Metraipolis › archive › dc_6c09e747abbf
See, Measure, and Reason: Learning Visually Grounded Reasoning in Pathology — arXiv:2609.34277
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34277
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:02:19.683Z
- SHA-256 of the archived text
6f840435ee3b52ea15f7a8f147c3130eea1bc5f987d7f9c0a4307816c23ce037- Stable URL of this page
https://metraipolis.com/documento/dc_6c09e747abbf
How to cite
See, Measure, and Reason: Learning Visually Grounded Reasoning in Pathology — arXiv:2609.34277 — arXiv (en), https://arxiv.org/abs/2609.34277 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6c09e747abbf (Metraipolis archive dc_6c09e747abbf, sha256 6f840435ee3b52ea15f7a8f147c3130eea1bc5f987d7f9c0a4307816c23ce037)
BibTeX
@misc{dc6c09e747abbf,
title = {See, Measure, and Reason: Learning Visually Grounded Reasoning in Pathology — arXiv:2609.34277},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34277},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6c09e747abbf; sha256 6f840435ee3b52ea15f7a8f147c3130eea1bc5f987d7f9c0a4307816c23ce037},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34277. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Pathological assessment relies on recognizing fine-grained visual details in histological images. Vision-language models (VLMs) increasingly support pathology interpretation, yet their ability to perceive these details remains inadequate. This weakness leads to inaccurate cellular observations that can persist even when final answers are correct. In this paper, we propose ASPECT to improve visually grounded reasoning through explicit supervision of cellular appearance and abundance. ASPECT trains intermediate visual tokens through pathology feature reconstruction, cell feature alignment, and count supervision. Three-stage supervised fine-tuning teaches the model to perceive, generate visual tokens, and reason, followed by reinforcement learning that rewards answer correctness and consistency with reported measurements. We also introduce PathoVernier, a benchmark of 759 expert-reviewed questions from five pathology datasets covering four cellular composition tasks. It evaluates both final answers and intermediate measurements to expose errors hidden by answer accuracy. On PathoVernier, ASPECT achieves relative accuracy gains of approximately 19.2% over the strongest baseline, Gemini-3.1-Pro, and 99.3% over its Qwen3-VL-8B backbone, while reducing RAWR, which measures counting errors within correct responses, by 28.1% and 42.7%, respectively. ASPECT also improves over its backbone on three external pathology benchmarks covering classification and question answering beyond cellular composition tasks. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.34277 — 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 2026-10-07T20:29:02.918Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).