Invertible Neural Networks

Ask about this topic

Overview

Invertible neural networks learn transformations whose inputs can be recovered from their outputs, making them useful for probabilistic modeling, inverse problems, and reversible computation. Common approaches include normalizing flows with coupling layers and tractable Jacobians, invertible residual blocks, and constrained adapters that preserve bounded geometric distortion. Applications range from image and video compression and inverse design to robotics, forecasting, and control, where models can generate outputs or infer inputs from desired outcomes. A central challenge is balancing tractable, stable inversion with expressive transformations: invertibility alone does not guarantee useful semantic geometry or robustness, so theoretical guarantees and tests across realistic settings remain important.

Latest papers

CardsList

14 papers3 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

  1. Semantic Latent Alignment for Flow Matching with Invertible Bi-Lipschitz Adapters

    Oct 15, 2026Felix Nützel, Mischa Dombrowski, Luca Hagen +1Latent Space AlignmentConditional Image Generation

    Friedrich-Alexander-Universität Erlangen-Nürnberg · Imperial College London

  2. PrT-Flow: Probability-Tractable Flow Matching for Reinforcement Learning

    Oct 13, 2026Congzhong Sun, Ning TanFlow MatchingFlow-Based Generative Modeling

    School of Computer Science and Engineering, Sun Yat-sen University

  3. LLN: Learnable Lens Networks for Parameter-Efficient Long-Horizon Dynamical Prediction

    Sep 28, 2026Binbin Yong, Zhao Su, Lan Guo +3Invertible Neural NetworksResidual Learning

    Lanzhou University · Monash University · University of Wollongong

  4. Conditional Invertible Neural Networks for Data-Driven UAV Control: A 2-D Proof of Concept

    Jul 15, 2026Christian Wittke, Stephan Myschik, Oliver NiggemannInvertible Neural NetworksQuadrotor Control

    Computer Science in Mechanical Engineering, Helmut Schmidt University, Hamburg, Germany. · Institute for Aeronautical Engineering, University of the Bundeswehr Munich, Bavaria, Germany

  5. Robustly Invertible Nonlinear Dynamics and the BiLipREN: From Inversion-Based Control to Generative Trajectory Modelling

    Jul 10, 2026Yurui Zhang, Ruigang Wang, Ian R. ManchesterInvertible Neural NetworksRecurrent Neural Networks

    Australian Centre for Robotics (ACFR), and the School of Aerospace, Mechanical and Mechatronic Engineering, The University of Sydney, Australia

  6. Efficient Cross-Scale Invertible Hiding Network with Spatial-Frequency Collaboration and Non-Invertible Mechanism

    Jun 24, 2026Junxue Yang, Xin LiaoInvertible Neural Networks

    College of Computer Science and Electronic Engineering, Hunan University, Changsha, China

  7. Invertible Neural Network Adapter for One-Step Flow Matching in Robot Manipulation

    Jun 17, 2026Yu Zhang, Kangyi Ji, Yongxiang Zou +3Invertible Neural NetworksFlow Matching

  8. High-Fidelity Video Compression based on Invertible Neural Transform and Implicit Conditioning

    Jun 11, 2026Siyue Teng, Ho Man Kwan, Yuxuan Jiang +2Invertible Neural NetworksNeural Video Compression

    Visual Information Lab, University of Bristol, UK

  9. Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior

    Jun 7, 2026Tuc Nguyen, Thai LeInvertible Neural NetworksLanguage Model Steering

    Indiana University Bloomington, USA

  10. TVRN: Invertible Neural Networks for Compression-Aware Temporal Video Rescaling

    May 15, 2026Xinmin Feng, Li Li, Dong Liu +1Invertible Neural NetworksVideo Compression

    MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei 230093, China

  11. Generative Design of a Gas Turbine Combustor Using Invertible Neural Networks

    Apr 27, 2026Patrick Krüger, Hanno Gottschalk, Werner Krebs +1Invertible Neural NetworksInverse Design

    Department of Mathematics, Technische Universität Berlin, Straße des 17. Juni 135, Berlin, Berlin, Germany · Sienmens Energy, Rheinstraße 100, Mühlheim an der Ruhr, NRW, Germany

  12. Reversible Residual Normalization Alleviates Spatio-Temporal Distribution Shift

    Apr 17, 2026Zhaobo Hu, Vincent Gauthier, Mehdi NaimaInvertible Neural NetworksDistribution Shift Robustness

    SAMOVAR, Télécom SudParis · Institut Polytechnique de Paris · CNRS – LIP6 +1

  13. Invertible Query-Key Coupling Composes with Attention Mechanisms

    Apr 2, 2026Barak Gahtan, Alex M. BronsteinInvertible Neural NetworksSelf-Attention

    Technion – Israel Institute of Technology · ISTA – Institute of Science and Technology Austria

  14. 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