MintFlow: Minimal Trajectory Intervention for Constrained Flow Matching

arXiv:2610.02260 · cs.AI · Submitted 2026-09-30 · Read on arXiv

cs.AI

Submitted: 2026-09-30

Updated: 2026-09-30

Code: https://github.com/Yebbi/MintFlow

Terminology

• Flow Matching — 1× in this paper · explained in 10 episodes

Sources

• Terminally constrained flow-based generative models from an optimal control perspective
• Functional Flow Matching
• SNAP-FM: Sparse Nonlinear Accelerated Projection for Physics-Constrained Generative Modeling
• Constrained Flow Matching via Lagrangian Dual Flows
• Chance-constrained Flow Matching for High-Fidelity Constraint-aware Generation
• Flow Matching Posterior Sampling: A Training-free Conditional Generation for Flow Matching
• Training Free Guided Flow Matching with Optimal Control
• ProFlow: Zero-Shot Physics-Consistent Sampling via Proximal Flow Guidance

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems