paper-with-me

Papers

GSR-BENCH: A Benchmark for Grounded Spatial Reasoning Evaluation via Multimodal LLMs

2024-06-19 · Navid Rajabi, Jana Kosecka

The ability to understand and reason about spatial relationships between objects in images is an important component of visual reasoning. This skill rests on the ability to recognize and localize objects of interest and determine their spatial relation. Early vision and language models (VLMs) have been shown to struggle to recognize spatial relations. We extend the previously released What'sUp dataset and propose a novel comprehensive evaluation for spatial relationship understanding that highlights the strengths and weaknesses of 27 different models. In addition to the VLMs evaluated in What'sUp, our extensive evaluation encompasses 3 classes of Multimodal LLMs (MLLMs) that vary in their parameter sizes (ranging from 7B to 110B), training/instruction-tuning methods, and visual resolution to benchmark their performances and scrutinize the scaling laws in this task.

📄 PDF Abstract BibTeX arXiv:2406.13246

Code (0)

등록된 구현이 없습니다.

Tasks

Spatial ReasoningVisual Reasoning

Similar Papers 제목 키워드 기반

Lost in Volume: The CT-SpatialVQA Benchmark for Evaluating Semantic-Spatial Understanding of 3D Medical Vision-Language Models

2026-05-09 · Mashrafi Monon, Umaima Rahman, Asif Hanif, Numan Saeed 외 arxiv

Recent advances in 3D medical vision-language models have enabled joint reasoning over volumetric images and text, showing strong performance in medical visual question-answering (VQA) and report generation. Despite this…

Relational ReasoningSpatial Reasoning

Spatially Grounded Long-Horizon Task Planning in the Wild

2026-03-13 · Sehun Jung, HyunJee Song, Dong-Hee Kim, Reuben Tan 외 arxiv

Recent advances in robot manipulation increasingly leverage Vision-Language Models (VLMs) for high-level reasoning, such as decomposing task instructions into sequential action plans expressed in natural language that gu…

Robot Manipulation

From Indoor to Open World: Revealing the Spatial Reasoning Gap in MLLMs

2025-12-22 · Mingrui Wu, Zhaozhi Wang, Fangjinhua Wang, Jiaolong Yang 외 arxiv

While Multimodal Large Language Models (MLLMs) have achieved impressive performance on semantic tasks, their spatial intelligence--crucial for robust and grounded AI systems--remains underdeveloped. Existing benchmarks f…

Relational ReasoningSpatial ReasoningVisual Reasoning

Reframing Spatial Reasoning Evaluation in Language Models: A Real-World Simulation Benchmark for Qualitative Reasoning

2024-05-23 · Fangjun Li, David C. Hogg, Anthony G. Cohn

Spatial reasoning plays a vital role in both human cognition and machine intelligence, prompting new research into language models' (LMs) capabilities in this regard. However, existing benchmarks reveal shortcomings in e…

Logical Reasoning Question AnsweringSpatial ReasoningVisual Question Answering

Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology

2025-07-10 · Haochen Wang, Xiangtai Li, Zilong Huang, Anran Wang 외 arxiv

Models like OpenAI-o3 pioneer visual grounded reasoning by dynamically referencing visual regions, just like human "thinking with images". However, no benchmark exists to evaluate these capabilities holistically. To brid…

Reinforcement LearningObject Localization