paper-with-me

Papers

Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguities

2024-10-22 · Zheyuan Zhang, Fengyuan Hu, Jayjun Lee, Freda Shi, Parisa Kordjamshidi, Joyce Chai, Ziqiao Ma

Spatial expressions in situated communication can be ambiguous, as their meanings vary depending on the frames of reference (FoR) adopted by speakers and listeners. While spatial language understanding and reasoning by vision-language models (VLMs) have gained increasing attention, potential ambiguities in these models are still under-explored. To address this issue, we present the COnsistent Multilingual Frame Of Reference Test (COMFORT), an evaluation protocol to systematically assess the spatial reasoning capabilities of VLMs. We evaluate nine state-of-the-art VLMs using COMFORT. Despite showing some alignment with English conventions in resolving ambiguities, our experiments reveal significant shortcomings of VLMs: notably, the models (1) exhibit poor robustness and consistency, (2) lack the flexibility to accommodate multiple FoRs, and (3) fail to adhere to language-specific or culture-specific conventions in cross-lingual tests, as English tends to dominate other languages. With a growing effort to align vision-language models with human cognitive intuitions, we call for more attention to the ambiguous nature and cross-cultural diversity of spatial reasoning.

📄 PDF Abstract BibTeX arXiv:2410.17385

Code (1)

sled-group/COMFORT 공식 구현 pytorch

Tasks

Spatial Reasoning

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Textual Supervision Enhances Geospatial Representations in Vision-Language Models

2026-06-05 · Marcelo Sartori Locatelli, Fernando Tonucci, Jea Kwon, Luiz Felipe Vecchietti 외 arxiv

Geospatial understanding is a critical yet underexplored dimension in the development of machine learning systems for tasks such as image geolocation and spatial reasoning. In this work, we analyze the geospatial represe…

Spatial Reasoning

EmbodimentSemantic: A Spatial Scene-Graph Dataset and Benchmark for Vision-Language Models on Embodied Manipulation Trajectories

2026-06-06 · Hassan Jaber, Refinath S N, Luca Cagliero, Christopher E. Mower 외 arxiv

Spatial grounding remains a key limitation of vision-language-action (VLA) systems for robotic manipulation. While current models can recognize objects and follow language instructions, they often lack an explicit repres…

Thinking in Structures: Evaluating Spatial Intelligence in Constraint-Governed Spaces

2026-02-08 · Chen Yang, Guanxin Lin, Youquan He, Peiyao Chen 외 arxiv

Spatial intelligence is crucial for vision--language models (VLMs), yet many scene-centric benchmarks evaluate unconstrained environments where a single image may admit multiple plausible 3D interpretations. We introduce…

Spatial Reasoning

AI's Spatial Intelligence: Evaluating AI's Understanding of Spatial Transformations in PSVT:R and Augmented Reality

2024-11-09 · Uttamasha Monjoree, Wei Yan

Spatial intelligence is important in Architecture, Construction, Science, Technology, Engineering, and Mathematics (STEM), and Medicine. Understanding three-dimensional (3D) spatial rotations can involve verbal descripti…

Spatial Reasoning

SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models

2024-06-03 · An-Chieh Cheng, Hongxu Yin, Yang Fu, Qiushan Guo 외

Vision Language Models (VLMs) have demonstrated remarkable performance in 2D vision and language tasks. However, their ability to reason about spatial arrangements remains limited. In this work, we introduce Spatial Regi…

Language ModellingSpatial Reasoning