Overview

Latent dynamics modeling studies how to represent a changing system with hidden states and learn how those states evolve from observations such as video, sensor streams, or sparse measurements. Common approaches include autoencoders with state-space models, neural ODEs and SDEs for continuous-time or stochastic change, Koopman operators for approximately linear evolution, and JEPA-style world models for action-conditioned prediction. These models support forecasting and control in robotics and physical simulation, as well as analysis of biological, clinical, and neural time series. A central challenge is that good one-step prediction or reconstruction does not guarantee reliable long-horizon rollouts, useful control, or recovery of meaningful physical mechanisms; work therefore explores stability, identifiability, and physics-based structure while balancing these constraints against model flexibility.

Latest papers

CardsList

274 papers27 papers in the last four weeks, down 50% on the four weeks before. 0.2% of all new papers.

  1. SLiDE: Structured Linear Dynamics for Forecasting with Exogenous Inputs

    Nov 14, 2026Sebastian Pütz, Theodore Glavas, Benjamin Schäfer +2Exogenous Time Series ForecastingRobust Time Series Forecasting

  2. Recovered or Memorized? Investigating Dynamical Consistency and Faithfulness in World Model Latents

    Nov 13, 2026Jerome Francisco, Kyle Deng, George Flint +1World ModelsLatent World Models

  3. Identifying Latent Neural Dynamics with Recognition-Parametrised Gaussian Process Dynamical Systems

    Nov 12, 2026Arielle Rosinski, Qianqian Feng, Lior Fox +1Latent Dynamics ModelingDynamical Systems

  4. InertiaMPDD: Multimodal Personalized Depression Detection via Emotional Inertia-Inspired Dynamics Modeling

    Nov 12, 2026Changzeng Fu, Songyang Wang, Chang Gao +9Depression DetectionLatent Dynamics Modeling

  5. Extending Grid Foundation Models for Phasor-Domain Dynamic Simulation

    Nov 6, 2026Boyang Zhao, Yifan Zhou, Alban Puech +2Power SystemsNeural Surrogate Modeling

  6. Identifying Neural Dynamics Using Nonlinear Interventional State Space Models

    Nov 5, 2026Hanna M. Tolle, Carles Balsells-Rodas, Yixin Wang +2State Space ModelsLatent Dynamics Modeling

  7. Neural Stochastic Forecasting for Lateral Molecular Diffusion Simulations

    Nov 4, 2026Jacob Ede Levine, Mario Hidalgo-Soria, Chen Yun Wen +2Probabilistic Trajectory PredictionNeural Surrogate Modeling

  8. Online Adaptation to Latent Physical Properties for Learning from Demonstration

    Nov 4, 2026Kotaro Kajitsuka, Masaki Murooka, Fumio KanehiroRobot Policy AdaptationLearning from Demonstration

  9. When Latent Dynamics Meet Data Assimilation: A Benchmark of Koopman-Type Representations

    Nov 2, 2026Zhiwei Zhang, Wenxuan Yuan, Xiaoyuan Cheng +10Latent Dynamics ModelingData Assimilation

  10. ForceLDM: A Force-aware Latent Dynamics Model for Contact-Rich Manipulation

    Nov 2, 2026Peiyuan Tang, Yao Li, Xiaodong Zhang +4Contact-Rich Robotic ManipulationLatent Dynamics Modeling

  11. Learning hidden-state dynamics from unpaired snapshots with lift-project SDEs

    Oct 31, 2026Qi Wang, Uduak George, Gustaaf JacobsLatent Dynamics ModelingStochastic Differential Equations

  12. PCD: Predictive Coding Dynamics for Irregularly Sampled Time Series

    Oct 30, 2026Tianrui Gou, Jiayangmei Xu, Xingzhou Zhang +1Time Series ModelingIrregular Time-Series Modeling

  13. SPT-Flow: One Integration, Many Futures in Continuous-Time World Models

    Oct 30, 2026Mingyang Lyu, Yinqian Sun, Gongce Cao +5World Model LearningWorld Models

  14. Meshless Latent Dynamics Models for Model Order Reduction of time-dependent Partial Differential Equations

    Oct 29, 2026Lorenzo Tomada, Federico Pichi, Gianluigi RozzaLatent Dynamics ModelingReduced-Order Modeling

  15. Learning Stabilizing Latent Feedback Controllers via Multi-Step Backward Losses

    Oct 29, 2026Paul Lutkus, Lars Lindemann, Stephen Tuoutput feedback stabilizationFeedback Control

  16. world2vec: Mechanistic world models through latent dynamics learning

    Oct 29, 2026Tobias Schmidt, Rodrigo Gonzalez Laiz, Krisztián Szuppinger +1World Model LearningWorld Models

  17. Hidden Phase Transition in Single-Polymer Stretching under Elongational Flow

    Oct 29, 2026Aiqing Zhu, Fushuai Wang, Eleonore Vissol-Gaudin +2Phase TransitionsMaterials Science

  18. Understanding the limits of latent world models

    Oct 27, 2026Rodrigo Gonzalez Laiz, Steffen SchneiderWorld ModelsLatent World Models

  19. Latent dynamics for reconstructing fine-scale PDE trajectories from coarse observations

    Oct 24, 2026Chenhao Si, Zishan Qian, Shing-Tung Yau +2Latent Dynamics ModelingPDE Surrogate Modeling

  20. ZENO: Nonlinear filtering with Zakai Equation Neural Operators

    Oct 23, 2026Aaditya Prasad, Steven W. Flavell, Brian DePasqualeLatent Dynamics ModelingStochastic Differential Equations

  21. Meta-iLaD: Identifiable Latent Dynamics via Meta-Learning of Dynamics Environments

    Oct 19, 2026Yubo Ye, Sweekar Piya, Xiajun Jiang +1Latent Dynamics ModelingTime Series Forecasting

  22. Vision-Language-Delta-Action: Learning Compact Deltas as Actionable Transition Interfaces for Robotic Manipulation

    Oct 19, 2026Lingsen Zhang, Wei Li, Jie He +5Robotic ManipulationVision-Language-Action Models

  23. See the Future, Classify the Present: Stochastic Latent World Modeling for Hyperspectral Images

    Oct 19, 2026Muhammad Ahmad, Gemine Vivone, Ronny Hänsch +3Hyperspectral Image ClassificationPredictive Representation Learning

  24. Latent Projection for Latent Planning

    Oct 19, 2026Yoo Sung Jang, Michael RyooLatent-Space PlanningWorld Model-Based Planning

  25. A discrete-continuous-time stochastic framework for attention-deficit/hyperactivity disorder-related symptom modeling and pharmacological intervention via methylphenidate

    Oct 18, 2026Oana-Maria-Catalina CrisanMental HealthStochastic Optimal Control