Magnifying What Matters: Attention-Guided Adaptive Rendering for Visual Text Comprehension
Authors: Shenglai Zeng, Qirui Wang, Kai Guo, Xinnan Dai, Xianxuan Long, Hui Liu
Organizations: Michigan State University · Xi’an Jiaotong University
Abstract
Visual Text Comprehension (VTC) renders text into images for a vision-language model (VLM) to read, sidestepping LLM context-window limits and powering applications from long-page OCR to multi-page memory QA. Yet existing VTC pipelines treat rendering and layout as a fixed, content-agnostic preprocessing step and offer little mechanistic understanding of how VLMs internally process visualized text. Through a focused empirical study on VTC QA tasks, we reveal that VLMs exhibit a localization-without-utilization regime: evidence-localizing attention emerges sharply in the middle-to-late layers and is largely decoupled from answer correctness, yet simply enlarging the localized spans on the rendered page recovers a large fraction of the failures. Building on these observations, we propose AGAR (Attention-Guided Adaptive Rendering), a training-free, model-agnostic method that leverages a VLM's own middle-to-late layer attention to identify the top-K important visual patches, maps them back to word spans, and re-renders the page with those spans enlarged before re-inferring the answer. Extensive experiments across nine VTC benchmarks (short-form, long-context, and multi-page memory QA) and four VLM backbones show that AGAR (i)consistently improves off-the-shelf VLMs as a plug-and-play enhancement, (ii)composes with VLM post-training to yield further gains, and (iii)remains robust under both visual- and text-side input degradation.
Recent work typically assesses vision--language consistency using attention distributions of answer-side tokens. However, we observe that highest attention regions are not always consistent with the intended semantic token. This probably stems from decoding drift, where language priors from previously generated answer tokens accumulate and mismatch with visual attention. Besides the priors from previous answer tokens, we find that structural tokens, e.g., modality boundary markers, may encompass the entire context and generate high attention to areas unrelated to the target. To avoid these distortions and provide consistency evaluation for large VLMs, we adopt prompt-side semantics and propose Prompt-Vision Token Activation Map (PV-TAM). PV-TAM further incorporates a filter to remove systematic bias induced by modality boundary markers. Unlike traditional methods that evaluate overlap solely through masks while ignoring activation intensity, our metrics leverage the peak distribution of attention to measure the alignment between prompts and visual regions. In experiments, PV-TAM consistently improves both attention-based and IoU-style localization metrics over answer-side baselines on various datasets.
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.
Vision-Text Compression (VTC) renders long texts into images and encodes them through the vision encoder (ViT), compressing thousands of text tokens into far fewer visual tokens. However, since the ViT is pretrained predominantly on natural images, it captures visual attributes (glyphs, font sizes, layout) rather than linguistic semantics, causing rendered-image representations to diverge from native-text representations. We term this cross-path inconsistency and show, via rendering perturbation experiments, that it is a critical yet overlooked bottleneck of VTC. We propose SPIRAL (Self-improving Path Integration and Realignment), a self-supervised alignment framework that closes this gap using only the model's own text-path behavior as supervision, requiring no external teachers or additional annotations. SPIRAL operates at two complementary granularities: token-level on-policy distillation (OPD) for local faithfulness, and sequence-level preference optimization (DPO) for global coherence. On VTCBench, SPIRAL improves the overall score of Qwen3-VL-8B from 35.10 to 54.02, approaching the native text-input performance (55.60) and outperforming models up to 30x larger. The two granularities exhibit complementary strengths: OPD excels at retrieval and is sample-efficient, while DPO is stronger on reasoning and memory and scales better with data. SPIRAL's benefits also generalize to out-of-domain benchmarks, confirming that effective VTC hinges on aligning rendered-image representations back to native-text semantics.