Generalization and Memorization in Rectified Flow
cs.LG, cs.CV
Submitted: 2026-03-12
Updated: 2026-08-29
Code: https://github.com/mx-ethan-rao/rf_gen_mem
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Building Normalizing Flows with Stochastic Interpolants
- Why Diffusion Models Don't Memorize: The Role of Implicit Dynamical Regularization in Training
- Differentially Private Diffusion Models
- A Probabilistic Fluctuation based Membership Inference Attack for Diffusion Models
- Likelihood-based Out-of-Distribution Detection with Denoising Diffusion Probabilistic Models
- FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models
- On Memorization in Diffusion Models
- LOGAN: Membership Inference Attacks Against Generative Models
- Generalization in diffusion models arises from geometry-adaptive harmonic representations
- Auto-Encoding Variational Bayes
- An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization
- Flow Matching for Generative Modeling
- Flow Matching Guide and Code
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- Locality in Image Diffusion Models Emerges from Data Statistics
- Do Deep Generative Models Know What They Don't Know?
- Multisample Flow Matching: Straightening Flows with Minibatch Couplings
- Latent Diffusion Inversion Requires Understanding the Latent Space
- Score-based Membership Inference on Diffusion Models
- Input complexity and out-of-distribution detection with likelihood-based generative models
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