AI RESEARCH
Annealed Co-Generation: Disentangling Variables via Progressive Pairwise Modeling
arXiv CS.LG
•
ArXi:2603.06615v1 Announce Type: new For multivariate co-generation in scientific applications, we advocate pairwise block rather than joint modeling of all variables. This design mitigates the computational burden and data imbalance. To this end, we propose an Annealed Co-Generation (ACG) framework that replaces high-dimensional diffusion modeling with a low-dimensional diffusion model, which enables multivariate co-generation by composing pairwise variable generations. We first train an unconditional diffusion model over causal variables that are disentangled into pairs.