UniX: Unifying Autoregression and Diffusion for Chest X-Ray Understanding and Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909992655781888 |
|---|---|
| author | Zhang, Ruiheng Yao, Jingfeng Zhao, Huangxuan Yan, Hao He, Xiao Chen, Lei Wei, Zhou Luo, Yong Wang, Zengmao Zhang, Lefei Tao, Dacheng Du, Bo |
| author_facet | Zhang, Ruiheng Yao, Jingfeng Zhao, Huangxuan Yan, Hao He, Xiao Chen, Lei Wei, Zhou Luo, Yong Wang, Zengmao Zhang, Lefei Tao, Dacheng Du, Bo |
| contents | Despite recent progress, medical foundation models still struggle to unify visual understanding and generation, as these tasks have inherently conflicting goals: semantic abstraction versus pixel-level reconstruction. Existing approaches, typically based on parameter-shared autoregressive architectures, frequently lead to compromised performance in one or both tasks. To address this, we present UniX, a next-generation unified medical foundation model for chest X-ray understanding and generation. UniX decouples the two tasks into an autoregressive branch for understanding and a diffusion branch for high-fidelity generation. Crucially, a cross-modal self-attention mechanism is introduced to dynamically guide the generation process with understanding features. Coupled with a rigorous data cleaning pipeline and a multi-stage training strategy, this architecture enables synergistic collaboration between tasks while leveraging the strengths of diffusion models for superior generation. On two representative benchmarks, UniX achieves a 46.1% improvement in understanding performance (Micro-F1) and a 24.2% gain in generation quality (FD-RadDino), using only a quarter of the parameters of LLM-CXR. By achieving performance on par with task-specific models, our work establishes a scalable paradigm for synergistic medical image understanding and generation. Codes and models are available at https://github.com/ZrH42/UniX. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_11522 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | UniX: Unifying Autoregression and Diffusion for Chest X-Ray Understanding and Generation Zhang, Ruiheng Yao, Jingfeng Zhao, Huangxuan Yan, Hao He, Xiao Chen, Lei Wei, Zhou Luo, Yong Wang, Zengmao Zhang, Lefei Tao, Dacheng Du, Bo Computer Vision and Pattern Recognition Despite recent progress, medical foundation models still struggle to unify visual understanding and generation, as these tasks have inherently conflicting goals: semantic abstraction versus pixel-level reconstruction. Existing approaches, typically based on parameter-shared autoregressive architectures, frequently lead to compromised performance in one or both tasks. To address this, we present UniX, a next-generation unified medical foundation model for chest X-ray understanding and generation. UniX decouples the two tasks into an autoregressive branch for understanding and a diffusion branch for high-fidelity generation. Crucially, a cross-modal self-attention mechanism is introduced to dynamically guide the generation process with understanding features. Coupled with a rigorous data cleaning pipeline and a multi-stage training strategy, this architecture enables synergistic collaboration between tasks while leveraging the strengths of diffusion models for superior generation. On two representative benchmarks, UniX achieves a 46.1% improvement in understanding performance (Micro-F1) and a 24.2% gain in generation quality (FD-RadDino), using only a quarter of the parameters of LLM-CXR. By achieving performance on par with task-specific models, our work establishes a scalable paradigm for synergistic medical image understanding and generation. Codes and models are available at https://github.com/ZrH42/UniX. |
| title | UniX: Unifying Autoregression and Diffusion for Chest X-Ray Understanding and Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.11522 |