SigLip-NaViT

<div style="display: flex; align-items: center; justify-content: center;"> <h1 style="margin: 0; text-align: left;"> Hulu-Med: A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding </h1> </div> <div align="center">

📄 Paper | 🤗 Hulu-Med-7B |🤗 Hulu-Med-14B |🤗 Hulu-Med-32B | 🔮 ModelScope Models | 📊 Demo

</div>

🔥 News

• [2025-10-08] Hulu-Med models and inference code released!

📖 Overview

Hulu-Med is a transparent medical vision-language model that unifies understanding across diverse modalities including medical text, 2D/3D images, and videos. Built with a focus on transparency and accessibility, Hulu-Med achieves state-of-the-art performance on 30 medical benchmarks while being trained entirely on public data.

Key Features

• 🌟 Holistic Multimodal Understanding: Seamlessly processes medical text, 2D images, 3D volumes, and surgical videos
• 🔓 Fully Transparent: Complete open-source pipeline including data curation, training code, and model weights
• 📊 State-of-the-Art Performance: Outperforms leading open-source models and competes with proprietary systems
• ⚡ Efficient Training: Only 4,000-40,000 GPU hours required for 7B-32B variants
• 🗂️ Comprehensive Coverage: Trained on 16.7M samples spanning 12 anatomical systems and 14 imaging modalities

Comprehensive Data Coverage

Our training corpus encompasses:

• 12 Major Anatomical Systems: Multi-System, Skin/Integumentary, Respiratory, Cellular/Tissue Level, Digestive, Nervous, Cardiovascular, Musculoskeletal, Reproductive, Urinary, Whole Body, Endocrine, Immune/Lymphatic, and Hematologic systems
• 14 Medical Imaging Modalities: CT, MRI, X-Ray, Ultrasound, PET, OCT, Endoscopy, Microscopy, Histopathology, Fundus, Dermoscopy, Angiography, Digital Photograph, and Medical Chart
• Diverse Downstream Tasks: Medical Dialogue, Anomaly Detection, Prognosis Prediction, Treatment Planning, Surgical Skill Assessment, Education, Medical Report Generation, Surgical Phase Recognition, Medical Computation, and more

🏆 Performance Highlights

Medical Multimodal Benchmarks

Performance comparison on medical multimodal benchmarks (For the 'Medical VLM < 10B' subgroup, bold indicates the best method):

Medical Text Benchmarks

Performance comparison on medical text benchmarks (bold indicates the best method in each subgroup):

🚀 Model Zoo

We provide three model variants with different parameter scales:

🛠️ Installation

# Clone the repository
git clone https://github.com/your-org/Hulu-Med.git
cd Hulu-Med
# Create conda environment
conda create -n hulumed python=3.10
conda activate hulumed
# PyTorch and torchvision for CUDA 11.8
pip install torch==2.4.0 torchvision==0.19.0 --extra-index-url https://download.pytorch.org/whl/cu118
# Flash-attn pinned to a compatible version
pip install flash-attn==2.7.3 --no-build-isolation --upgrade
# Transformers and accelerate
pip install transformers==4.51.2 accelerate==1.7.0
# Video processing dependencies
pip install decord ffmpeg-python imageio opencv-python
# Install other dependencies
pip install -r requirements.txt

💻 Quick Start

2D Example

import torch
from transformers import AutoModelForCausalLM, AutoProcessor
from hulumed import disable_torch_init, model_init, mm_infer
from hulumed import disable_torch_init, model_init, mm_infer
from hulumed.model import load_pretrained_model
from hulumed.mm_utils import load_images, process_images, load_video, process_video, tokenizer_multimodal_token, get_model_name_from_path, KeywordsStoppingCriteria
from hulumed.model.processor import HulumedProcessor
import os
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
model_path = "xxxxxx"
model_name = get_model_name_from_path(model_path)
tokenizer, model, image_processor, context_len = load_pretrained_model(model_path, None, model_name,device_map='cuda:0')
processor = HulumedProcessor(image_processor, tokenizer)
slices = load_images(
    "./demo/demo.jpg", 
)
conversation = [
        {
            "role": "user",
            "content": [
               {"type": "image"},
                {"type": "text", "text": "Describe this image in detail."},
            ]
        }
    ]
modal='image'
model=model.to("cuda:0")
inputs = processor(
        images=[slices] if modal != "text" else None,
        text=conversation,
        merge_size=2 if modal == "video" else 1,
        return_tensors="pt"
        )
inputs = {k: v.cuda().to('cuda:0') if isinstance(v, torch.Tensor) else v for k, v in inputs.items()}
if "pixel_values" in inputs:
    inputs["pixel_values"] = inputs["pixel_values"].to(torch.bfloat16)
with torch.inference_mode():
        output_ids = model.generate(
            **inputs,
            do_sample=True,
            modals=[modal],
            temperature=0.6,
            max_new_tokens=8192,
            use_cache=True,
            pad_token_id=tokenizer.eos_token_id,
        )
outputs = tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0].strip()
print(outputs)

