Constrained Flow Matching via Lagrangian Dual Flows

Excerpt

arXiv:2607.04513v2 Announce Type: replace-cross Abstract: Flow matching is a powerful tool for generative modeling, but emerging applications in robotics, planning, and control require inference-time constraints on generated outputs. Such constraints are often complex and highly nonlinear. As a result, methods designed for linear constraints like image inpainting are rarely sufficient, and projection or optimization-based alternatives can be prohibitively expensive. In this paper, we introduce L