Metraipolis › archive › dc_4879d0499edd
ZoomCap: Evidence-Routed Visual Zooming for Recoverable Visual Information Transfer — arXiv:2610.21320
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.21320
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T10:02:15.645Z
- SHA-256 of the archived text
6376c14483b65a25e80a5d906cc164ecb19ba2931256c1eac208404b0374ba48- Stable URL of this page
https://metraipolis.com/documento/dc_4879d0499edd
How to cite
ZoomCap: Evidence-Routed Visual Zooming for Recoverable Visual Information Transfer — arXiv:2610.21320 — arXiv (en), https://arxiv.org/abs/2610.21320 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4879d0499edd (Metraipolis archive dc_4879d0499edd, sha256 6376c14483b65a25e80a5d906cc164ecb19ba2931256c1eac208404b0374ba48)
BibTeX
@misc{dc4879d0499edd,
title = {ZoomCap: Evidence-Routed Visual Zooming for Recoverable Visual Information Transfer — arXiv:2610.21320},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.21320},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4879d0499edd; sha256 6376c14483b65a25e80a5d906cc164ecb19ba2931256c1eac208404b0374ba48},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21320. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Detailed captions transfer visual information into vision-language model supervision, but quality is easily conflated with length: long single-pass outputs still miss small objects, text, and spatial relations or promote uncertain observations into confident claims. We formulate fine-grained captioning as recoverable visual information transfer, in which a teacher acquires missing evidence under a finite observation budget and converts it into reusable supervision. ZoomCap uses a draft caption to route conditional knowledge retrieval, OCR-sensitive reading, coverage-gap recovery, and adaptive visual zooming, allocating deeper crops only to the most complex eligible region, deriving spatial relations from grounded geometry, and fusing non-duplicate evidence. We also introduce FactCycle, which scores caption-derived atomic claims on two blind anchors--source image (truthfulness) and reconstruction (realizability)--separating fabrication from generator loss claim by claim; human and multi-judge comparisons complement this fact-level view. Against Qwen3.5-397B-A17B captions, ZoomCap achieves an 81.9% human tie-adjusted preference score with a teacher over 10x smaller, and FactCycle counts 52.4 transferred claims per image vs. 31.5 for ScaleCap. The evidence also transfers: in continual pre-training, ZoomCap-450K improves the 11-benchmark average by 1.31-2.38 points over the strongest competing corpus and Ling-Tiny-VL-v3 gains 1.4 points on a production document/OCR monitor suite (1.5 on perception) at 60B tokens; in medical pre-training, 2.64M ZoomCap-captioned images improve five VQA benchmarks by 3.04 points (vs. 1.76 for same-image Gemini-3.1-Pro captions). Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Computation and Language (cs.CL); Multimedia (cs.MM). Pagina del lavoro: https://arxiv.org/abs/2610.21320 — 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 2026-10-16T08:44:47.750Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).