Pith. sign in

REVIEW 8 cited by

BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Tasks

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.17100 v4 pith:KGQDAYMY submitted 2023-05-26 cs.CL cs.AI

Kai Zhang , Rong Zhou , Eashan Adhikarla , Zhiling Yan , Yixin Liu , Jun Yu , Zhengliang Liu , Xun Chen
show 15 more authors
Brian D. Davison Hui Ren Jing Huang Chen Chen Yuyin Zhou Sunyang Fu Wei Liu Tianming Liu Xiang Li Yong Chen Lifang He James Zou Quanzheng Li Hongfang Liu Lichao Sun
This is my paper · ORCID
classification cs.CLcs.AI
keywords biomedgptbiomedicalgeneralistdiversemodeltasksabilityanswering
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Traditional biomedical artificial intelligence (AI) models, designed for specific tasks or modalities, often exhibit limited flexibility in real-world deployment and struggle to utilize holistic information. Generalist AI holds the potential to address these limitations due to its versatility in interpreting different data types and generating tailored outputs for diverse needs. However, existing biomedical generalist AI solutions are typically heavyweight and closed source to researchers, practitioners, and patients. Here, we propose BiomedGPT, the first open-source and lightweight vision-language foundation model, designed as a generalist capable of performing various biomedical tasks. BiomedGPT achieved state-of-the-art results in 16 out of 25 experiments while maintaining a computing-friendly model scale. We also conducted human evaluations to assess the capabilities of BiomedGPT in radiology visual question answering, report generation, and summarization. BiomedGPT exhibits robust prediction ability with a low error rate of 3.8% in question answering, satisfactory performance with an error rate of 8.3% in writing complex radiology reports, and competitive summarization ability with a nearly equivalent preference score to human experts. Our method demonstrates that effective training with diverse data can lead to more practical biomedical AI for improving diagnosis and workflow efficiency.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 52 citations worldwide. Full citation record

  1. HSCR: Hierarchical Self-Contrastive Rewarding for Aligning Medical Vision Language Models

    cs.CV 2025-06 conditional novelty 6.0 of 10

    HSCR uses visual token dropout and logit contrast to construct self-generated dispreferred answers, then trains a medical VLM with explicit and implicit preference losses, improving zero-shot Rad-VQA, SLAKE, and PathV...

  2. Modular Foundation Models for Time-Series Perception in Digital Twins

    cs.LG 2026-07 conditional novelty 5.0 of 10

    A gated bank of frozen self-supervised time-series encoders, aligned and aggregated by a Transformer, supports competitive multi-task perception for digital twins and hydro-generator virtual sensing.

  3. Knowing or Guessing? Robust Medical Visual Question Answering via Joint Consistency and Contrastive Learning

    cs.CL 2025-08 conditional novelty 5.0 of 10

    RoMed and CCL: a 144k-question perturbation benchmark for medical VQA and a consistency-plus-contrastive training method that improves LLaVA-Med's accuracy and reduces answer variation.

  4. Inference-Time Agentic Decision Rules Beat Longer Evolving Search for Multi-Image Medical Reasoning

    cs.CV 2026-07 conditional novelty 4.0 of 10

    On MedFrameQA, order-vote (57.89%) beats fixed prompting (52.73%) and order-rerank (55.79%), and a single 100-generation run drops final-test accuracy to 56.02%.

  5. DobicVLM: Aligning Chest X-Ray Report Generation with Clinically-Grounded Programmatic Rewards via Group Relative Policy Optimization

    cs.CV 2026-07 conditional novelty 4.0 of 10

    A GRPO-tuned medical VLM using rule-based rewards reaches 27.2% expert acceptance for diagnostic impression accuracy on 69 CXR cases, barely beating its base model and clearly beating a generalist Gemini baseline.

  6. Deep Learning for Semen Analysis in Male Infertility: Computer Vision, Multimodal Fusion, and Clinical Translation

    cs.CV 2026-07 accept novelty 4.0 of 10

    A comprehensive review synthesizing AI-driven sperm analysis across computer vision tasks, multimodal fusion, and a staged clinical translation roadmap.

  7. MIRA: A Novel Framework for Fusing Modalities in Medical RAG

    cs.CV 2025-07 reject novelty 4.0 of 10

    A medical multimodal RAG pipeline with rethink-and-rearrange and online search; the claimed SOTA is contradicted by the paper's own PMC-VQA numbers.

  8. Improving TCM Question Answering through Tree-Organized Self-Reflective Retrieval with LLMs

    cs.CL 2025-02 conditional novelty 4.0 of 10

    A tree-organized, self-reflective retrieval framework over a TCM knowledge base lifts GPT-4 accuracy on a 600-question licensing-exam sample by 19.85 absolute percentage points.

Pith tools