Metraipolis › archive › dc_a45170d98288
ReVision3D: Attribution-Guided Recursive Self-Improvement for 3D Medical Perception — arXiv:2609.32984
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.32984
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T23:51:08.590Z
- SHA-256 of the archived text
3154414f8e55abc228d94aa7b0a0a7a1300eee6950be4ff8d10eee4e18f5a3a5- Stable URL of this page
https://metraipolis.com/documento/dc_a45170d98288
How to cite
ReVision3D: Attribution-Guided Recursive Self-Improvement for 3D Medical Perception — arXiv:2609.32984 — arXiv (en), https://arxiv.org/abs/2609.32984 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a45170d98288 (Metraipolis archive dc_a45170d98288, sha256 3154414f8e55abc228d94aa7b0a0a7a1300eee6950be4ff8d10eee4e18f5a3a5)
BibTeX
@misc{dca45170d98288,
title = {ReVision3D: Attribution-Guided Recursive Self-Improvement for 3D Medical Perception — arXiv:2609.32984},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.32984},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a45170d98288; sha256 3154414f8e55abc228d94aa7b0a0a7a1300eee6950be4ff8d10eee4e18f5a3a5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32984. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recursive self-improvement (RSI) offers a promising path for overcoming the limited visual capability of current medical imaging agents. Yet applying RSI to volumetric imaging remains difficult: failures can arise from acquisition, perception, training recipe, or downstream inference, while self-generated feedback and logged trajectories provide little guidance on which component should change. We introduce ReVision3D, an RSI system that leverages 3D volumes with spatially grounded annotations to determine where visual evidence is lost and recursively improve the corresponding visual capability. A frozen language-model designer proposes revisions to acquisition, perception, training, or inference, while the verifier and system-level objective remain fixed. Our key insight is that an annotated volume forms an exact replay world for view rendering and spatial verification: unvisited views can be rendered on demand, and localized predictions can be checked directly against reference masks. This grounded feedback directs targeted revision, while only changes that improve beyond measured seed noise are retained. Each accepted change triggers renewed attribution, allowing the dominant bottleneck to shift across rounds. On abdominal CT, attribution identifies perception as the dominant remaining limitation. Revising that level enables ReVision3D to achieve 79% liver recall and 83% kidney recall at under 0.4 false positives per patient, outperforming the evaluated frozen multimodal foundation models, with the largest gains on small lesions. Our framework is public available with interactive demo in this project page: \url{ this https URL }
Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.32984 — 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 2026-10-07T23:29:27.122Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).