AI RESEARCH
Multiscale Supervised Unbalanced Optimal Transport Flow Matching
arXiv CS.LG
•
ArXi:2605.16529v1 Announce Type: new Unbalanced optimal transport (UOT) provides a principled framework for modeling single-cell transitions and birth-death dynamics, but its high computational cost limits scalability to large-scale datasets. Although single-cell data often contain hierarchical annotations and known transition priors, existing UOT approximations rarely exploit this multiscale structure or prior knowledge. We