paper-with-me

Papers

Open3DVQA: A Benchmark for Comprehensive Spatial Reasoning with Multimodal Large Language Model in Open Space

2025-03-14 · Weichen Zhang, Zile Zhou, Zhiheng Zheng, Chen Gao, Jinqiang Cui, Yong Li, Xinlei Chen, Xiao-Ping Zhang

Spatial reasoning is a fundamental capability of embodied agents and has garnered widespread attention in the field of multimodal large language models (MLLMs). In this work, we propose a novel benchmark, Open3DVQA, to comprehensively evaluate the spatial reasoning capacities of current state-of-the-art (SOTA) foundation models in open 3D space. Open3DVQA consists of 9k VQA samples, collected using an efficient semi-automated tool in a high-fidelity urban simulator. We evaluate several SOTA MLLMs across various aspects of spatial reasoning, such as relative and absolute spatial relationships, situational reasoning, and object-centric spatial attributes. Our results reveal that: 1) MLLMs perform better at answering questions regarding relative spatial relationships than absolute spatial relationships, 2) MLLMs demonstrate similar spatial reasoning abilities for both egocentric and allocentric perspectives, and 3) Fine-tuning large models significantly improves their performance across different spatial reasoning tasks. We believe that our open-source data collection tools and in-depth analyses will inspire further research on MLLM spatial reasoning capabilities. The benchmark is available at https://github.com/WeichenZh/Open3DVQA.

📄 PDF Abstract BibTeX arXiv:2503.11094

Code (1)

weichenzh/open3dvqa 공식 구현

Tasks

Language ModelingLanguage ModellingLarge Language ModelMultimodal Large Language ModelSpatial ReasoningVisual Question Answering (VQA)

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

Similar Papers 제목 키워드 기반

Geo3DVQA: Evaluating Vision-Language Models for 3D Geospatial Reasoning from Aerial Imagery

2025-12-08 · Mai Tsujimoto, Junjue Wang, Weihao Xuan, Naoto Yokoya arxiv

Three-dimensional geospatial analysis is critical for applications in urban planning, climate adaptation, and environmental assessment. However, current methodologies depend on costly, specialized sensors, such as LiDAR …

Spatial Reasoning

MedVQA-TREE: A Multimodal Reasoning and Retrieval Framework for Sarcopenia Prediction

2025-08-26 · Pardis Moradbeiki, Nasser Ghadiri, Sayed Jalal Zahabi, Uffe Kock Wiil 외 arxiv

Accurate sarcopenia diagnosis via ultrasound remains challenging due to subtle imaging cues, limited labeled data, and the absence of clinical context in most models. We propose MedVQA-TREE, a multimodal framework that i…

Multimodal ReasoningClinical KnowledgeSpatial Reasoning

How Good LLMs Are at Answering Bangla Medical Visual Questions? Dataset and Benchmarking

2026-05-18 · Rafid Ahmed, Intesar Tahmid, Mir Sazzat Hossain, Tasnimul Hossain Tomal 외 arxiv

Recent advancements in Large Language Models (LLMs) and Large Vision Language Models (LVLMs) have enabled general-purpose systems to demonstrate promising capabilities in complex reasoning tasks, including those in the m…

Visual Question Answering

HandVQA: Diagnosing and Improving Fine-Grained Spatial Reasoning about Hands in Vision-Language Models

2026-03-27 · MD Khalequzzaman Chowdhury Sayem, Mubarrat Tajoar Chowdhury, Yihalem Yimolal Tiruneh, Muneeb A. Khan 외 arxiv

Understanding the fine-grained articulation of human hands is critical in high-stakes settings such as robot-assisted surgery, chip manufacturing, and AR/VR-based human-AI interaction. Despite achieving near-human perfor…

Visual Question AnsweringHand Gesture RecognitionSpatial Reasoning

Localizing Before Answering: A Hallucination Evaluation Benchmark for Grounded Medical Multimodal LLMs

2025-04-30 · Dung Nguyen, Minh Khoi Ho, Huy Ta, Thanh Tam Nguyen 외

Medical Large Multi-modal Models (LMMs) have demonstrated remarkable capabilities in medical data interpretation. However, these models frequently generate hallucinations contradicting source evidence, particularly due t…

HallucinationHallucination EvaluationVisual Question Answering (VQA)Visual Reasoning