SOURCE-LINKED INTELLIGENCE

Closing Cost-Quality Gap in Document VLMs: Difficulty-Aware Data Curation and Quality-Adjusted Deployment Economics

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Extracting structured fields from hundreds of millions of documents annually remains costly in regulated industries: bespoke OCR cascades cover only a fraction of workflows, privacy rules preclude external models, and existing open-source VLMs that clear quality thresholds cost more to serve than human annotation. We present a deployed document-understanding system built on a Mixture-of-Experts VLM (35B total, 3B active), fine-tuned on in-house production data mixed with open-domain documents curated by a Difficulty-Aware pipeline for layout diversity, fact-extractability, and cross-model cons

Read original source ↗ Open in workspace

recordType

paper

region

Global