Where Bits Matter in World Model Planning: A Paired Mixed-Bit Study for Efficient Spatial Reasoning

TL;DR

This paper investigates how the allocation of limited bits in world models affects spatial reasoning, revealing that strategic bit distribution across modules enhances planning efficiency under tight precision constraints.

Contribution

It introduces a paired mixed-bit evaluation method demonstrating the importance of module-aware quantization for efficient spatial reasoning in world models.

Findings

8-bit and 6-bit settings perform close to FP16.

3-bit settings cause collapse in performance.

Allocation-sensitive 4-bit settings improve planning.

Abstract

Efficient spatial reasoning requires world models that remain reliable under tight precision budgets. We study whether low-bit planning behavior is determined mostly by total bitwidth or by where bits are allocated across modules. Using DINO-WM on the Wall planning task, we run a paired-goal mixed-bit evaluation across uniform, mixed, asymmetric, and layerwise variants under two planner budgets. We observe a consistent three-regime pattern: 8-bit and 6-bit settings remain close to FP16, 3-bit settings collapse, and 4-bit settings are allocation-sensitive. In that transition region, preserving encoder precision improves planning relative to uniform quantization, and near-size asymmetric variants show the same encoder-side direction. In a later strict 22-cell replication with smaller per-cell episode count, the mixed-versus-uniform INT4 sign becomes budget-conditioned, which further highlights the sensitivity of this transition regime. These findings motivate module-aware, budget-aware quantization policies as a broader research direction for efficient spatial reasoning. Code and run artifacts are available at https://github.com/suraj-ranganath/DINO-MBQuant.