We introduce LiveVQA, an automatically collected dataset of latest visual knowledge from the Internet with synthesized VQA problems. LiveVQA consists of 3,602 single- and multi-hop visual questions from 6 news websites across 14 news categories, featuring high-quality image-text coherence and authentic information. Our evaluation across 15 MLLMs (e.g., GPT-4o, Gemma-3, and Qwen-2.5-VL family) demonstrates that stronger models perform better overall, with advanced visual reasoning capabilities proving crucial for complex multi-hop questions. Despite excellent performance on textual problems, models with tools like search engines still show significant gaps when addressing visual questions requiring latest visual knowledge, highlighting important areas for future research.
View on arXiv@article{fu2025_2504.05288,
title={ LiveVQA: Live Visual Knowledge Seeking },
author={ Mingyang Fu and Yuyang Peng and Benlin Liu and Yao Wan and Dongping Chen },
journal={arXiv preprint arXiv:2504.05288},
year={ 2025 }
}