5 papers
ColoDiff: Integrating Dynamic Consistency With Content Awareness for Colonoscopy Video Generation
Junhu Fu, Shuyu Liang, Wutong Li +9
Colonoscopy video generation delivers dynamic, information-rich data critical for diagnosing intestinal diseases, particularly in data-scarce scenarios. High-quality video generati…
VAP-Diffusion: Enriching Descriptions with MLLMs for Enhanced Medical Image Generation
Peng Huang, Junhu Fu, Bowen Guo +3
As the appearance of medical images is influenced by multiple underlying factors, generative models require rich attribute information beyond labels to produce realistic and divers…
Can We Infer Confidential Properties of Training Data from LLMs?
Pengrun Huang, Chhavi Yadav, Kamalika Chaudhuri +1
Large language models (LLMs) are increasingly fine-tuned on domain-specific datasets to support applications in fields such as healthcare, finance, and law. These fine-tuning datas…
Diff-CXR: Report-to-CXR generation through a disease-knowledge enhanced diffusion model
Peng Huang, Bowen Guo, Shuyu Liang +3
Text-To-Image (TTI) generation is significant for controlled and diverse image generation with broad potential applications. Although current medical TTI methods have made some pro…
Chest-Diffusion: A Light-Weight Text-to-Image Model for Report-to-CXR Generation
Peng Huang, Xue Gao, Lihong Huang +4
Text-to-image generation has important implications for generation of diverse and controllable images. Several attempts have been made to adapt Stable Diffusion (SD) to the medical…