cs.LGNov 12, 2026

Manifold Attracting Flow Matching: Physics-Constrained Sampling via Continuous Geometric Dynamics

Authors: Guanyu Chen, Jinchen Wang, Shengze Xu, Xingyu Ren, Tieyong Zeng, Antonios Armaou, Dong Ni

Organizations: Zhejiang University · University of California, Los Angeles · The Chinese University of Hong Kong · Pennsylvania State University

Abstract

Generating scientific data under previously unseen equality constraints requires satisfying the prescribed constraints without destroying the physical structure learned from data. Existing inference-time approaches often enforce physical constraints by repeatedly correcting predicted endpoints, but such discrete corrections can distort learned generative structure and introduce unstable feedback. In this work, we propose Manifold Attracting Flow Matching (MAFM), which continuously evolves a persistent anchor through an ODE whose dynamics drive it analytically toward the constraint manifold. Specifically, its geometric correction preserves model-guided tangent motion while prescribing the normal motion to contract constraint violations toward the manifold. This construction separates model tracking from constraint attraction and provides theoretical guarantees for residual contraction and local feedback stabilization. Experiments across geometric and partial differential equation benchmarks demonstrate improved generation quality over variant constraint-guided baselines while maintaining low constraint residuals. MAFM provides a flexible framework for coordinating learned physical structure and explicit constraints through controllable sampling dynamics, without retraining the underlying generative model.

Figures & tables

Appendix figures & tables24 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Constraint-Aware Flow Matching: Decision Aligned End-to-End Training for Constrained Sampling

    May 12, 2026Jacob K. Christopher, James E. Warner, Ferdinando FiorettoConstrained Generative ModelingFlow Matching

  2. MintFlow: Minimal Trajectory Intervention for Constrained Flow Matching

    Sep 30, 2026Yesom Park, Kelvin Kan, Qifan Chen +3constrained flow matchingConstrained Generative Modeling