng, Xiangyuan Dong, Xingsi Wu, Si |
| contents | We propose Grid-like Code Quantization (GCQ), a brain-inspired method for compressing observation-action sequences into discrete representations using grid-like patterns in attractor dynamics. Unlike conventional vector quantization approaches that operate on static inputs, GCQ performs spatiotemporal compression through an action-conditioned codebook, where codewords are derived from continuous attractor neural networks and dynamically selected based on actions. This enables GCQ to jointly compress space and time, serving as a unified world model. The resulting representation supports long-horizon prediction, goal-directed planning, and inverse modeling. Experiments across diverse tasks demonstrate GCQ's effectiveness in compact encoding and downstream performance. Our work offers both a computational tool for efficient sequence modeling and a theoretical perspective on the formation of grid-like codes in neural systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_16039 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Vector Quantization in the Brain: Grid-like Codes in World Models Peng, Xiangyuan Dong, Xingsi Wu, Si Machine Learning Artificial Intelligence We propose Grid-like Code Quantization (GCQ), a brain-inspired method for compressing observation-action sequences into discrete representations using grid-like patterns in attractor dynamics. Unlike conventional vector quantization approaches that operate on static inputs, GCQ performs spatiotemporal compression through an action-conditioned codebook, where codewords are derived from continuous attractor neural networks and dynamically selected based on actions. This enables GCQ to jointly compress space and time, serving as a unified world model. The resulting representation supports long-horizon prediction, goal-directed planning, and inverse modeling. Experiments across diverse tasks demonstrate GCQ's effectiveness in compact encoding and downstream performance. Our work offers both a computational tool for efficient sequence modeling and a theoretical perspective on the formation of grid-like codes in neural systems. |
| title | Vector Quantization in the Brain: Grid-like Codes in World Models |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2510.16039 |