Training-Free Refinement of Flow Matching with Divergence-based Sampling

arXiv:2604.04646 · cs.CV, cs.AI · Submitted 2026-04-06 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-04-06

Updated: 2026-09-01

Project page: https://yeonwoo378.github.io/official_fds

Terminology

• alpha — 37× in this paper · explained in 1 episode
• Flow Divergence Sampler — 19× in this paper
• Flow Matching — 15× in this paper · explained in 8 episodes
• Diffusion Model — 13× in this paper · explained in 8 episodes
• Diffusion Models — 13× in this paper · explained in 6 episodes
• Fidelity — 12× in this paper · explained in 2 episodes
• Inverse Problem — 10× in this paper · explained in 2 episodes
• Ablation — 9× in this paper · explained in 1 episode
• Generative Model — 6× in this paper · explained in 2 episodes
• Generative Models — 6× in this paper · explained in 2 episodes
• Steering — 5× in this paper · explained in 2 episodes
• Trace — 5× in this paper · explained in 2 episodes
• Computational overhead — 4× in this paper · explained in 2 episodes
• Core — 4× in this paper · explained in 2 episodes
• Robustness — 4× in this paper · explained in 5 episodes
• Transformer — 4× in this paper · explained in 2 episodes
• Rectified Flow — 3× in this paper · explained in 3 episodes
• Wasserstein Distance — 3× in this paper · explained in 4 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Latent Diffusion Model — 2× in this paper · explained in 2 episodes
• Latent Diffusion Models — 2× in this paper · explained in 2 episodes
• Training-Free Framework — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Conditional Flow Matching — 1× in this paper
• Generalization — 1× in this paper · explained in 13 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Inception Score — 1× in this paper
• Nash Equilibrium — 1× in this paper · explained in 2 episodes

Sources

• Zigzag Diffusion Sampling: Diffusion Models Can Self-Improve via Self-Reflection
• FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models
• Imagen Video: High Definition Video Generation with Diffusion Models
• Make-A-Video: Text-to-Video Generation without Text-Video Data
• SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers
• Towards Hierarchical Rectified Flow

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models