Metraipolis › archive › dc_347ca3ecd6f3
CVIF: A Criticality-Driven Visual Intervention Framework for Geometric Diagram Understanding in MLLMs — arXiv:2610.06399
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.06399
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:25:33.970Z
- SHA-256 of the archived text
544a9397ff4c7cbf1bb87b4b0408758e51646b9d3c5e3b991615ab4761cec722- Stable URL of this page
https://metraipolis.com/documento/dc_347ca3ecd6f3
How to cite
CVIF: A Criticality-Driven Visual Intervention Framework for Geometric Diagram Understanding in MLLMs — arXiv:2610.06399 — arXiv, https://arxiv.org/abs/2610.06399 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_347ca3ecd6f3 (Metraipolis archive dc_347ca3ecd6f3, sha256 544a9397ff4c7cbf1bb87b4b0408758e51646b9d3c5e3b991615ab4761cec722)
BibTeX
@misc{dc347ca3ecd6f3,
title = {CVIF: A Criticality-Driven Visual Intervention Framework for Geometric Diagram Understanding in MLLMs — arXiv:2610.06399},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.06399},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_347ca3ecd6f3; sha256 544a9397ff4c7cbf1bb87b4b0408758e51646b9d3c5e3b991615ab4761cec722},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06399. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Despite significant progress in visual tasks by Multimodal Large Language Models (MLLMs), geometric diagram understanding remains challenging due to the presence of sparse visual cues and ambiguous symbol-primitive associations. MLLMs may therefore rely on textual priors, producing interpretations that conflict with visual evidence. We introduce the training-free Criticality-Driven Visual Intervention Framework (CVIF), an inference-time method that localizes critical layers and executes visual interventions during the transition from evidence aggregation to semantic decoding. At these layers, a Geometry-Constrained Local Relation Reconstruction (GCLR) module selects and weights vertex-centered visual evidence, while an Adaptive Visual Steering Operator (AVSO) redistributes attention mass toward the selected tokens. Experiments on PGPS9K and PGDP5K show that CVIF raises Overall F1 from 77.85 to 85.58 and from 75.23 to 82.84, respectively, establishing a novel inference-time visual intervention paradigm. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.06399 — 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 2026-10-06T05:24:05.674Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).