A Time-Reparameterized Cumulative Intensity Extrapolation Sampler for Discrete Flow Matching

• URL: http://arxiv.org/abs/2606.24140v2
• Date: Wed, 24 Jun 2026 04:09:21 GMT
• Title: A Time-Reparameterized Cumulative Intensity Extrapolation Sampler for Discrete Flow Matching
• Abstract summary: TR-CIE aims to improve sampling quality when function evaluations are restricted.<n>We provide a theoretical analysis that bounds the local approximation error of cumulative intensities.<n>Experiments on synthetic tasks, text generation, and text-to-image benchmarks demonstrate that our method improves sampling quality under limited NFE.
• Score: 25.54630601391996
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Discrete flow matching (DFM) provides a principled framework for generative modeling on discrete state spaces via continuous-time Markov chain dynamics. In practice, sampling for DFM commonly employs discretizations such as $τ$-leaping, yet efficient sampling methods under a limited number of function evaluations (NFE) remain less studied. To address this gap, we propose the Time-Reparameterized Cumulative Intensity Extrapolation (TR-CIE) sampler, which aims to improve sampling quality when function evaluations are restricted. TR-CIE consists of two components. First, a schedule-based time reparameterization rescales the time grid according to the noise schedule. Under standard factorized DFM rate parameterizations, this transformation of variables absorbs the schedule-dependent growth term and mitigates stiffness near the terminal sampling stage. Second, we introduce a cumulative-intensity extrapolation updating rule. By reusing cached model outputs from the previous step as a history term, this improves the approximation of stepwise cumulative intensities on the resulting non-uniform time grid. We provide a theoretical analysis that bounds the local approximation error of cumulative intensities and establishes convergence results. The resulting sampler requires one NFE per step and introduces no additional model evaluations compared to the standard $τ$-leaping sampler. Extensive experiments on synthetic tasks, text generation, and text-to-image benchmarks demonstrate that our method improves sampling quality under limited NFE.

