LensVLM: Selective Context Expansion for Compressed Visual Representation of Text

TL;DR

LensVLM introduces a selective expansion method for compressed visual representations in vision-language models, maintaining high accuracy at significant compression levels across various tasks.

Contribution

It presents a novel inference framework and training recipe enabling VLMs to selectively expand relevant compressed images, improving accuracy under high compression.

Findings

Maintains accuracy comparable to full-text at 4.3x compression.

Outperforms baselines up to 10.1x compression on text QA benchmarks.

Generalizes to multimodal document and code understanding tasks.

Abstract

Vision Language Models (VLMs) offer the exciting possibility of processing text as rendered images, bypassing the need for tokenizing the text into long token sequences. Since VLM image encoders map fixed-size images to a fixed number of visual tokens, varying rendering resolution provides a fine-grained compression knob. However, accuracy deteriorates quickly as compression increases: characters shrink below the vision encoder's effective resolution, making them indistinguishable. To address this, we propose LensVLM, an inference framework and post-training recipe that enables VLMs to scan compressed images, then selectively expand only the relevant images to their uncompressed form via learned tools. Building on Qwen3.5-9B-Base, LensVLM maintains accuracy comparable to the full-text upper bound at 4.3x effective compression and outperforms retrieval-based, text- and visual-compression baselines up to 10.1x effective compression across seven text QA benchmarks. LensVLM also generalizes to multimodal document and code understanding tasks, with the accuracy gain over baselines growing as compression increases. Our analysis validates this approach: training makes visual compression robust to rendering choices, and as compression grows the model increasingly relies on expanded content rather than unreliable visual reading. The analysis also yields practical tool-choice guidance: text expansion is preferable for rendered text, while high-resolution image expansion suits native documents whose layout cues carry task-relevant information.