2 papers
cs.LG2026
Structured Coupling for Flow Matching
Xavier Sumba, Carles Balsells-Rodas, Yingzhen Li
Standard flow matching scales well but typically relies on an unstructured source distribution, limiting its ability to learn interpretable latent structure. Latent-variable models…
stat.ML2026
End-to-End Identifiable and Consistent Recurrent Switching Dynamical Systems
Carles Balsells-Rodas, Zhengrui Xiang, Xavier Sumba +1
Learning identifiable representations in deep generative models remains a fundamental challenge, particularly for sequential data with regime-switching dynamics. Existing approache…