Constrained Flow Matching via Lagrangian Dual Flows

arXiv:2607.04513 · math.OC, cs.LG · Submitted 2026-07-05 · Read on arXiv

math.OC, cs.LG

Submitted: 2026-07-05

Updated: 2026-09-30

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Flow Matching — 3× in this paper · explained in 15 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes

Sources

• A Differentiable Interior-Point Method in Single Precision
• $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
• SafeFlow: Safe Robot Motion Planning with Flow Matching via Control Barrier Functions
• D4RL: Datasets for Deep Data-Driven Reinforcement Learning
• Generative Predictive Control: Flow Matching Policies for Dynamic and Difficult-to-Demonstrate Tasks
• HardFlow: Hard-Constrained Sampling for Flow-Matching Models via Trajectory Optimization
• Improving Diffusion Models for Inverse Problems Using Optimal Posterior Covariance
• UniConFlow: A Unified Constrained Flow-Matching Framework for Certified Motion Planning

Related papers

• Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise
• Adam-HNAG: A Convergent Reformulation of Adam with Accelerated Rate
• Incremental Learning in Mirror Flows
• Beyond Aggregate Drift: Optimal Client-Specific Windows in Federated Learning
• Lower Bounds for Randomized Linear-Oracle Optimization over Strongly Convex Sets
• Second-Order Optimization with Asynchronous Curvature