Metraipolis › archive › dc_bce8502d0deb

UltraG-Bench: A Multi-task Benchmark for assessing Large Vision-Language Models on Pixel-level Evidence Grounding in Ultrasound — arXiv:2609.30928

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.30928
License (as archived)
CC0-1.0
Archived
2026-10-08T01:39:34.846Z
SHA-256 of the archived text
1e03955fad44b040718ff01eb442ddca685e7efb7cfd4ce2a29deb45512cb4ee
Stable URL of this page
https://metraipolis.com/documento/dc_bce8502d0deb

How to cite

UltraG-Bench: A Multi-task Benchmark for assessing Large Vision-Language Models on Pixel-level Evidence Grounding in Ultrasound — arXiv:2609.30928 — arXiv (en), https://arxiv.org/abs/2609.30928 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bce8502d0deb (Metraipolis archive dc_bce8502d0deb, sha256 1e03955fad44b040718ff01eb442ddca685e7efb7cfd4ce2a29deb45512cb4ee)
BibTeX
@misc{dcbce8502d0deb,
  title = {UltraG-Bench: A Multi-task Benchmark for assessing Large Vision-Language Models on Pixel-level Evidence Grounding in Ultrasound — arXiv:2609.30928},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30928},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bce8502d0deb; sha256 1e03955fad44b040718ff01eb442ddca685e7efb7cfd4ce2a29deb45512cb4ee},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30928. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Ultrasound is one of the most widely used medical imaging modalities, and recent large vision-language models(VLMs) have shown increasing capabilities in ultrasound image understanding. However, these models fail to provide pixel-level visual evidence aligned with their semantic predictions, and their fine-grained grounding capability in ultrasound remains largely unclear. We introduce UltraG-Bench, a large-scale multi-task benchmark for evaluating pixel-level evidence grounding in ultrasound. UltraG-Bench is built by annotating 40 public ultrasound segmentation datasets spanning 13 anatomical categories, and comprises three progressive tasks: instruction-guided segmentation, evidence-grounded VQA, and evidence-grounded report generation, with 331125, 666779, and 138832 annotations, respectively. Comprehensive evaluation of 14 state-of-the-art models reveals a substantial gap between semantic understanding and fine-grained pixel-level localization. We further propose UltraG-Agent, which combines the semantic reasoning capabilities of a VLM with the ultrasound-specific segmentation capability of UltraSAM3. Experiments show that UltraG-Agent substantially improves both semantic prediction and pixel-level visual grounding. Our dataset and code are available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.30928 — 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 2026-10-08T01:12:14.500Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).