CAT-Flow: Curvature-Adaptive sTeps for Flow Matching

arXiv:2609.01746 · cs.LG · Submitted 2026-09-01 · Read on arXiv

cs.LG

Submitted: 2026-09-01

Updated: 2026-09-01

Code: https://github.com/discus0434/aesthetic-predictor-v2-5

Terminology

• Flow Matching — 53× in this paper · explained in 7 episodes
• Gradient Flow — 20× in this paper · explained in 2 episodes
• Adam — 5× in this paper · explained in 2 episodes
• Diffusion Model — 5× in this paper · explained in 8 episodes
• Diffusion Models — 5× in this paper · explained in 6 episodes
• Rectified Flow — 5× in this paper · explained in 3 episodes
• Adaptation — 4× in this paper · explained in 1 episode
• Alignment — 3× in this paper · explained in 1 episode
• Generative Model — 3× in this paper · explained in 2 episodes
• Generative Modeling — 3× in this paper · explained in 3 episodes
• Loss Function — 3× in this paper · explained in 2 episodes
• Adaptability — 2× in this paper · explained in 1 episode
• Adaptive Solvers — 2× in this paper · explained in 1 episode
• Generative Models — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Feature Extraction — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Stable Flow: Vital Layers for Training-Free Image Editing
• Training-Free Refinement of Flow Matching with Divergence-based Sampling
• ProbeFlow: Training-Free Adaptive Flow Matching for Vision-Language-Action Models
• Generating Sequences With Recurrent Neural Networks
• Prediction--Loss Alignment for Sampler--Robust Flow Matching Training
• Gotta Go Fast When Generating Data with Score-Based Models
• A study of deep perceptual metrics for image quality assessment
• Isokinetic Flow Matching for Pathwise Straightening of Generative Flows
• Adam: A Method for Stochastic Optimization
• FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space
• Cost-Aware Routing for Efficient Text-To-Image Generation
• Flow Matching Guide and Code
• CurveFlow: Curvature-Guided Flow Matching for Image Generation
• Look-Ahead and Look-Back Flows: Training-Free Image Generation with Trajectory Smoothing
• Adams Bashforth Moulton Solver for Inversion and Editing in Rectified Flow
• Bellman Optimal Stepsize Straightening of Flow-Matching Models
• PromptMoG: Enhancing Diversity in Long-Prompt Image Generation via Prompt Embedding Mixture-of-Gaussian Sampling
• UniFlow-Audio: Unified Flow Matching for Audio Generation from Omni-Modalities

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: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks