Adaptively Guided Multimodal Conditional Latent Diffusion for Complex Dynamic Systems

In generative AI, diffusion models are state-of-the-art for high resolution representations of highly diverse complex objects. This work presents an adaptively guided multimodal conditional latent diffusion approach which utilizes various modalities of data to generate accurate representations of complex dynamic systems. The approach is demonstrated for generating high resolution dynamics of the 6D phase space of intense charged particle beams in particle accelerators. This talk also discusses how this general diffusion approach can be combined with transformers for a wide range of time-varying complex dynamic systems for science. This talk shows how adaptive feedback incorporated within the architectures of latent diffusion models makes them applicable to time-varying systems such as intense beams in large particle accelerators.