@inproceedings{huang-etal-2026-ryze,
    title = "Ryze: Evidence-Enriched Data Synthesis from Biomedical Papers",
    author = "Huang, Yeqi  and
      Chen, Yue  and
      Ye, Yanwei  and
      Su, Guanhao  and
      Mai, Luo",
    editor = "Durrett, Greg  and
      Jian, Ping",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 3: System Demonstrations)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-demo.73/",
    pages = "743--749",
    ISBN = "979-8-89176-392-0",
    abstract = "General-purpose VLMs remain unreliable for biomedical research because valid answers in scientific papers depend on evidence split across figures, tables, charts, captions, and referring text.Existing post-training pipelines are bottlenecked by costly expert annotation and by synthetic data that drops this evidence structure.We present Ryze, a fully automated system that converts raw biomedical papers into an \textit{evidence-enriched} training set and a domain-specialized VLM.Ryze synthesizes QA pairs with complete supporting evidence (visual element, caption, extracted structure, and referring paragraphs), reduces layout and OCR errors via chart/table-aware extraction and LLM-based cleansing, and applies a two-stage post-training strategy combining supervised fine-tuning with reinforcement learning.Starting from Qwen3-VL-8B, Ryze produces BioVLM-8B at under {\$}200, achieving 48.0{\%} weighted accuracy on LAB-Bench{---}outperforming the base model by +12.6{\%} and surpassing GPT-5.2 by +3.8{\%}.We release Ryze as open source together with the trained BioVLM-8B model."
}