In this talk, we present a model-independent analysis based on a latent diffusion model to address the flavor structure of leptons. The latent diffusion model combines a diffusion model with a variational autoencoder as a generative AI framework. By generating a wide variety of parameter sets consistent with experimental observations, we find non-trivial features characterizing lepton flavor...
Searches for BSM Physics have produced many theoretical ideas, but only a few can be directly tested at the LHC. Reinterpreting existing results is therefore essential for constraining a wider range of models. Independent of the specific reinterpretation method, the final step always involves statistical analysis and hypothesis testing. Accurate tests require detailed information on...
Recent studies actively apply machine learning to the exploration of flavor physics. In analyzing the flavor structure of the lepton sector, we apply reinforcement learning to a $U(1)$ flavor model with $L_{e}-L_{mu}-L_{tau}$ charges. By testing multiple architectures to explore charge combinations, we develop a strategy to efficiently achieve high-precision solutions. It turns out that the...
