Generalization and Memorization in Rectified Flow

• URL: http://arxiv.org/abs/2603.13421v1
• Date: Thu, 12 Mar 2026 21:10:39 GMT
• Title: Generalization and Memorization in Rectified Flow
• Abstract summary: Generative models based on the Flow Matching objective, particularly Rectified Flow, have emerged as a dominant paradigm for efficient, high-fidelity image synthesis.<n>We investigate the memorization behaviors of RF through the test statistics of Membership Inference Attacks (MIA)<n>We show that replacing uniform timestep sampling with a Symmetric Exponential (U-shaped) distribution effectively minimizes exposure to vulnerable intermediate timesteps.
• Score: 2.230929655489877
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative models based on the Flow Matching objective, particularly Rectified Flow, have emerged as a dominant paradigm for efficient, high-fidelity image synthesis. However, while existing research heavily prioritizes generation quality and architectural scaling, the underlying dynamics of how RF models memorize training data remain largely underexplored. In this paper, we systematically investigate the memorization behaviors of RF through the test statistics of Membership Inference Attacks (MIA). We progressively formulate three test statistics, culminating in a complexity-calibrated metric ($T_\text{mc\_cal}$) that successfully decouples intrinsic image spatial complexity from genuine memorization signals. This calibration yields a significant performance surge -- boosting attack AUC by up to 15\% and the privacy-critical TPR@1\%FPR metric by up to 45\% -- establishing the first non-trivial MIA specifically tailored for RF. Leveraging these refined metrics, we uncover a distinct temporal pattern: under standard uniform temporal training, a model's susceptibility to MIA strictly peaks at the integration midpoint, a phenomenon we justify via the network's forced deviation from linear approximations. Finally, we demonstrate that substituting uniform timestep sampling with a Symmetric Exponential (U-shaped) distribution effectively minimizes exposure to vulnerable intermediate timesteps. Extensive evaluations across three datasets confirm that this temporal regularization suppresses memorization while preserving generative fidelity.

