Challenge: Existing models assess spatial capabilities from a static, single-view and egocentric perspective, failing to capture the dynamic nature of real-world spatial cognition.
Approach: They propose a benchmark to diagnose spatial reasoning capabilities using a 360 field of view.
Outcome: The proposed benchmark evaluates allocentric and egocentric reasoning capabilities from multiple perspectives in high-quality 3D environments.

Similar Papers

An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models (2024.emnlp-main)

Copied to clipboard

Challenge: Large Multimodal Models (LMMs) have shown impressive generalization ability on vision and language tasks, but their spatial understanding is under-explored.
Approach: They construct a VQA dataset to analyze LMMs' spatial reasoning capabilities.
Outcome: The proposed model is stronger at basic object detection than complex spatial reasoning.
EmbSpatial-Bench: Benchmarking Spatial Understanding for Embodied Tasks with Large Vision-Language Models (2024.acl-short)

Copied to clipboard

Challenge: Recent studies have revealed significant deficiencies of LVLMs in understanding visual contents, leaving the gap between current embodied intelligence and large vision-language models (LVLM) .
Approach: They propose to use a benchmark to evaluate LVLMs' spatial understanding of embodied environments to evaluate their ability to understand visual contents.
Outcome: The proposed benchmark is derived from embodied scenes and covers 6 spatial relationships from an egocentric perspective.
CityCube: Benchmarking Cross-view Spatial Reasoning on Vision-Language Models in Urban Environments (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks focus on indoor or street settings, overlooking challenges of open-ended urban spaces.
Approach: They propose a benchmark to probe cross-view spatial reasoning capabilities of current VLMs in urban settings.
Outcome: The citycube benchmark examines the performance of current vision-language models in urban environments.
SpaRE: Enhancing Spatial Reasoning in Vision-Language Models with Synthetic Data (2025.acl-long)

Copied to clipboard

Challenge: Vision-language models struggle with spatial reasoning, a skill that humans excel at.
Approach: They propose to use a spatial-reasoning Enhanced (SpaRE) VLM to improve spatial reasoning in visual question answering and robotics.
Outcome: The proposed model achieves a 49% performance gain on the What's Up benchmark while maintaining strong results on general tasks.
Can Multimodal Large Language Models Understand Spatial Relations? (2025.acl-long)

Copied to clipboard

Challenge: Spatial relation reasoning is a crucial task for multimodal large language models to understand the objective world.
Approach: They propose a human-annotated spatial relation reasoning benchmark based on COCO2017 to improve MLLMs' spatial relation thinking.
Outcome: The proposed benchmark achieves 48.14% accuracy, far below the human-level accuracy of 98.40%.
TopViewRS: Vision-Language Models as Top-View Spatial Reasoners (2024.emnlp-main)

Copied to clipboard

Challenge: Top-view perspective is a typical way in which humans read and reason over different types of maps, but spatial reasoning capabilities of modern VLMs in this setup remain unattested and underexplored.
Approach: They introduce a top-view spatial reasoning dataset and use it to evaluate VLMs across 4 perception and reasoning tasks with different levels of complexity.
Outcome: The proposed model can understand and reason over spatial relations from the top view and can be controlled at different granularities of spatial reasoning.
Out of Sight, Not Out of Context? Egocentric Spatial Reasoning in VLMs Across Disjoint Frames (2025.emnlp-main)

Copied to clipboard

Challenge: Disjoint-3DQA evaluates the spatial reasoning ability of embodied AI assistants based on egocentric video . it aims to catalyze future research at the intersection of vision, language, and embodie .
Approach: They propose a generative QA benchmark that evaluates the ability of embodied AI assistants to integrate spatial cues across time by asking object pairs that are not co-visible in the same frame.
Outcome: The proposed benchmark compares seven state-of-the-art VLMs and finds that they lag behind human performance by 28%, with steeper declines as the temporal gap widens.
What’s “up” with vision-language models? Investigating their struggle with spatial reasoning (2023.emnlp-main)

Copied to clipboard

Challenge: Recent work has re-surfaced a concern that has long plagued vision-language models: poor performance on simple tasks like attribute attachment, counting, etc.
Approach: They evaluate 18 vision-language models and find they perform poorly on VQAv2 . they find that popular vision-linguistic pretraining corpora lack reliable data for learning spatial relationships .
Outcome: The new models are compared with existing datasets on what'sup and visual-language models . they achieve 56% accuracy on the new benchmarks compared to 99% for humans .
Defining and Evaluating Visual Language Models’ Basic Spatial Abilities: A Perspective from Psychometrics (2025.acl-long)

Copied to clipboard

Challenge: Existing studies assessing the spatial abilities of VLMs lack a solid theoretical foundation and lack measurable data.
Approach: They propose a psychometric framework defining five basic spatial abilities in Visual Language Models.
Outcome: The proposed framework defines five basic spatial abilities in Visual Language Models (VLMs) it provides a comprehensive evaluation benchmark and methodological perspective for embodied AI development .
Visual Spatial Reasoning (2023.tacl-1)

Copied to clipboard

Challenge: Existing benchmarks for testing vision-language models (VLMs) are not ideal as they conflate multiple sources of error and do not allow controlled analysis on specific linguistic or cognitive properties.
Approach: They present a dataset containing more than 10k natural text-image pairs with 66 types of spatial relations in English (e.g., under, in front of, facing).
Outcome: The proposed model fails to capture relational information in a visual question answering task and referring expression comprehension tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations