Metraipolis › archive › dc_f12e1063b1de

A Strong Baseline for Evaluating Vision Encoders in Multimodal Large Language Models — arXiv:2610.05413

Source
arXiv
Original
https://arxiv.org/abs/2610.05413
License (as archived)
CC0-1.0
Archived
2026-10-06T05:26:55.602Z
SHA-256 of the archived text
a9711709d080d46219b862ef21a1702f0c0a9d12b3690f4d0a01496d5db538de
Stable URL of this page
https://metraipolis.com/documento/dc_f12e1063b1de

How to cite

A Strong Baseline for Evaluating Vision Encoders in Multimodal Large Language Models — arXiv:2610.05413 — arXiv, https://arxiv.org/abs/2610.05413 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f12e1063b1de (Metraipolis archive dc_f12e1063b1de, sha256 a9711709d080d46219b862ef21a1702f0c0a9d12b3690f4d0a01496d5db538de)
BibTeX
@misc{dcf12e1063b1de,
  title = {A Strong Baseline for Evaluating Vision Encoders in Multimodal Large Language Models — arXiv:2610.05413},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05413},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f12e1063b1de; sha256 a9711709d080d46219b862ef21a1702f0c0a9d12b3690f4d0a01496d5db538de},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05413. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Evaluating vision encoders requires metrics that reliably predict their downstream performance in multimodal large language models (MLLMs). Although recent studies have shown that cross-modal metrics can better capture such performance, unimodal metrics remain the dominant choice in practice. In this work, we revisit cross-modal evaluation of vision encoders through large-scale experiments. We identify important limitations in both the experimental design and methodological formulation of prior approaches. After addressing these limitations and introducing simple improvements, we propose RAVEL, a training-free method based on cross-modal nearest-neighbor retrieval. Despite its simplicity, RAVEL achieves state-of-the-art performance across our experiments, outperforming prior methods by a substantial margin. Our results demonstrate that simple cross-modal metrics, when evaluated under a careful and comprehensive setup, can provide a strong basis for evaluating vision encoders for MLLMs.

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/2610.05413 — 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 2026-10-06T05:24:06.024Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).