Related papers

• From Atoms to Entropy: Optimal Noise Allocation for Diffusion Training in the Convex Regime [52.459513910242485]
  We develop a general statistical framework for studying optimal noise-level allocation in diffusion training.<n>We show that the optimized training schedule admits an atomic minimizer, concentrated on finitely many noise levels.<n>We then evaluate the entropic schedule in larger-scale experiments, where full schedule optimization is currently intractable.
  arXiv  Detail & Related papers  (2026-07-10T20:59:06Z)
• On the Error-Correcting Effects of Stochasticity in Discrete Diffusion [0.0]
  Discrete diffusion models achieve strong performance in text and image generation, but their inference remains slow and must inherently balance sampling and sample quality.<n>We show that highly deterministic transitions converge rapidly but suffer from error accumulation, while more transitions converge more slowly yet can achieve higher final sample quality.<n>Motivated by this analysis, we propose emphDiscrete Churn and Restart Sampling (DCRS), a novel inference algorithm that injects controlledity by alternating between forward and reverse diffusion processes.
  arXiv  Detail & Related papers  (2026-05-26T05:58:46Z)
• Precise: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models [56.67321805551389]
  Reinforcement learning (RL) has become an effective way to improve prompt alignment and perceptual quality in diffusion and flow-matching generators.<n>The sampler, controlling the exploration behavior and denoising dynamics, is thus part of the policy.<n>We propose a new sampler that balances effective exploration with stability.
  arXiv  Detail & Related papers  (2026-05-22T11:37:22Z)
• TFTF: Training-Free Targeted Flow for Conditional Sampling [1.4151684142137693]
  We propose a training-free conditional sampling method for flow matching models based on importance sampling.<n>Because a nave application of importance sampling suffers from weighteneracy in high-dimensional settings, we modify and incorporate a resampling technique in sequential Monte Carlo.<n>Our framework requires no additional training, while providing theoretical guarantees of accuracy.
  arXiv  Detail & Related papers  (2026-02-13T13:41:35Z)
• Diversified Scaling Inference in Time Series Foundation Models [17.268760626931517]
  This work systematically investigates two questions: how do TSFMs behave under standard sampling-based inference scaling, and can controlled sampling diversity enhance performance?<n>We first examine the properties of TSFMs under standard sampling often fail to adhere to scaling laws due to insufficient exploration of the solution space.<n>We then delve into diversified inference scaling via tailored time series perturbations to expand the generative distribution's support.
  arXiv  Detail & Related papers  (2026-01-24T08:53:42Z)
• 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)
• FreqFlow: Long-term forecasting using lightweight flow matching [3.5235875824926346]
  We introduce FreqFlow, a novel framework that leverages conditional flow matching in the frequency domain for deterministic MTS forecasting.<n>FreqFlow transforms the forecasting problem into the spectral domain, where it learns to model amplitude and phase shifts.<n>Experiments on real-world traffic speed, volume, and flow datasets demonstrate that FreqFlow achieves state-of-the-art forecasting performance.
  arXiv  Detail & Related papers  (2025-11-20T14:50:13Z)
• Inference-Time Scaling of Diffusion Language Models with Particle Gibbs Sampling [70.8832906871441]
  We study how to steer generation toward desired rewards without retraining the models.<n>Prior methods typically resample or filter within a single denoising trajectory, optimizing rewards step-by-step without trajectory-level refinement.<n>We introduce particle Gibbs sampling for diffusion language models (PG-DLM), a novel inference-time algorithm enabling trajectory-level refinement while preserving generation perplexity.
  arXiv  Detail & Related papers  (2025-07-11T08:00:47Z)
• Noise Conditional Variational Score Distillation [60.38982038894823]
  Noise Conditional Variational Score Distillation (NCVSD) is a novel method for distilling pretrained diffusion models into generative denoisers.<n>By integrating this insight into the Variational Score Distillation framework, we enable scalable learning of generative denoisers.
  arXiv  Detail & Related papers  (2025-06-11T06:01:39Z)
• Neural Flow Samplers with Shortcut Models [19.81513273510523]
  Continuous flow-based neural samplers offer a promising approach to generate samples from unnormalized densities.<n>We introduce an improved estimator for these challenging quantities, employing a velocity-driven Sequential Monte Carlo method.<n>Our proposed Neural Flow Shortcut Sampler empirically outperforms existing flow-based neural samplers on both synthetic datasets and complex n-body system targets.
  arXiv  Detail & Related papers  (2025-02-11T07:55:41Z)
• FlowTS: Time Series Generation via Rectified Flow [67.41208519939626]
  FlowTS is an ODE-based model that leverages rectified flow with straight-line transport in probability space.<n>For unconditional setting, FlowTS achieves state-of-the-art performance, with context FID scores of 0.019 and 0.011 on Stock and ETTh datasets.<n>For conditional setting, we have achieved superior performance in solar forecasting.
  arXiv  Detail & Related papers  (2024-11-12T03:03:23Z)
• Score-based Generative Models with Adaptive Momentum [40.84399531998246]
  We propose an adaptive momentum sampling method to accelerate the transforming process. We show that our method can produce more faithful images/graphs in small sampling steps with 2 to 5 times speed up.
  arXiv  Detail & Related papers  (2024-05-22T15:20:27Z)
• Fast Sampling via Discrete Non-Markov Diffusion Models with Predetermined Transition Time [49.598085130313514]
  We propose discrete non-Markov diffusion models (DNDM), which naturally induce the predetermined transition time set.<n>This enables a training-free sampling algorithm that significantly reduces the number of function evaluations.<n>We study the transition from finite to infinite step sampling, offering new insights into bridging the gap between discrete and continuous-time processes.
  arXiv  Detail & Related papers  (2023-12-14T18:14:11Z)

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.