Metraipolis › archive › dc_6ec9be5e126d

Pay More Attention To Text In High-Resolution MLLMs — arXiv:2609.23495

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.23495
License (as archived)
CC0-1.0
Archived
2026-10-09T21:59:40.169Z
SHA-256 of the archived text
7222eb52fa9b023e29915d074fb41ca2d98e2e07aff0671ddce653d58858c4c8
Stable URL of this page
https://metraipolis.com/documento/dc_6ec9be5e126d

How to cite

Pay More Attention To Text In High-Resolution MLLMs — arXiv:2609.23495 — arXiv (en), https://arxiv.org/abs/2609.23495 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6ec9be5e126d (Metraipolis archive dc_6ec9be5e126d, sha256 7222eb52fa9b023e29915d074fb41ca2d98e2e07aff0671ddce653d58858c4c8)
BibTeX
@misc{dc6ec9be5e126d,
  title = {Pay More Attention To Text In High-Resolution MLLMs — arXiv:2609.23495},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.23495},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6ec9be5e126d; sha256 7222eb52fa9b023e29915d074fb41ca2d98e2e07aff0671ddce653d58858c4c8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23495. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Failures of high-resolution MLLMs are commonly attributed to a visual problem, motivating zooming, cropping, and related visual interventions to recover fine-grained evidence or suppress interference. Yet recent studies suggest that relevant visual evidence is already encoded in intermediate representations, indicating that visual-side improvements alone insufficient. This raises a natural question: does the remaining bottleneck lie in the text that guides visual search? We identify a previously overlooked linguistic bottleneck: questions formulated for answering do not necessarily specify the visual evidence required for localization. To address this mismatch, we introduce EviSpec, a training-free compiler that derives complementary evidence specifications while preserving the original question for final reasoning. We further validate it through matched-control experiments that isolate the roles of evidence specification and localization. With the search budget fixed, structured evidence specifications yield an 8.6% relative gain over generic requests. With evidence geometry matched, the evidence localized by EviSpec yields a 14.8% relative gain over random evidence. Together, these controls isolate the benefit of specifying what evidence to seek rather than merely expanding visual access. Across all five MLLMs, EviSpec consistently improves upon the corresponding baseline on each of the three benchmarks, yielding average relative gains of \textbf{10.4%, 8.8%, and 12.4%} on V\textsuperscript{*}Bench, HR-Bench-4K, and HR-Bench-8K, respectively. Beyond high-resolution reasoning, EviSpec also achieves state-of-the-art performance on VQA and hallucination-focused benchmarks.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.23495 — 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 2026-10-09T21:45:20.909Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).