AI RESEARCH

Learning Unbiased Permutations via Flow Matching

arXiv CS.LG

ArXi:2605.16755v1 Announce Type: new Learning permutations is fundamental to sorting, ranking, and matching, but existing differentiable methods based on entropy-regularized Sinkhorn produce a single softened solution and collapse under ambiguity. We present PermFlow, a conditional flow matching framework that operates directly on the affine subspace of matrices with unit row and column sums.