Grounding Isn't Knowing: Do VLMs Need Object Localization for Spatial Reasoning?

• URL: http://arxiv.org/abs/2608.23074v1
• Date: Mon, 24 Aug 2026 10:26:15 GMT
• Title: Grounding Isn't Knowing: Do VLMs Need Object Localization for Spatial Reasoning?
• Abstract summary: Vision-language models (VLMs) can answer spatial questions, yet the mechanisms connecting object grounding to spatial reasoning remain poorly understood.<n>In this work, we investigate two representative model families, LLaVA-1.5 and Qwen2.5-VL, using a suite of mechanistic interpretability tools.<n>We find that spatial relation prediction follows a staged grounding-to-reasoning process in which object-aligned tokens establish coarse target-reference anchors, while precise bounding-box boundaries are not required.
• Score: 24.02857259963021
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-language models (VLMs) can answer spatial questions, yet the mechanisms connecting object grounding to spatial reasoning remain poorly understood. It is underexplored whether spatial reasoning internally requires precise objects localization, or can bypass explicit localization through global layout cues. In this work, we investigate two representative model families, LLaVA-1.5 and Qwen2.5-VL, using a suite of mechanistic interpretability tools, including token ablation, layer-wise probing, attention knockout, and causal mediation analysis. We find that spatial relation prediction follows a staged grounding-to-reasoning process in which object-aligned tokens establish coarse target-reference anchors, while precise bounding-box boundaries are not required. Positional information becomes decodable before relation decisions emerge, and a small set of attention heads mediates the causal effects of both localization and spatial reasoning. The two tasks share early grounding-related processing but ultimately rely on partially distinct specialized pathways. Through rigorous experiments, we provide a token-, layer-, and head-level account of how VLMs transform object grounding into spatial relations, showing that knowing where objects are is not equivalent to knowing how they relate.

Related papers

• S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence [77.5121349100339]
  textscS-Agent reshapes spatial perception into scene-centric understanding beyond frame-centric recognition.<n>textscS-Agent casts the VLM as a semantic planner that decides what evidence is needed.<n>textscS-Agent consistently improves both open-source and closed-source VLMs in a training-free manner.
  arXiv  Detail & Related papers  (2026-06-18T17:34:55Z)
• Mechanisms of Object Localization in Vision-Language Models [10.367669666212473]
  We study the processes that support object localization in visually-grounded language models (VLMs)<n>We find that localization is driven by a containerization mechanism in which object-aligned tokens define the spatial extent of the object.<n>Only a very small set of attention heads mediates the causal effect for both classification and localization.
  arXiv  Detail & Related papers  (2026-05-19T12:56:32Z)
• 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)
• Spatial Reasoning in Foundation Models: Benchmarking Object-Centric Spatial Understanding [8.202861909913791]
  We present a benchmark for object-centric spatial reasoning in foundation models.<n>We find a stable trade-off: detectors such as GroundingDINO and OWLv2 deliver precise boxes with limited relational reasoning.<n>Our study highlights the gap between localization and true spatial understanding, and pointing toward the need for spatially-aware foundation models in the community.
  arXiv  Detail & Related papers  (2025-09-26T06:06:19Z)
• FloorplanQA: A Benchmark for Spatial Reasoning in LLMs using Structured Representations [78.65988445433844]
  FloorplanQA is a diagnostic benchmark for evaluating spatial reasoning in large-language models.<n>The benchmark covers core spatial tasks, including distance measurement, visibility, path finding, and object placement within constrained spaces.
  arXiv  Detail & Related papers  (2025-07-10T11:16:48Z)
• Can LLMs Learn to Map the World from Local Descriptions? [50.490593949836146]
  This study investigates whether Large Language Models (LLMs) can construct coherent global spatial cognition.<n> Experiments conducted in a simulated urban environment demonstrate that LLMs exhibit latent representations aligned with real-world spatial distributions.
  arXiv  Detail & Related papers  (2025-05-27T08:22:58Z)
• 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)
• Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas [69.56484419619919]
  We study the spatial reasoning challenge from the lens of mechanistic interpretability.<n>We observe that successful spatial reasoning correlates strongly with the model's ability to align its attention with actual object locations.<n>Motivated by these findings, we propose ADAPTVIS to sharpen the attention on highly relevant regions when confident.
  arXiv  Detail & Related papers  (2025-03-03T17:57:03Z)
• Weakly Supervised Relative Spatial Reasoning for Visual Question Answering [38.05223339919346]
  We evaluate the faithfulness of V&L models to such geometric understanding. We train V&L with weak supervision from off-the-shelf depth estimators. This leads to considerable improvements in accuracy for the "GQA" visual question answering challenge.
  arXiv  Detail & Related papers  (2021-09-04T21:29:06Z)
• SIRI: Spatial Relation Induced Network For Spatial Description Resolution [64.38872296406211]
  We propose a novel relationship induced (SIRI) network for language-guided localization. We show that our method is around 24% better than the state-of-the-art method in terms of accuracy, measured by an 80-pixel radius. Our method also generalizes well on our proposed extended dataset collected using the same settings as Touchdown.
  arXiv  Detail & Related papers  (2020-10-27T14:04:05Z)

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.