Metraipolis › archive › dc_cf16d0ee2d06
CoEvolve: Construct-to-Edit Visual Grounding with Bidirectional State Refinement — arXiv:2610.01710
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.01710
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T12:05:54.248Z
- SHA-256 of the archived text
f50b0876f387c102739302238d68125733ee8890d5a2642ec243d050142d3bdc- Stable URL of this page
https://metraipolis.com/documento/dc_cf16d0ee2d06
How to cite
CoEvolve: Construct-to-Edit Visual Grounding with Bidirectional State Refinement — arXiv:2610.01710 — arXiv (en), https://arxiv.org/abs/2610.01710 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cf16d0ee2d06 (Metraipolis archive dc_cf16d0ee2d06, sha256 f50b0876f387c102739302238d68125733ee8890d5a2642ec243d050142d3bdc)
BibTeX
@misc{dccf16d0ee2d06,
title = {CoEvolve: Construct-to-Edit Visual Grounding with Bidirectional State Refinement — arXiv:2610.01710},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.01710},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cf16d0ee2d06; sha256 f50b0876f387c102739302238d68125733ee8890d5a2642ec243d050142d3bdc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01710. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Visual grounding localizes an object described by language with a bounding box. Most multimodal grounding models compress target identification, spatial reasoning, and boundary estimation into one terminal prediction. Free-form rationales make reasoning linguistically explicit but do not necessarily expose measurable, editable spatial states. Intermediate localization errors are therefore difficult to diagnose and correct, allowing incorrect region choices and imprecise boundaries to persist in the final box. We introduce CoEvolve, a construct-to-edit framework that separates grounding into explicit state construction and state editing. Region-Evolution Reinforcement (RER) organizes grounding analysis into a progressive semantic--spatial trajectory, with each reasoning step committing to an explicit candidate region. Bidirectional Denoising Refiner (BDR) treats the reasoning text as fixed semantic context and refines the trajectory's coordinate fields through bidirectional same-position reconstruction. Geometry- and behavior-level objectives provide target geometry and edit-preference signals for consolidating reliable candidates, preserving accurate inputs, or correcting toward annotations. Evaluations cover natural-image and remote-sensing grounding. With a 9B backbone, CoEvolve rivals models up to 241B parameters in grounding accuracy. Under controlled corruption, a single BDR pass improves mean box overlap by over 27 percentage points, demonstrating strong recovery from substantial localization errors. State-source comparisons further support the complementarity of explicit state construction and source-matched editing. The project is at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.01710 — 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 2026-10-06T10:21:27.969Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).