Metraipolis › archive › dc_a5e64237ca83

Open-Weight MLLMs Cannot Compare What They Cannot Name — arXiv:2610.41841

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41841
License (as archived)
CC0-1.0
Archived
2026-11-02T05:04:19.150Z
SHA-256 of the archived text
15797510388fead18441a49acea0d81f9158c48799999d0bbffa33a6bcbcc839
Stable URL of this page
https://metraipolis.com/documento/dc_a5e64237ca83

How to cite

Open-Weight MLLMs Cannot Compare What They Cannot Name — arXiv:2610.41841 — arXiv (en), https://arxiv.org/abs/2610.41841 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a5e64237ca83 (Metraipolis archive dc_a5e64237ca83, sha256 15797510388fead18441a49acea0d81f9158c48799999d0bbffa33a6bcbcc839)
BibTeX
@misc{dca5e64237ca83,
  title = {Open-Weight MLLMs Cannot Compare What They Cannot Name — arXiv:2610.41841},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41841},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a5e64237ca83; sha256 15797510388fead18441a49acea0d81f9158c48799999d0bbffa33a6bcbcc839},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41841. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal Large Language Models (MLLMs) are increasingly capable of understanding images and performing complex visual reasoning, suggesting the possibility of using them to automate biological image analysis. This need is becoming increasingly urgent as advances in technology continue to generate ever larger and more diverse microscopy datasets, already exceeding the scale at which manual visual analysis is feasible. With the final aim to use MLLMs for visual comparison of complex phenotypes, we investigate a very simple baseline: comparison of the size of body parts in synthetic images of ants. We find that state-of-the-art open-weight MLLMs fail for some body parts, but not for others, even though the comparison itself is visually trivial for all of them. We evaluate different in-context learning strategies and analyze performance on the related object recognition task. Our results suggest a recognition-driven grounding failure: structures that the models cannot recognize are instead associated with a recognizable semantic concept, impairing the grounding and comparison of both. Further analysis of the vision encoder is consistent with the hypothesis that fine-grained visual structure may be less well preserved without semantic support. Together, our results reveal a surprising limitation of current MLLMs: semantic recognition can gate simple visual comparisons that do not intrinsically require semantic understanding. Our code and data are available at this https URL

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.41841 — 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 2026-11-02T04:49:13.277Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).