Spatial Reasoning with Denoising Models

2025-02-28

AI Summary

Existing spatial generative models—such as diffusion models and flow matching—suffer from hallucination when modeling complex distributions, leading to distorted inference and mode collapse. To address this, we propose the Spatial Reasoning Model (SRM) framework, the first to adapt denoising-based generation for causal or constraint-driven reasoning over continuous variable sets, enabling high-fidelity continuous inference from observed to unobserved variables. Our key contributions are: (1) a learnable, adaptive generation-order prediction mechanism; (2) a continuous reasoning architecture explicitly designed for spatial constraints; and (3) the first benchmark suite quantifying generative hallucination in spatial reasoning. Experiments demonstrate that SRM boosts accuracy on targeted spatial reasoning tasks from <1% to >50%, substantially mitigates hallucination, and empirically validates both the learnability of generation order and its decisive impact on reasoning performance.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

We introduce Spatial Reasoning Models (SRMs), a framework to perform reasoning over sets of continuous variables via denoising generative models. SRMs infer continuous representations on a set of unobserved variables, given observations on observed variables. Current generative models on spatial domains, such as diffusion and flow matching models, often collapse to hallucination in case of complex distributions. To measure this, we introduce a set of benchmark tasks that test the quality of complex reasoning in generative models and can quantify hallucination. The SRM framework allows to report key findings about importance of sequentialization in generation, the associated order, as well as the sampling strategies during training. It demonstrates, for the first time, that order of generation can successfully be predicted by the denoising network itself. Using these findings, we can increase the accuracy of specific reasoning tasks from<1% to>50%.

Problem

• Introduces Spatial Reasoning Models for continuous variable reasoning.
• Addresses hallucination in generative models for complex distributions.
• Demonstrates improved reasoning accuracy via denoising network predictions.

Innovation

• SRMs use denoising models for spatial reasoning
• Benchmark tasks quantify generative model hallucination
• Denoising network predicts generation order accurately