paper-with-me

Papers

HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale

2024-06-27 · Junying Chen, Chi Gui, Ruyi Ouyang, Anningzhe Gao, Shunian Chen, Guiming Hardy Chen, Xidong Wang, Ruifei Zhang, Zhenyang Cai, Ke Ji, Guangjun Yu, Xiang Wan, Benyou Wang

The rapid development of multimodal large language models (MLLMs), such as GPT-4V, has led to significant advancements. However, these models still face challenges in medical multimodal capabilities due to limitations in the quantity and quality of medical vision-text data, stemming from data privacy concerns and high annotation costs. While pioneering approaches utilize PubMed's large-scale, de-identified medical image-text pairs to address these limitations, they still fall short due to inherent data noise. To tackle this, we refined medical image-text pairs from PubMed and employed MLLMs (GPT-4V) in an 'unblinded' capacity to denoise and reformat the data, resulting in the creation of the PubMedVision dataset with 1.3 million medical VQA samples. Our validation demonstrates that: (1) PubMedVision can significantly enhance the medical multimodal capabilities of current MLLMs, showing significant improvement in benchmarks including the MMMU Health & Medicine track; (2) manual checks by medical experts and empirical results validate the superior data quality of our dataset compared to other data construction methods. Using PubMedVision, we train a 34B medical MLLM HuatuoGPT-Vision, which shows superior performance in medical multimodal scenarios among open-source MLLMs.

📄 PDF Abstract BibTeX arXiv:2406.19280

Code (1)

freedomintelligence/huatuogpt-vision 공식 구현 pytorch

Tasks

Visual Question Answering (VQA)

Similar Papers 제목 키워드 기반

HuatuoGPT-II, One-stage Training for Medical Adaption of LLMs

2023-11-16 · Junying Chen, Xidong Wang, Ke Ji, Anningzhe Gao 외

Adapting a language model into a specific domain, a.k.a `domain adaption', is a common practice when specialized knowledge, e.g. medicine, is not encapsulated in a general language model like Llama2. The challenge lies i…

Domain AdaptationLanguage ModelingLanguage Modelling

SemiHVision: Enhancing Medical Multimodal Models with a Semi-Human Annotated Dataset and Fine-Tuned Instruction Generation

2024-10-19 · Junda Wang, Yujan Ting, Eric Z. Chen, Hieu Tran 외

Multimodal large language models (MLLMs) have made significant strides, yet they face challenges in the medical domain due to limited specialized knowledge. While recent medical MLLMs demonstrate strong performance in la…

DiagnosticGPUVisual Question Answering (VQA)

HuatuoGPT, towards Taming Language Model to Be a Doctor

2023-05-24 · Hongbo Zhang, Junying Chen, Feng Jiang, Fei Yu 외

In this paper, we present HuatuoGPT, a large language model (LLM) for medical consultation. The core recipe of HuatuoGPT is to leverage both \textit{distilled data from ChatGPT} and \textit{real-world data from doctors} …

Language ModelingLanguage ModellingLarge Language Model

Token-Sparse Medical Multimodal Reasoning via Dual-Stream Reinforcement Learning

2026-06-30 · Kaitao Chen, Weiqian Zhao, Jiamin Wu, Qihao Zheng 외 arxiv

Vision-language models (VLMs) combining reinforcement learning (RL) ignite remarkable progress in multimodal reasoning, yet still struggle with medical images, which typically exhibit extremely sparse visual evidence to …

Reinforcement LearningMultimodal ReasoningQuestion Answering

Benchmarking Direct Preference Optimization for Medical Large Vision-Language Models

2026-01-25 · Dain Kim, Jiwoo Lee, Jaehoon Yun, Yong Hoe Koo 외 arxiv

Large Vision-Language Models (LVLMs) hold significant promise for medical applications, yet their deployment is often constrained by insufficient alignment and reliability. While Direct Preference Optimization (DPO) has …