SOURCE-LINKED INTELLIGENCE

State-Conditioned Visual Evidence Retrieval for Fine-Grained Perception in Document Vision-Language Models

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

Compared with typical vision-language tasks, document parsing places stronger demands on fine-grained visual perception. Existing vision-language model (VLM)-based parsing approaches rely on globally compressed visual tokens, where fine-grained details are entangled within a single representation and repeatedly accessed during decoding. However, we observe that the visual evidence for each prediction is typically localized and conditioned on the current decoding state, whereas such representations must be accessed in full at every decoding step, resulting in inefficient computation. To address

Read original source ↗ Open in workspace

recordType

paper

region

Global