REVIEW 21 cited by
Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models
read the original abstract
Vision-Language Models (VLMs) have recently emerged as powerful tools, excelling in tasks that integrate visual and textual comprehension, such as image captioning, visual question answering, and image-text retrieval. However, existing benchmarks for VLMs include spatial components, which often fail to isolate spatial reasoning from related tasks such as object detection or semantic comprehension. In this paper, we address these deficiencies with a multi-faceted approach towards understanding spatial reasoning. Informed by the diverse and multi-dimensional nature of human spatial reasoning abilities, we present a detailed analysis that first delineates the core elements of spatial reasoning: spatial relations, orientation and navigation, mental rotation, and spatial visualization, and then assesses the performance of these models in both synthetic and real-world images, bridging controlled and naturalistic contexts. We analyze 13 state-of-the-art Vision-Language Models, uncovering pivotal insights into their spatial reasoning performance. Our results reveal profound shortcomings in current VLMs, with average accuracy across the 13 models approximating random chance, highlighting spatial reasoning as a persistent obstacle. This work not only exposes the pressing need to advance spatial reasoning within VLMs but also establishes a solid platform for future exploration. Code available on GitHub (https://github.com/stogiannidis/srbench) and dataset available on HuggingFace (https://huggingface.co/datasets/stogiannidis/srbench).
Forward citations
Cited by 21 Pith papers
-
OmniCoT: A Benchmark for Global and Multi-Step Panoramic Reasoning
OmniCoT is a new panoramic reasoning benchmark with 6.7K eval, 1K real, and 14.3K training examples plus a two-stage SFT+GRPO training method to enforce global 360-degree consistency.
-
Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?
Frontier VLMs overconfidently answer spatial questions under occlusion (~30% accuracy) and perspective ambiguity (<10% accuracy) instead of abstaining, and often fail to select helpful additional views.
-
PhotoFlow: Agentic 3D Virtual Photography Missions
PhotoFlow is a closed-loop agent framework that searches for camera parameters in 3D scenes according to language intent and outperforms one-shot, reflection, and random baselines on the new VPhotoBench of 47 scenes a...
-
DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving
DriveSpatial benchmark shows the best of 15 VLMs trails humans by 28.4 points on spatiotemporal driving tasks, with cognitive scene construction as the main failure mode.
-
DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving
DriveSpatial benchmark shows the strongest of 15 VLMs trails humans by 28.4 points on spatiotemporal tasks, with cognitive scene construction as the primary weakness.
-
VisAnalog: A Diagnostic Suite for Visual Concept Transfer on Natural Images
VisAnalog is a new controlled benchmark showing VLMs substantially underperform humans on visual concept transfer under one- to four-step deterministic transformations, with relation inference as the main failure mode.
-
SpatialScore: Towards Comprehensive Evaluation for Spatial Intelligence
Presents SpatialScore benchmark for MLLM spatial reasoning, evaluates 49 models showing large human gap, and supplies SpatialCorpus plus SpatialAgent to improve performance.
-
AeroVerse-SatAgent: UAV-Satellite Collaborative Spatial Reasoning Inspired by the Dual Visual Pathway Theory of Cognitive Neuroscience
SatAgent is a UAV-satellite collaborative spatial reasoning model using geometric 3D encoding, multi-view alignment, and a new 130K dataset that reports 25.91% and 11.69% gains over general and specialized baselines.
-
The Art of Interrogation: Consistency Amplifies Factuality in Spatial Reasoning
A new consistency-verifier RL framework with OT-GRPO raises spatial reasoning accuracy in LRMs to near supervised levels using only internal geometric and semantic checks.
-
Readable Yet Unpredictable: Rotated-Outcome Prediction in Vision-Language Models
VLMs recognize rotated images when shown directly but fail to predict rotated outcomes from originals on the new RotOutBench benchmark.
-
Do Vision-Language Models Understand 3D Scenes or Just Catalogue Objects?
VLMs achieve 53-97% on rearrangement planning but only 6-45% on occlusion and under 7% on reflections, with failures localized to visual token compression after the vision encoder.
-
Do Vision-Language Models Understand 3D Scenes or Just Catalogue Objects?
VLMs achieve 53-97% on volumetric rearrangement planning but only 6-45% on occlusion and under 7% on reflections in a new 3,034-sample benchmark, with white-box analysis localizing the failure to visual-token merger i...
-
PanoWorld: Towards Spatial Supersensing in 360$^\circ$ Panorama World
PanoWorld adds spherical spatial cross-attention and pano-native training data to MLLMs for improved spatial reasoning on ERP panoramas, outperforming baselines on new and existing benchmarks.
-
PanoWorld: Towards Spatial Supersensing in 360$^\circ$ Panorama World
PanoWorld adds spherical geometry to MLLMs via cross-attention and pano-specific instruction data, yielding better performance on panoramic spatial reasoning benchmarks than standard perspective-based pipelines.
-
Do multimodal models imagine electric sheep?
Fine-tuning VLMs to output action sequences for puzzles causes emergent internal visual representations that improve performance when integrated into reasoning.
-
SpaceMind++: Toward Allocentric Cognitive Maps for Spatially Grounded Video MLLMs
SpaceMind++ adds an explicit voxelized allocentric cognitive map and coordinate-guided fusion to video MLLMs, claiming SOTA on VSI-Bench and improved out-of-distribution generalization on three other 3D benchmarks.
-
State Beyond Appearance: Diagnosing and Improving State Consistency in Dial-Based Measurement Reading
MLLMs ignore dial state geometry and cluster by appearance, causing inconsistency under variations; TriSCA's state-distance alignment, metadata supervision, and objective alignment improve robustness on clock and gaug...
-
SocialGrid: A Benchmark for Planning and Social Reasoning in Embodied Multi-Agent Systems
SocialGrid benchmark shows even top LLMs achieve below 60% in embodied planning and task completion, with deception detection near random chance regardless of model scale.
-
Agent-Aided Design for Dynamic CAD Models
AADvark extends agent-aided CAD design to dynamic 3D assemblies with movable parts by integrating constraint solvers and visual feedback to create a verification signal for the agent.
-
Do MLLMs Really Understand Space? A Mathematical Reasoning Evaluation
MLLMs show a large gap in spatial mathematical reasoning compared to humans, and a new 10,000-problem dataset helps narrow it through training.
-
Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models
A 235-item multimodal stress-test shows frontier closed models outpace open-weight peers by ~10% and leaves shared failures on counting, spatial, and character-level tasks.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.