Normalizing Flows

Ask about this topic

Overview

Normalizing flows learn reversible transformations from a simple distribution, such as a Gaussian, into a complex one, allowing both samples and exact probability densities to be computed. Common approaches include coupling and autoregressive layers, spline transformations, continuous flows, and structured or conditional flows for tasks such as image generation, Bayesian inference, anomaly detection, and control. Current work also combines flows with compact latent representations, flow matching, and physics-informed models, extending their use in scientific simulation and uncertainty estimation. A central tension is balancing expressive, multimodal models against efficient and stable computation, while ensuring that good likelihoods translate into reliable mode coverage and calibrated uncertainty.

Latest papers

CardsList

73 papers7 papers in the last four weeks, down 12% on the four weeks before. 0.0% of all new papers.

  1. The Coupling Within: Flow Matching via Distilled Normalizing Flows

    Mar 9, 2026David Berthelot, Tianrong Chen, Jiatao Gu +6Flow-Based Generative ModelingFlow Matching

  2. Image Generation Models: A Technical History

    Mar 8, 2026Rouzbeh ShirvaniImage GenerationDiffusion-Based Image Generation

  3. Variance reduction in lattice QCD observables via normalizing flows

    Mar 3, 2026Ryan Abbott, Denis Boyda, Yang Fu +5Lattice Field TheoryVariance Reduction

    Physics Department, Columbia University, New York, NY 10027, USA · Center for Theoretical Physics, Massachusetts Institute of Technology, Cambridge, MA 02139, USA · The NSF AI Institute for Artificial Intelligence and Fundamental Interactions +3

  4. IHF-Harmony: Multi-Modality Magnetic Resonance Images Harmonization using Invertible Hierarchy Flow Model

    Feb 25, 2026Pengli Zhu, Yitao Zhu, Haowen Pang +1Medical Image HarmonizationMagnetic Resonance Imaging

    Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong · School of Integrated Circuits and Electronics, Beijing Institute of Technology, China · Mental Health Research Center, The Hong Kong Polytechnic University, Hong Kong +1

  5. VINA: Variational Invertible Neural Architectures

    Feb 24, 2026Shubhanshu Shekhar, Mohammad Javad Khojasteh, Ananya Acharya +2Invertible Neural NetworksNormalizing Flows

    EME Department, Rochester Institute of Technology · Department of Mechanical Engineering, Massachusetts Institute of Technology

  6. Why Does Counterintuitive Likelihood Behavior Rarely Emerge in Tabular Anomaly Detection?

    Feb 10, 2026Donghwan Kim, Junghun Phee, Hyunsoo YoonAnomaly DetectionTabular Anomaly Detection

    Department of Industrial Engineering, University of Yonsei, Republic of Korea, Seoul · H. Milton Stewart School of Industrial and Systems Engineering (ISyE), Georgia Institute of Technology, USA, GA

  7. Mitigating the Likelihood Paradox in Flow-based OOD Detection: An Entropic Perspective

    Feb 10, 2026Donghwan Kim, Hyunsoo YoonOOD DetectionNormalizing Flows

    Department of Industrial Engineering University of Yonsei

  8. From Core to Detail: Unsupervised Disentanglement with Entropy-Ordered Flows

    Feb 6, 2026Daniel Galperin, Ullrich KötheUnsupervised LearningDisentangled Representation Learning

    Heidelberg University

  9. Enhancing Low-resolution Image Representation Through Normalizing Flows

    Jan 11, 2026Chenglong Bao, Tongyao Pang, Zuowei Shen +2Learned Image CompressionNormalizing Flows

    Yau Mathematical Sciences Center, Tsinghua University, Beijing, China, and Beijing Institute of Mathematical Sciences and Applications, Beijing, China · Yau Mathematical Sciences Center, Tsinghua University, Beijing, China · Department of Mathematics, National University of Singapore, Singapore +2

  10. CDFlow: Building Invertible Layers with Circulant and Diagonal Matrices

    Oct 29, 2025Xuchen Feng, Siyu LiaoNormalizing FlowsDensity Estimation

    School of Integrated Circuits Sun Yat-sen University

  11. Neural Variational Cut Posteriors without Upstream Data

    Oct 11, 2025Jiafang Song, Sandipan Pramanik, Abhirup DattaBayesian InferenceVariational Inference

    Department of Biostatistics, Johns Hopkins University, USA

  12. Normalizing Flows are Capable Models for Continuous Control

    May 29, 2025Raj Ghugare, Benjamin EysenbachNormalizing FlowsReinforcement Learning

    Department of Computer Science Princeton University

  13. Physics-Informed Sylvester Normalizing Flows for Bayesian Inference in Magnetic Resonance Spectroscopy

    May 6, 2025Julian P. Merkofer, Dennis M. J. van de Sande, Alex A. Bhogal +1Normalizing FlowsBayesian Inference

    Eindhoven University of Technology, Eindhoven, The Netherlands · University Medical Center Utrecht, Utrecht, The Netherlands