Metraipolis › archive › dc_c5b24eddbeac

Candidate-Expanding Routing with Permutation-Stabilized Experts for Mixed-Format Medical VQA — arXiv:2609.00959

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.00959
License (as archived)
CC0-1.0
Archived
2026-10-17T07:13:43.457Z
SHA-256 of the archived text
af0d5a34c9981f6116f97f3add9dca9d1c9b6abe21dd4412503e71d75296a59f
Stable URL of this page
https://metraipolis.com/documento/dc_c5b24eddbeac

How to cite

Candidate-Expanding Routing with Permutation-Stabilized Experts for Mixed-Format Medical VQA — arXiv:2609.00959 — arXiv (en), https://arxiv.org/abs/2609.00959 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c5b24eddbeac (Metraipolis archive dc_c5b24eddbeac, sha256 af0d5a34c9981f6116f97f3add9dca9d1c9b6abe21dd4412503e71d75296a59f)
BibTeX
@misc{dcc5b24eddbeac,
  title = {Candidate-Expanding Routing with Permutation-Stabilized Experts for Mixed-Format Medical VQA — arXiv:2609.00959},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00959},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c5b24eddbeac; sha256 af0d5a34c9981f6116f97f3add9dca9d1c9b6abe21dd4412503e71d75296a59f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00959. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Mixed-format medical visual question answering (VQA) requires stable option selection and machine-readable free-text output. The two formats fail differently: multiple-choice predictions can change with option symbols or positions, while clinically plausible open answers can fail automated evaluation when serialization is malformed. We address both challenges with an answer-text memory, a permutation-stabilized vision--language expert, and a sparse candidate- expanding router. The cyclic schedule follows prior work; our contribution is to make expert top-2 a routable candidate alongside memory and expert top-1. On a 1,403-case retrospective internal analysis, this expansion improves a matched binary router from 88.95% to 91.73% (+2.78 percentage points; 95% CI 1.57--3.99), with 56 rescued errors and 17 regressions. Oracle coverage rises from 90.31% to 96.15%, and the final submitted configuration reaches 92.23% on the same retrospective split. For open questions, strict generation and deterministic guards produce 475/475 schema- valid participant-facing outputs without repair, retry, or hard-gate failure. Visual ablations reveal substantial textual dependence. Candidate expansion supplies the principal controlled routing gain; open-path evidence establishes output-contract validity rather than clinical correctness in medical use or deployment.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-02 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.00959 — 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 2026-10-17T07:00:58.951Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).