Research
AREX: Affine-Residual Exponential Integrator for Few-Step Sampling in Flow Matching
arXiv:2610.03483v1 Announce Type: cross Abstract: We introduce AREX, a training-free sampler for pretrained flow matching models that uses the target mean and covariance to capture an analytically tra
arXiv:2610.03483v1 Announce Type: cross Abstract: We introduce AREX, a training-free sampler for pretrained flow matching models that uses the target mean and covariance to capture an analytically tractable part of the sampling dynamics. We show that the velocity field of the moment-matched Gaussian target is the L^2-optimal affine approximation to the marginal velocity field. This motivates decomposition of the learned dynamics into an affine component over the whole sampling path, determined by the first two target moments, and a neural residual term. AREX keeps the affine component and integrates it using an explicit matrix-valued propagator. In turn, we only require to integrate over the residual term. This differs from scalar exponential integrators, which analytically handle only isotropic linear dynamics. Across image and text-to-image generation tasks, AREX consistently improves sample fidelity in the few-step sampling regime without retraining the underlying model.
Related
- Improving Few-Step Language Flows with Untied Self-Conditioning
- MeanVoiceFlow2: Joint Optimization of Mean Flow and Content Encoder for Fast One-Step Zero-Shot Voice Conversion
- Flow-Map GRPO: Reinforcement Learning for Few-Step Flow-Map Generators via Anchored Stochastic Composition
- Contextual Flow Matching: Adaptive Step Selection in Flow Models for Efficient Visual Generation
- Score-Regularized Joint Sampling with Importance Weights for Flow Matching
Source: arXiv cs.AI | 2026-10-05