Liquid Neural Networks

Ask about this topic

Overview

Liquid Neural Networks study sequence models whose internal state changes over time, often adapting its dynamics to the input and elapsed time between observations. Approaches include continuous-time cells such as closed-form continuous-time networks, multi-timescale experts, and parallel liquid-inspired updates that avoid costly sequential solvers. Researchers apply them to irregular time series, robotics, dynamic vision, medical data, and scheduling, comparing them with recurrent models, MLPs, and diffusion policies on task-specific benchmarks. Results often show advantages in parameter or compute efficiency and robustness to sparse timing, but performance is task-dependent: gains in prediction or reconstruction do not always carry over to closed-loop control, real-world data, or direct outcomes such as remaining useful life.

Latest papers

CardsList

13 papers1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

  1. ContiLNN: Mitigating Slice Sampling Discontinuity with Liquid Neural Networks for Medical Image Restoration

    Oct 8, 2026Jialei He, Enhe Liu, Sifan Song +10Image RestorationMedical Image Analysis

    Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, Yunnan, 650504, China · Academy of Artificial Intelligence and Advanced Technology, Xi’an Jiaotong-Liverpool University, Suzhou, Jiangsu, 215123, China · Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts, 02115, United States +1

  2. MTLiquid: Enabling Efficient Multi-Task Learning using Liquid Neural Networks for Lightweight Healthcare Monitoring Systems

    Sep 27, 2026Rachmad Vidya Wicaksana Putra, Fahad Abdul Rauf, Muhammad ShafiqueSepsis PredictionMulti-Task Learning

    eBRAIN Lab, New York University (NYU) Abu Dhabi, Abu Dhabi, United Arab Emirates

  3. Stochastic Liquid Deformation Fields: An SDE Generalisation of Closed-Form Continuous-Time Cells for Dynamic 3D Gaussian Splatting

    Aug 27, 2026Mingzhao Li, Arghya Pal3D Gaussian SplattingDynamic Scene Reconstruction

    School of Information Technology, Monash University, Selangor, Malaysia

  4. PLAN: Parallel Liquid-Inspired Approximation Network for Efficient Representation Learning in Flexible Job Shop Scheduling

    Aug 4, 2026Dhivya Dharshini Kannan, Wei Zhang, Jieyi Bi +5Efficient Neural Network InferenceLiquid Neural Networks

    Singapore Institute of Technology (SIT) · Nanyang Technological University (NTU) · Shanghai Jiao Tong University +1

  5. Liquid Latent State Dynamics for Interpretable Turbofan Degradation Modeling

    Jul 2, 2026Weizhi Nie, Weijie Wang, Yuting SuMultivariate Time Series ForecastingLiquid Neural Networks

    Tianjin University

  6. On the Necessity of a Liquid Substrate for Mesh Intelligence

    Jun 25, 2026Hongwei XuLiquid Neural NetworksMulti-Agent Systems

  7. Fast Human Attention Prediction for Fixation-guided Active Perception in Autonomous Navigation

    Jun 18, 2026Fatma Youssef Mohammed, Grzegorz Malczyk, Kostas AlexisActive PerceptionScanpath Prediction

    Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Norway

  8. Multi-Rate Mixture of Experts for Accelerating Liquid Neural Network Training

    Jun 10, 2026Shilong Zong, Almuatazbellah Boker, Hoda EldardiryIrregular Time-Series ModelingLiquid Neural Networks

    Department of Computer Science, Virginia Tech Blacksburg, VA 24061 USA · Department of Electrical and Computer Engineering, Virginia Tech Blacksburg, VA 24061 USA

  9. Liquid Neural Networks as a Drop-in Continuous-Time Deformation Field for Dynamic 3D Gaussian Splatting

    Jun 4, 2026Mingzhao Li, Arghya Pal, Guan Yuan Tan3D Gaussian SplattingLiquid Neural Networks

    School of Information Technology, Monash University, Selangor, Malaysia

  10. Comparative Analysis of Liquid Neural Networks and LSTM for Sequential Pattern Recognition: Robustness, Efficiency, and Clinical Utility

    May 26, 2026Ye Kyaw Thu, Thazin Myint Oo, Thepchai SupnithiEfficient Neural Network InferenceLiquid Neural Networks

    National Electronics and Computer Technology Center (NECTEC), Pathumthani, Thailand · Language Understanding Lab., Yangon, Myanmar

  11. Liquid Neural Network Models for Natural Gas Spot Price Time-Series Forecasting

    Apr 24, 2026Yiqian Liu, Jiayi Niu, Adam Kelleher +1Liquid Neural NetworksTime Series Forecasting

    Department of Data Science, Columbia University New York, NY, USA

  12. LiquidTAD: Efficient Temporal Action Detection via Parallel Liquid-Inspired Temporal Relaxation

    Apr 20, 2026Zepeng Sun, Naichuan Zheng, Hailun Xia +3Liquid Neural NetworksHuman Activity Recognition

  13. Liquid Networks with Mixture Density Heads for Efficient Imitation Learning

    Mar 28, 2026Nikolaus CorrellMixture Density NetworksImitation Learning

    University of Colorado Boulder