international / Feb 2026
From Correspondence to Actions: Human-Like Multi-Image Spatial Reasoning in Multi-modal Large Language Models
International Conference on Machine Learning (ICML 2026)
Proposes a framework for evaluating human-like multi-image spatial reasoning in multi-modal large language models, analyzing how models establish correspondence across images and translate spatial understanding into actions.
Citation引用情報
@inproceedings{ohi2026hatch,
title={From Correspondence to Actions: Human-Like Multi-Image Spatial Reasoning in Multi-modal Large Language Models},
author={Masanari Ohi and Koki Maeda and Ryuto Koike and Daisuke Oba and Nakamasa Inoue and Naoaki Okazaki},
booktitle={International Conference on Machine Learning (ICML 2026)},
year={2026},
eprint={2602.08735},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2602.08735}
}