Metraipolis › archive › dc_4fa8733d9ecf

VLMProbe: An Open-source Library for VLM Probing and Interpretation — arXiv:2610.33072

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.33072
License (as archived)
CC0-1.0
Archived
2026-10-27T07:59:33.483Z
SHA-256 of the archived text
90c988a004a1837ccd326e51cfe02152091cde1ce312b4a5a9455822a44cc9ed
Stable URL of this page
https://metraipolis.com/documento/dc_4fa8733d9ecf

How to cite

VLMProbe: An Open-source Library for VLM Probing and Interpretation — arXiv:2610.33072 — arXiv (en), https://arxiv.org/abs/2610.33072 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4fa8733d9ecf (Metraipolis archive dc_4fa8733d9ecf, sha256 90c988a004a1837ccd326e51cfe02152091cde1ce312b4a5a9455822a44cc9ed)
BibTeX
@misc{dc4fa8733d9ecf,
  title = {VLMProbe: An Open-source Library for VLM Probing and Interpretation — arXiv:2610.33072},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.33072},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4fa8733d9ecf; sha256 90c988a004a1837ccd326e51cfe02152091cde1ce312b4a5a9455822a44cc9ed},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.33072. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Understanding how vision-language models use visual information requires connecting internal representations to model behavior. We present vlmprobe, an open-source library that integrates lens readouts, attention attribution, causal interventions, and sparse autoencoder (SAE) analysis within a common model interface. Shared adapters, calibration and checkpoint utilities, evaluation pipelines, and visualizations support systematic analysis across architectures. Using this framework, we compare methods across vision-language, language, and vision models through matched case studies and controlled evaluations of pretrained sparse dictionaries. The comparisons show that representation readouts and spatial explanations depend on the analysis objective and observation site, and that local attribution estimates can disagree with measured intervention effects. SAE evaluations further expose distinct trade-offs in reconstruction fidelity, concept readout, and spatial localization. Together, these results support combining multiple forms of evidence to evaluate an interpretation. vlmprobe provides a reusable basis for selecting methods, comparing their conclusions, and testing hypotheses about model behavior. The code is available on this http URL

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/2610.33072 — 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 2026-10-27T07:55:30.805Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).