paper-with-me

홈 › Papers

Ryze: Evidence-Enriched Data Synthesis from Biomedical Papers

2026-05-30 · Yeqi Huang, Yue Chen, Yanwei Ye, Guanhao Su, Luo Mai arxiv

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.

📄 PDF Abstract BibTeX arXiv:2606.00902

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Biomedical reasoning in action: Multi-agent System for Auditable Biomedical Evidence Synthesis

2025-10-06 · Oskar Wysocki, Magdalena Wysocka, Mauricio Jacobo, Harriet Unsworth 외 arxiv

We present M-Reason, a demonstration system for transparent, agent-based reasoning and evidence integration in the biomedical domain, with a focus on cancer research. M-Reason leverages recent advances in large language …

Automating Biomedical Evidence Synthesis: RobotReviewer

2017-07-01 · ACL 2017 7 · Iain Marshall, Jo{\"e}l Kuiper, Edward Banner, Byron C. Wallace

Query-driven Document-level Scientific Evidence Extraction from Biomedical Studies

2025-05-09 · Massimiliano Pronesti, Joao Bettencourt-Silva, Paul Flanagan, Alessandra Pascale 외

Extracting scientific evidence from biomedical studies for clinical research questions (e.g., Does stem cell transplantation improve quality of life in patients with medically refractory Crohn's disease compared to place…

RetrievalRetrieval-augmented Generation

A Review on Scientific Knowledge Extraction using Large Language Models in Biomedical Sciences

2024-12-04 · Gabriel Lino Garcia, João Renato Ribeiro Manesco, Pedro Henrique Paiola, Lucas Miranda 외

The rapid advancement of large language models (LLMs) has opened new boundaries in the extraction and synthesis of medical knowledge, particularly within evidence synthesis. This paper reviews the state-of-the-art applic…

RAGRetrieval-augmented Generation

AutoForest: Automatically Generating Forest Plots from Biomedical Studies with End-to-End Evidence Extraction and Synthesis

2026-06-01 · Massimiliano Pronesti, Angelo Miculescu, Mohsin Kapdi, Paul Flanagan 외 arxiv

Systematic reviews rely on forest plots to synthesise quantitative evidence across biomedical studies, but generating them remains a fragmented and labour-intensive process. Researchers must interpret complex clinical te…