LyapuFlow: Controlling Generative Flows with Lyapunov Feedback for Inverse Problems
cs.LG, stat.ML
Submitted: 2026-10-03
Updated: 2026-10-03
Code: https://github.com/NVlabs/FastGen
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- D-Flow: Differentiating through Flows for Controlled Generation
- A Survey on Diffusion Models for Inverse Problems
- xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism
- Sharpen Your Flow: Sharpness-Aware Sampling for Flow Matching
- Classifier-Free Diffusion Guidance
- SAD-Flower: Flow Matching for Safe, Admissible, and Dynamically Consistent Planning
- Manifold-Aware Perturbations for Constrained Generative Modeling
- Functional Flow Matching
- Fourier Neural Operator for Parametric Partial Differential Equations
- FlowLPS: Langevin-Proximal Sampling for Flow-based Inverse Problem Solvers
- Training Free Guided Flow Matching with Optimal Control
- UniConFlow: A Unified Constrained Flow-Matching Framework for Certified Motion Planning
- ProFlow: Zero-Shot Physics-Consistent Sampling via Proximal Flow Guidance
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks