Lorentz-regularized interpretable VAE for multi-scale single-cell transcriptomic and epigenomic embeddings

LiVAE provides a robust, general-purpose framework for single-cell representation learning that resolves the local-global trade-off through geometric regularization. By maintaining Euclidean latent spaces while leveraging hyperbolic priors, LiVAE enables improved developmental trajectory inference and mechanistic biological discovery without sacrificing compatibility with existing computational ecosystems.