{"ID":2854463,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.16039","arxiv_id":"2510.16039","title":"Vector Quantization in the Brain: Grid-like Codes in World Models","abstract":"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.","short_abstract":"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 throu...","url_abs":"https://arxiv.org/abs/2510.16039","url_pdf":"https://arxiv.org/pdf/2510.16039v1","authors":"[\"Xiangyuan Peng\",\"Xingsi Dong\",\"Si Wu\"]","published":"2025-10-16T06:41:46Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[]","has_code":false}