3D Example

slices = load_images(
    "./src/demo/amos_0013.nii", ##Support nii 3D input
    nii_num_slices=160      
)
conversation = [
        {
            "role": "user",
            "content": [
               {"type": "video", "num_frames": len(slices)},
                {"type": "text", "text": "This is a medical 3D scenario. Please generate a medical report for the given 3D medical images, including both findings and impressions."},
            ]
        }
    ]
modal='video'
model=model.to("cuda:0")
inputs = processor(
        images=[slices] if modal != "text" else None,
        text=conversation,
        merge_size=2 if modal == "video" else 1,
        return_tensors="pt"
        )
inputs = {k: v.cuda().to('cuda:0') if isinstance(v, torch.Tensor) else v for k, v in inputs.items()}
if "pixel_values" in inputs:
    inputs["pixel_values"] = inputs["pixel_values"].to(torch.bfloat16)
with torch.inference_mode():
        output_ids = model.generate(
            **inputs,
            do_sample=True,
            modals=[modal],
            temperature=0.6,
            max_new_tokens=8192,
            use_cache=True,
            pad_token_id=tokenizer.eos_token_id,
        )
outputs = tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0].strip()
print(outputs)

Video Example

frames, timestamps = load_video("./src/demo/1min_demo.mp4", fps=1, max_frames=3000)
conversation = [
        {
            "role": "user",
            "content": [
               {"type": "video", "num_frames": len(frames)},
                {"type": "text", "text": "Please describe this video in detail."},
            ]
        }
    ]
modal='video'
model=model.to("cuda:0")
inputs = processor(
        images=[frames] if modal != "text" else None,
        text=conversation,
        merge_size=2 if modal == "video" else 1,
        return_tensors="pt"
        )
inputs = {k: v.cuda().to('cuda:0') if isinstance(v, torch.Tensor) else v for k, v in inputs.items()}
if "pixel_values" in inputs:
    inputs["pixel_values"] = inputs["pixel_values"].to(torch.bfloat16)
with torch.inference_mode():
        output_ids = model.generate(
            **inputs,
            do_sample=True,
            modals=[modal],
            temperature=0.6,
            max_new_tokens=8192,
            use_cache=True,
            pad_token_id=tokenizer.eos_token_id,
        )
outputs = tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0].strip()
print(outputs)

Text Example

conversation = [
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Hello, I have a headache, what should I do?"},
            ]
        }
    ]
modal='text'
model=model.to("cuda:0")
inputs = processor(
        text=conversation,
        merge_size=2 if modal == "video" else 1,
        return_tensors="pt"
        )
inputs = {k: v.cuda().to('cuda:0') if isinstance(v, torch.Tensor) else v for k, v in inputs.items()}
if "pixel_values" in inputs:
    inputs["pixel_values"] = inputs["pixel_values"].to(torch.bfloat16)
with torch.inference_mode():
        output_ids = model.generate(
            **inputs,
            do_sample=True,
            modals=[modal],
            temperature=0.6,
            max_new_tokens=8192,
            use_cache=True,
            pad_token_id=tokenizer.eos_token_id,
        )
outputs = tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0].strip()
print(outputs)

📊 Training

Data Preparation

Our training data consists of 16.7M samples across four categories:

• Medical Multimodal Data (9M samples): Covering 14 imaging modalities
• Medical Text Data (4.9M samples): Clinical notes, literature, QA pairs
• General Multimodal Data (1.3M samples): Enhancing generalization
• General Text Data (1.5M samples): Improving reasoning capabilities

Download and prepare the data: Comming soon

🏗️ Model Architecture

Hulu-Med consists of four core components:

1. Vision Encoder: SigLIP-based encoder with 2D RoPE for unified 2D/3D/video processing
2. Multimodal Projector: Projects visual tokens into language model space
3. LLM Decoder: Qwen-based decoder for generating responses
4. Medical-Aware Token Reduction: Efficient processing with ~55% token reduction

📋 Supported Tasks

• ✅ Visual Question Answering (2D/3D/Video)
• ✅ Medical Report Generation
• ✅ Disease Diagnosis
• ✅ Anatomical Understanding
• ✅ Surgical Phase Recognition
• ✅ Clinical Dialogue
• ✅ Medical Text Reasoning
• ✅ Multilingual Medical QA
• ✅ Rare Disease Diagnosis
• More

📄 Citation

If you find Hulu-Med useful in your research, please cite:

@misc{jiang2025hulumedtransparentgeneralistmodel,
      title={Hulu-Med: A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding}, 
      author={Songtao Jiang and Yuan Wang and Sibo Song and Tianxiang Hu and Chenyi Zhou and Bin Pu and Yan Zhang and Zhibo Yang and Yang Feng and Joey Tianyi Zhou and Jin Hao and Zijian Chen and Ruijia Wu and Tao Tang and Junhui Lv and Hongxia Xu and Hongwei Wang and Jun Xiao and Bin Feng and Fudong Zhu and Kenli Li and Weidi Xie and Jimeng Sun and Jian Wu and Zuozhu Liu},
      year={2025},
      eprint={2510.08668},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2510.08668}, 
}

📜 License

This project is released under the Apache 2.0 License.

---

<div align="center"> Made with ❤️ by the ZJU AI4H Team </div>