Metraipolis › archive › dc_2f29e31025fc
Beyond Discrete Tokens: Preserving Numerical Continuity in Medical Vision-Language Models — arXiv:2610.32948
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.32948
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-26T19:52:42.387Z
- SHA-256 of the archived text
cbf9282b7c9ed8722168ca38398bafd0406c697d847b65f3891da3ea8c94ece9- Stable URL of this page
https://metraipolis.com/documento/dc_2f29e31025fc
How to cite
Beyond Discrete Tokens: Preserving Numerical Continuity in Medical Vision-Language Models — arXiv:2610.32948 — arXiv (en), https://arxiv.org/abs/2610.32948 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2f29e31025fc (Metraipolis archive dc_2f29e31025fc, sha256 cbf9282b7c9ed8722168ca38398bafd0406c697d847b65f3891da3ea8c94ece9)
BibTeX
@misc{dc2f29e31025fc,
title = {Beyond Discrete Tokens: Preserving Numerical Continuity in Medical Vision-Language Models — arXiv:2610.32948},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.32948},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2f29e31025fc; sha256 cbf9282b7c9ed8722168ca38398bafd0406c697d847b65f3891da3ea8c94ece9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32948. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Objective: To develop a unified vision-language model for prompt-conditioned quantitative ultrasound measurement that addresses the mismatch between continuous measurement targets and discrete token-based numerical prediction. Methods: This article presents HAD-VLM, a hybrid autoregressive-diffusion framework that combines autoregressive text generation with continuous measurement prediction within a shared backbone. Visual prompt tuning adapts the vision encoder to ultrasound images. A diffusion process predicts a five-component representation comprising caliper endpoint coordinates and measurement length. A post-processing strategy combining the proposed coordinate-length consistency mechanism with ensemble prediction is introduced to refine measurement estimates. We evaluate four echocardiographic measurement tasks on EchoNet-LVH, with additional assessments of medical question answering and X-ray vertebral measurement. Results: HAD-VLM achieves mean absolute errors of 1.36, 2.77, 3.05, and 1.16 mm for IVSd, LVIDd, LVIDs, and LVPWd, respectively, reducing errors by 21.4-37.6\% relative to the Vicuna-based autoregressive baseline. It also outperforms fine-tuned Qwen3-VL and direct MLP regression across all four tasks. Medical question answering performance is preserved on the evaluated dataset. For X-ray vertebral measurement, HAD-VLM reduces mean absolute error from 11.4 to 6.7 pixels. Conclusion: Integrating autoregressive language generation with diffusion-based continuous prediction improves quantitative medical image measurement while retaining prompt-conditioned task flexibility. Significance: HAD-VLM provides a unified approach to combining language interaction with anatomically grounded numerical prediction for quantitative medical image analysis. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.32948 — 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 2026-10-26T19:45:33.442Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).