Metraipolis › archive › dc_dcd9dea9e013

Flow-of-Thought: A Framework for Visual Reasoning — arXiv:2610.09746

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.09746
License (as archived)
CC0-1.0
Archived
2026-10-08T12:47:33.534Z
SHA-256 of the archived text
78881002240fb247215684c90a90038d0d4ba9c0c0a65370d3797affdd578713
Stable URL of this page
https://metraipolis.com/documento/dc_dcd9dea9e013

How to cite

Flow-of-Thought: A Framework for Visual Reasoning — arXiv:2610.09746 — arXiv (en), https://arxiv.org/abs/2610.09746 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dcd9dea9e013 (Metraipolis archive dc_dcd9dea9e013, sha256 78881002240fb247215684c90a90038d0d4ba9c0c0a65370d3797affdd578713)
BibTeX
@misc{dcdcd9dea9e013,
  title = {Flow-of-Thought: A Framework for Visual Reasoning — arXiv:2610.09746},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09746},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dcd9dea9e013; sha256 78881002240fb247215684c90a90038d0d4ba9c0c0a65370d3797affdd578713},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09746. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Mental imagery, ``seeing with the mind's eye'' is an essential aspect of human cognition. Despite rapid progress Large Language Models (LLMs) and Vision Transformers (ViTs) still underperform on tasks requiring spatial understanding. To address this, we introduce Flow-of-Thought (FoT), a framework that integrates the generation of visual sketches as intermediate reasoning steps, mimicking mental imagery in humans. We train coordinate-aware trajectory flow fields on $SO(2)$ group orbits and cumulative shortest paths, then freeze the learned dynamics; same vs. different decisions compare competing generative hypotheses using foreground-weighted reconstruction energy. On locked tests FoT reaches 100.0% accuracy on Tetris and 99.0% on colored shapes. Under frozen transfer, the orbit-trained 2D flow improves over its endpoint-only control on BLINK Multi-view (72.2% vs. 63.9% on 133 public validation pairs), supporting continuous visual traces as an effective and interpretable representation for spatial reasoning in some out-of-distribution settings.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.09746 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T12:18:15.406Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).