The Dual Mechanisms of Spatial Reasoning in Vision-Language Models

• URL: http://arxiv.org/abs/2603.22278v1
• Date: Mon, 23 Mar 2026 17:58:02 GMT
• Title: The Dual Mechanisms of Spatial Reasoning in Vision-Language Models
• Abstract summary: multimodal tasks require vision-language models (VLMs) to associate objects with their properties and spatial relations.<n>We show that VLMs rely on two concurrent mechanisms to represent such associations.<n>We show that enhancing vision-derived spatial representations globally across all image tokens improves spatial reasoning performance on naturalistic images.
• Score: 38.440901436153716
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Many multimodal tasks, such as image captioning and visual question answering, require vision-language models (VLMs) to associate objects with their properties and spatial relations. Yet it remains unclear where and how such associations are computed within VLMs. In this work, we show that VLMs rely on two concurrent mechanisms to represent such associations. In the language model backbone, intermediate layers represent content-independent spatial relations on top of visual tokens corresponding to objects. However, this mechanism plays only a secondary role in shaping model predictions. Instead, the dominant source of spatial information originates in the vision encoder, whose representations encode the layout of objects and are directly exploited by the language model backbone. Notably, this spatial signal is distributed globally across visual tokens, extending beyond object regions into surrounding background areas. We show that enhancing these vision-derived spatial representations globally across all image tokens improves spatial reasoning performance on naturalistic images. Together, our results clarify how spatial association is computed within VLMs and highlight the central role of vision encoders in enabling spatial reasoning.

Related papers

• OmniGF: A Dual-Branch Vision-Language Framework for Unified Gaze Following [59.53720386342017]
  We propose a unified vision-language framework that adapts foundational Vision-Language Models for scalable multi-person gaze reasoning.<n>By modeling all individuals, OmniGF seamlessly integrates precise spatial gaze target estimation, semantic gaze prediction, and complex social gaze reasoning.
  arXiv  Detail & Related papers  (2026-05-26T00:08:06Z)
• GeoWorld-VLM: Geometry from World Models for Vision-Language Models [10.86505613923278]
  Modern Vision-Language Models (VLMs) achieve strong semantic recognition, yet remain brittle on elementary spatial relations.<n>We introduce GeoWorld-VLM, a VLM-side distillation framework that transfers geometric structure from frozen video world models intoVLMs.<n>GeoWorld-VLM fine-tunes only the image encoder and multimodal projector, aligning post-projector image features with intermediate world-model representations while leaving the main backbone frozen.
  arXiv  Detail & Related papers  (2026-05-15T23:52:11Z)
• TagaVLM: Topology-Aware Global Action Reasoning for Vision-Language Navigation [70.23578202012048]
  Vision-Language Navigation (VLN) presents a unique challenge for Large Vision-Language Models (VLMs) due to their inherent architectural mismatch.<n>We propose TagaVLM (Topology-Aware Global Action reasoning), an end-to-end framework that explicitly injects topological structures into the VLM backbone.<n>To enhance topological node information, an Interleaved Navigation Prompt strengthens node-level visual-text alignment.<n>With the embedded topological graph, the model is capable of global action reasoning, allowing for robust path correction.
  arXiv  Detail & Related papers  (2026-03-03T13:28:07Z)
• Thinking with Blueprints: Assisting Vision-Language Models in Spatial Reasoning via Structured Object Representation [52.605647992080485]
  spatial reasoning advances vision-language models from visual perception toward semantic understanding.<n>We integrate the cognitive concept of an object-centric blueprint into spatial reasoning.<n>Our method consistently outperforms existing vision-language models.
  arXiv  Detail & Related papers  (2026-01-05T10:38:26Z)
• Attention Guided Alignment in Efficient Vision-Language Models [56.20286899428444]
  Large Vision-Language Models (VLMs) rely on effective multimodal alignment between pre-trained vision encoders and Large Language Models (LLMs)<n>This paper presents a comprehensive analysis of attention patterns in efficient VLMs.<n>We introduce Attention-Guided Efficient Vision-Language Models (AGE-VLM), a novel framework that enhances visual grounding through interleaved cross-attention layers.
  arXiv  Detail & Related papers  (2025-11-21T21:36:48Z)
• Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception [71.26728044621458]
  DeCLIP is a novel framework that enhances CLIP by decoupling the self-attention module to obtain content'' and context'' features respectively.<n>It consistently achieves state-of-the-art performance across a broad spectrum of tasks, including 2D detection and segmentation, 3D instance segmentation, video instance segmentation, and 6D object pose estimation.
  arXiv  Detail & Related papers  (2025-08-15T06:43:51Z)
• Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models [14.442394137843923]
  We present a detailed analysis that first delineates the core elements of spatial reasoning.<n>We then assesses the performance of these models in both synthetic and real-world images.
  arXiv  Detail & Related papers  (2025-03-25T14:34:06Z)
• Scale-wise Bidirectional Alignment Network for Referring Remote Sensing Image Segmentation [12.893224628061516]
  The goal of referring remote sensing image segmentation (RRSIS) is to extract specific pixel-level regions within an aerial image via a natural language expression.<n>We propose an innovative framework called Scale-wise Bidirectional Alignment Network (SBANet) to address these challenges.<n>Our proposed method achieves superior performance in comparison to previous state-of-the-art methods on the RRSIS-D and RefSegRS datasets.
  arXiv  Detail & Related papers  (2025-01-01T14:24:04Z)
• REVISION: Rendering Tools Enable Spatial Fidelity in Vision-Language Models [67.55362046790512]
  Vision-language models lack the ability to correctly reason over spatial relationships. We develop the REVISION framework which improves spatial fidelity in vision-language models. Our results and findings indicate that utilizing rendering-based frameworks is an effective approach for developing spatially-aware models.
  arXiv  Detail & Related papers  (2024-08-05T04:51:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.