Year: 2025
Type: preprint
Abstract: When thinking with images, humans rarely rely on a single glance: they revisit visual evidence while reasoning. In contrast, most Multimodal Language Models encode an image once to key-value cache and then reason purely in text, making it hard to re-ground intermediate steps. We empirically confirm this: as reasoning chains lengthen, models progressively lose focus on relevant regions. We introduce v1, a lightweight extension for active visual referencing via point-and-copy: the model selects relevant image patches and copies their embeddings back into the reasoning stream. Crucially, our point-and-copy mechanism retrieves patches using their semantic representations as keys, ensuring perceptual evidence remains aligned with the reasoning space. To train this behavior, we build v1g, a dataset of 300K multimodal reasoning traces with interleaved grounding annotations. Across multimodal mathematical reasoning benchmarks, v1 consistently outperforms comparable baselines. We release our code, model, and data.
Source: arXiv (Cornell University)
Authors: Chung, Jiwan, Kim, Junhyeok, Kim, Siyeol, Lee, Jaeyoung, Kim, Min Soo, Yu, Youngjae
Institutions: Seoul National University, Yonsei University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4414801147
Cites:
Cited by:
Related to: