Few-Step Boltzmann Generators via Scalable Likelihood Flow Maps

• URL: http://arxiv.org/abs/2606.29110v1
• Date: Sat, 27 Jun 2026 23:26:53 GMT
• Title: Few-Step Boltzmann Generators via Scalable Likelihood Flow Maps
• Abstract summary: Flow-based generative modeling has led to models that output high-quality samples while using only a small number of function evaluations.<n>In this work, we introduce LikeLihood distillation of flOw maPs (SCALLOP)<n>SCALLOP significantly reduces both training variance and training time while consistently improving performance.
• Score: 33.896605880822115
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent progress in flow-based generative modeling has led to models that output high-quality samples while using only a small number of function evaluations. However, at present, there is a lack of similar advances in estimating the model likelihood. In particular, most existing methods either rely on restrictive architectures that enable exact calculations, or use stochastic approximations such as Hutchinson's trace estimator that introduce substantial variance. In this work, we introduce SCAlable LikeLihood distillation of flOw maPs (SCALLOP). SCALLOP builds on the recently proposed F2D2, a likelihood flow map model that can generate samples and their densities in a small number of function evaluations. While F2D2 uses Hutchinson's estimator during training, we introduce an alternative and more scalable likelihood distillation objective that is Hutchinson-free and admits a vectorized formulation. Empirically, we demonstrate the effectiveness of SCALLOP as a Boltzmann generator in molecular science, and further validate its benefit on image datasets. SCALLOP significantly reduces both training variance and training time while consistently improving performance compared to F2D2, and is competitive with the state-of-the-art while achieving up to 10x inference speedup over the fastest baseline.

Related papers

• Perceptual Flow Matching for Few-Step Generative Modeling [64.26537634881244]
  Perceptual Flow Matching is a framework for few-step generation in flow-matching models.<n>We show that PFM produces high-quality few-step generators when supervised in an appropriate representation space.
  arXiv  Detail & Related papers  (2026-07-03T17:55:01Z)
• StAD: Stein Amortized Divergence for Fast Likelihoods with Diffusion and Flow [0.0]
  StAD is a new method to predict and learn the divergence of the probability flow ordinary differential equation (PF-ODE)<n>We show that our method is competitive with the Hutchinson and Hutch++ on CIFAR-10, ImageNet and other density estimation tasks.
  arXiv  Detail & Related papers  (2026-05-15T18:00:00Z)
• FALCON: Few-step Accurate Likelihoods for Continuous Flows [78.37361800856583]
  We propose Few-step Accurate Likelihoods for Continuous Flows (FALCON), which allows for few-step sampling with a likelihood accurate enough for importance sampling applications.<n>We show FALCON outperforms state-of-the-art normalizing flow models for molecular Boltzmann sampling and is two orders of magnitude faster than the equivalently performing CNF model.
  arXiv  Detail & Related papers  (2025-12-10T18:47:25Z)
• Joint Distillation for Fast Likelihood Evaluation and Sampling in Flow-based Models [100.28111930893188]
  Some of today's best generative models still require hundreds to thousands of neural function evaluations to compute a single likelihood.<n>We present fast flow joint distillation (F2D2), a framework that simultaneously reduces the number of NFEs required for both sampling and likelihood evaluation by two orders of magnitude.<n>F2D2 is modular, compatible with existing flow-based few-step sampling models, and requires only an additional divergence prediction head.
  arXiv  Detail & Related papers  (2025-12-02T10:48:20Z)
• Generative Modeling with Continuous Flows: Sample Complexity of Flow Matching [60.37045080890305]
  We provide the first analysis of the sample complexity for flow-matching based generative models.<n>We decompose the velocity field estimation error into neural-network approximation error, statistical error due to the finite sample size, and optimization error due to the finite number of optimization steps for estimating the velocity field.
  arXiv  Detail & Related papers  (2025-12-01T05:14:25Z)
• On the Wasserstein Convergence and Straightness of Rectified Flow [54.580605276017096]
  Rectified Flow (RF) is a generative model that aims to learn straight flow trajectories from noise to data.<n>We provide a theoretical analysis of the Wasserstein distance between the sampling distribution of RF and the target distribution.<n>We present general conditions guaranteeing uniqueness and straightness of 1-RF, which is in line with previous empirical findings.
  arXiv  Detail & Related papers  (2024-10-19T02:36:11Z)
• Cumulative Hazard Function Based Efficient Multivariate Temporal Point Process Learning [0.0]
  In this paper, we explore using neural networks to model a flexible but well-defined CHF. We show that the proposed model achieves the state-of-the-art performance on data fitting and event prediction tasks.
  arXiv  Detail & Related papers  (2024-04-21T13:51:31Z)
• Structural Pruning for Diffusion Models [65.02607075556742]
  We present Diff-Pruning, an efficient compression method tailored for learning lightweight diffusion models from pre-existing ones. Our empirical assessment, undertaken across several datasets highlights two primary benefits of our proposed method.
  arXiv  Detail & Related papers  (2023-05-18T12:38:21Z)
• Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEs [21.08236758778604]
  We propose several improved techniques for maximum likelihood estimation for diffusion ODEs. For training, we propose velocity parameterization and explore variance reduction techniques for faster convergence. For evaluation, we propose a novel training-free truncated-normal dequantization to fill the training-evaluation gap commonly existing in diffusion ODEs.
  arXiv  Detail & Related papers  (2023-05-06T05:21:24Z)

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.