Related papers

• Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning [8.422673935994451]
  consistency distillation has significantly accelerated the inference of diffusion models.<n>We propose Curvature-Adaptive Consistency Flow Matching to address the limitations of static sampling.<n>Our approach achieves new state-of-the-art results on large-scale models such as FLUX and SDXL.
  arXiv  Detail & Related papers  (2026-06-21T08:49:50Z)
• Fast and Scalable Analytical Diffusion [43.4234198410875]
  Analytical diffusion models offer a mathematically transparent path to generative modeling by formulating the denoising score as an empirical-Bayes posterior mean.<n>Standard formulation requires a full-dataset scan at every timestep, scaling linearly with dataset size.<n>We propose Dynamic Time-Aware Golden Subset Diffusion (GoldDiff), a training-free framework that decouples inference from dataset size.
  arXiv  Detail & Related papers  (2026-02-18T14:41:09Z)
• The Stationarity Bias: Stratified Stress-Testing for Time-Series Imputation in Regulated Dynamical Systems [0.098314893665023]
  Time-series imputation benchmarks use random masking and shape-agnostic metrics.<n>We formalize this bias and propose a emphStratified Stress-Test that partitions evaluation into Stationary and Transient regimes.
  arXiv  Detail & Related papers  (2026-02-17T15:05:56Z)
• Temper-Then-Tilt: Principled Unlearning for Generative Models through Tempering and Classifier Guidance [51.532841645285835]
  We study machine unlearning in large generative models by framing the task as density ratio estimation to a target distribution.<n>We show it can fail to faithfully unlearn with finite samples when the forget set represents a sharp, concentrated data distribution.<n>We introduce Temper-Then-Tilt Unlearning (T3-Unlearning), which freezes the base model and applies a two-step inference procedure.
  arXiv  Detail & Related papers  (2026-02-10T19:08:40Z)
• Is Flow Matching Just Trajectory Replay for Sequential Data? [46.770624059457724]
  Flow matching (FM) is increasingly used for time-series generation.<n>It is not well understood whether it learns a general dynamical structure or simply performs an effective "trajectory replay"<n>We show that the implied sampler is an ODE whose dynamics constitutes a nonparametric, memory-augmented continuous-time dynamical system.
  arXiv  Detail & Related papers  (2026-02-09T06:48:45Z)
• Low-Dimensional Adaptation of Rectified Flow: A New Perspective through the Lens of Diffusion and Stochastic Localization [59.04314685837778]
  Rectified flow (RF) has gained considerable popularity due to its generation efficiency and state-of-the-art performance.<n>In this paper, we investigate the degree to which RF automatically adapts to the intrinsic low dimensionality of the support of the target distribution to accelerate sampling.<n>We show that, using a carefully designed choice of the time-discretization scheme and with sufficiently accurate drift estimates, the RF sampler enjoys an complexity of order $O(k/varepsilon)$.
  arXiv  Detail & Related papers  (2026-01-21T22:09:27Z)
• Bifidelity Karhunen-Loève Expansion Surrogate with Active Learning for Random Fields [0.4899818550820576]
  We present a bifidelity Karhunen-Loeve expansion (KLE) surrogate model for field-valued quantities of interest (QoIs) under uncertain inputs.<n>We form an active learning strategy that adaptively selects new HF evaluations based on the surrogate's generalization error.<n>New HF samples are then acquired by maximizing an expected improvement criterion, targeting regions of high surrogate error.
  arXiv  Detail & Related papers  (2025-11-05T04:14:44Z)
• Scalable, Explainable and Provably Robust Anomaly Detection with One-Step Flow Matching [14.503330877000758]
  Time-Conditioned Contraction Matching is a novel method for semi-supervised anomaly detection in tabular data.<n>It is inspired by flow matching, a recent generative modeling framework that learns velocity fields between probability distributions.<n>Extensive experiments on the ADBench benchmark show that TCCM strikes a favorable balance between detection accuracy and inference cost.
  arXiv  Detail & Related papers  (2025-10-21T06:26:38Z)
• RAAG: Ratio Aware Adaptive Guidance [9.525432706814675]
  Flow-based generative models have achieved remarkable progress.<n>Applying a strong, fixed guidance scale throughout inference is poorly suited for the rapid, few-step sampling required by modern applications.<n>We propose a simple, theoretically grounded, adaptive guidance schedule that automatically dampens the guidance scale at early steps based on the evolving ratio.
  arXiv  Detail & Related papers  (2025-08-05T13:41:05Z)
• Solving Inverse Problems with FLAIR [68.87167940623318]
  We present FLAIR, a training-free variational framework that leverages flow-based generative models as prior for inverse problems.<n>Results on standard imaging benchmarks demonstrate that FLAIR consistently outperforms existing diffusion- and flow-based methods in terms of reconstruction quality and sample diversity.
  arXiv  Detail & Related papers  (2025-06-03T09:29:47Z)
• Re-Visible Dual-Domain Self-Supervised Deep Unfolding Network for MRI Reconstruction [48.30341580103962]
  We propose a novel re-visible dual-domain self-supervised deep unfolding network to address these issues.<n>We design a deep unfolding network based on Chambolle and Pock Proximal Point Algorithm (DUN-CP-PPA) to achieve end-to-end reconstruction.<n> Experiments conducted on the fastMRI and IXI datasets demonstrate that our method significantly outperforms state-of-the-art approaches in terms of reconstruction performance.
  arXiv  Detail & Related papers  (2025-01-07T12:29:32Z)
• Detecting Anomalies in Dynamic Graphs via Memory enhanced Normality [39.476378833827184]
  Anomaly detection in dynamic graphs presents a significant challenge due to the temporal evolution of graph structures and attributes. We introduce a novel spatial- temporal memories-enhanced graph autoencoder (STRIPE) STRIPE significantly outperforms existing methods with 5.8% improvement in AUC scores and 4.62X faster in training time.
  arXiv  Detail & Related papers  (2024-03-14T02:26:10Z)
• Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach [49.995833831087175]
  This work proposes a novel method for generating generic Video-temporal PAs by inpainting a masked out region of an image. In addition, we present a simple unified framework to detect real-world anomalies under the OCC setting. Our method performs on par with other existing state-of-the-art PAs generation and reconstruction based methods under the OCC setting.
  arXiv  Detail & Related papers  (2023-11-27T13:14:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.