Metraipolis › archive › dc_dbb5f2f99292

NumerosityVLM: A Cognitively Inspired Benchmark for Interpreting Numerosity Representations in Vision-Language Models — arXiv:2608.15425

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.15425
License (as archived)
CC0-1.0
Archived
2026-10-18T18:03:30.761Z
SHA-256 of the archived text
a11ddcab49856f1c4c4cf94a96577fb033ade774948d3d9fe19b70d311c41fe7
Stable URL of this page
https://metraipolis.com/documento/dc_dbb5f2f99292

How to cite

NumerosityVLM: A Cognitively Inspired Benchmark for Interpreting Numerosity Representations in Vision-Language Models — arXiv:2608.15425 — arXiv (en), https://arxiv.org/abs/2608.15425 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dbb5f2f99292 (Metraipolis archive dc_dbb5f2f99292, sha256 a11ddcab49856f1c4c4cf94a96577fb033ade774948d3d9fe19b70d311c41fe7)
BibTeX
@misc{dcdbb5f2f99292,
  title = {NumerosityVLM: A Cognitively Inspired Benchmark for Interpreting Numerosity Representations in Vision-Language Models — arXiv:2608.15425},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15425},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dbb5f2f99292; sha256 a11ddcab49856f1c4c4cf94a96577fb033ade774948d3d9fe19b70d311c41fe7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15425. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language models (VLMs) achieve strong performance on high-level multimodal tasks, yet numerosity perception, a cognitive ability that emerges in human infants before language acquisition, remains poorly understood in current models, as existing counting benchmarks entangle numerosity with correlated visual factors. We introduce a cognitively inspired diagnostic benchmark, NumerosityVLM, comprising 10,800 synthetic images across six controlled conditions. The benchmark orthogonally manipulates object size, spatial arrangement, and numerosity, while progressively ablating texture, shape, and color. Evaluating seven VLMs in a zero-shot setting, multi-factor analysis reveals that model architecture explains the largest proportion of performance variance (partial $\omega^{2}=0.325$), far exceeding visual conditions. Layer-wise probing further shows that linearly separable numerosity signals consistently emerge at early stages of the vision encoder, while performance differences across evaluated models are primarily associated with the language model component. Code and data are publicly available at this https URL , and this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.15425 — 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 2026-10-18T16:29:14.018Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).