flow-maps

The paper introduces Wasserstein-Tilted Flow Maps (WTF), a simulation-free reinforcement learning algorithm for fine-tuning flow-based generative models to enhance reward alignment, achieving higher rewards with up to 280x less compute than baselines.

This paper introduces SGFlow, a method for learning flow maps for diffusion models that avoids invertibility constraints and backpropagation through model iterations, achieving competitive FID scores on CIFAR with a proven stationary-point guarantee.