{"ID":2922200,"CreatedAt":"2026-06-02T02:42:49.606572591Z","UpdatedAt":"2026-06-02T21:47:10.793334713Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.00902","arxiv_id":"2606.00902","title":"Ryze: Evidence-Enriched Data Synthesis from Biomedical Papers","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 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 progress-gated post-training strategy combining supervised fine-tuning with reinforcement learning. Starting from Qwen3-VL-8B, Ryze produces BioVLM-8B at under USD 200, achieving 48.0% weighted accuracy on LAB-Bench, outperforming the base model by +12.6 percentage points (pp) and surpassing GPT-5.2 by +3.8 pp. We release Ryze as open source together with the trained BioVLM-8B model.","short_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 st...","url_abs":"https://arxiv.org/abs/2606.00902","url_pdf":"https://arxiv.org/pdf/2606.00902v1","authors":"[\"Yeqi Huang\",\"Yue Chen\",\"Yanwei Ye\",\"Guanhao Su\",\"Luo Mai\"]","published":"2026-05-30T21:54:02Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\"]","has_code":false}