paper-with-me

Papers

OmniMapBench: Benchmarking Visual-Centric Reasoning on Diverse Map Documents

2026-07-10 · Yang Chen, Yunwen Li, Yufan Shen, Minghao Liu, Tianyu Zheng, Bin Fu, Qunshu Lin, Zhi Yu, Botian Shi arxiv

Recent advancements in LVLMs necessitate robust benchmarks for complex, visually grounded reasoning. A critical limitation is identified in many document understanding benchmarks: visual content is often reducible to text, enabling high performance without genuine visual grounding. To address this limitation, OmniMapBench is introduced to foster visual-centric reasoning for map documents. The benchmark comprises 2,096 manually annotated question-answer pairs across 1,603 map documents from nine categories. It is designed to probe a hierarchy of skills, ranging from perception to multi-step visual reasoning. To quantify benchmark properties, a simple yet effective benchmark-level metric is proposed: the Visual Dependency Index (VDI), defined as the accuracy drop when images are replaced with question-agnostic descriptions. OmniMapBench exhibits higher VDI than established benchmarks, which quantitatively validates its focus on irreducible visual reasoning. Comprehensive evaluations of 25 leading LVLMs are conducted on OmniMapBench. A significant performance gap is observed, with the top-performing model achieving only 75.03\% accuracy. This result underscores the challenges posed by OmniMapBench to current LVLMs. This work aims to catalyze progress in visual-centric reasoning for document understanding of LVLMs. The dataset and code are publicly available at https://github.com/SIGMME/OmniMapBench.

📄 PDF Abstract BibTeX arXiv:2607.09068

Code (0)

등록된 구현이 없습니다.

Tasks

Visual ReasoningVisual Grounding

Similar Papers 제목 키워드 기반

HumanVideo-MME: Benchmarking MLLMs for Human-Centric Video Understanding

2025-07-07 · Yuxuan Cai, Jiangning Zhang, Zhenye Gan, Qingdong He 외 arxiv

Multimodal Large Language Models (MLLMs) have demonstrated significant advances in visual understanding tasks involving both images and videos. However, their capacity to comprehend human-centric video data remains under…

Emotion RecognitionAction RecognitionVideo GenerationAge Estimation

Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought

2025-05-29 · CVPR 2025 1 · Yunze Man, De-An Huang, Guilin Liu, Shiwei Sheng 외

Recent advances in multimodal large language models (MLLMs) have demonstrated remarkable capabilities in vision-language tasks, yet they often struggle with vision-centric scenarios where precise visual focus is needed f…

Multimodal Reasoning

Minerva-Ego: Spatiotemporal Hints for Egocentric Video Understanding

2026-05-14 · Arsha Nagrani, Jasper Uijilings, Shyamal Buch, Tobias Weyand 외 arxiv

Video reasoning models are a core component of egocentric and embodied agents. However, standard benchmarks for assessing models provide only evaluation of the output (e.g. the answer to a question), without evaluation o…

Visual Reasoning

EGOILLUSION: Benchmarking Hallucinations in Egocentric Video Understanding

2025-08-18 · Ashish Seth, Utkarsh Tyagi, Ramaneswaran Selvakumar, Nishit Anand 외 arxiv

Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance in complex multimodal tasks. While MLLMs excel at visual perception and reasoning in third-person and egocentric videos, they are prone to…

Long Grounded Thoughts: Synthesizing Visual Problems and Reasoning Chains at Scale

2025-11-07 · David Acuna, Chao-Han Huck Yang, Yuntian Deng, Jaehun Jung 외 arxiv

Despite rapid progress, multimodal reasoning still lacks a systematic approach to synthesize large-scale vision-centric datasets beyond visual math. We introduce a framework able to synthesize vision-centric problems spa…

Multimodal ReasoningOffline RL