Framing visual text compression as measure transport decomposes encoding loss into precision and coverage costs, enabling a label-free routing rule that matches oracle performance on 17 of 24 NLP datasets while using 10% fewer tokens.
Text or pixels? it takes half: On the token efficiency of visual text inputs in multimodal llms.arXiv preprint arXiv:2510.18279
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 4years
2026 4roles
background 1polarities
background 1representative citing papers
VISTA-Bench shows vision-language models degrade on visualized text in images compared to equivalent pure text, with larger gaps under increased perceptual difficulty.
LoMo is a lightweight data curation technique that locally substitutes text with images in prompts to enforce cross-modal invariance, yielding 2.67-2.82 point gains over standard SFT on two VLMs across 13 benchmarks.
IPPg embeds text into images to reduce multimodal model inference costs by 35.8-91% with competitive accuracy on many VQA and code benchmarks.
citing papers explorer
-
Visual Text Compression as Measure Transport
Framing visual text compression as measure transport decomposes encoding loss into precision and coverage costs, enabling a label-free routing rule that matches oracle performance on 17 of 24 NLP datasets while using 10% fewer tokens.
-
VISTA-Bench: Do Vision-Language Models Really Understand Visualized Text as Well as Pure Text?
VISTA-Bench shows vision-language models degrade on visualized text in images compared to equivalent pure text, with larger gaps under increased perceptual difficulty.
-
LoMo: Local Modality Substitution for Deeper Vision-Language Fusion
LoMo is a lightweight data curation technique that locally substitutes text with images in prompts to enforce cross-modal invariance, yielding 2.67-2.82 point gains over standard SFT on two VLMs across 13 benchmarks.
-
Token-Efficient Multimodal Reasoning via Image Prompt Packaging
IPPg embeds text into images to reduce multimodal model inference costs by 35.8-91% with competitive accuracy on many VQA and code benchmarks.