AI RESEARCH

StrEBM: A Structured Latent Energy-Based Model for Blind Source Separation

arXiv CS.LG

ArXi:2604.17381v1 Announce Type: cross This paper proposes StrEBM, a structured latent energy-based model for source-wise structured representation learning. The framework is motivated by a broader goal of promoting identifiable and decoupled latent organization by assigning different latent dimensions their own learnable structural biases, rather than cons