Latent Dynamics Modeling

Follow this topic Ask about this topic

Momentum

35 papers in the last four weeks, up 483% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 172

All topics

Interpreting Latent CoT Reasoning as Dynamical Systems
Jun 20, 2026Sabari Iyyappan Duraipandian, Shreya Sanjay Boyane, Manju Nagesh +3Latent Dynamics Modeling LLM Interpretability
1San Jose State University. · 2Worcester Polytechnic Institute. · 3George Mason University. +1
Beyond the Next Step: Variable-Length Latent World Models for Long-Horizon Planning
Jun 19, 2026Tianqi Du, Qi Zhang, Yifei Wang +1Latent Dynamics Modeling World Models
State Key Lab of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University · Amazon AGI SF Lab · Institute for Artificial Intelligence, Peking University
Diffusion-Driven State Space Models
Jun 19, 2026Jack Ruder, Michael WojnowiczLatent Dynamics Modeling Latent Diffusion Models
1Montana State University
Anomaly Detection for Sparse and Irregular Multivariate Time Series with Latent SDEs
Jun 17, 2026Martin Uray, Dominik Geng, Florian Graf +2Irregular Time-Series Modeling Latent Dynamics Modeling
Josef Ressel Centre for Intelligent and Secure Industrial Automation, University of Applied Sciences, Salzburg, Austria · University of Salzburg, Austria
Ghost Attractor Networks: Basin-Structured Dynamical Decoders for Closed-Loop Sequential Generation
Jun 16, 2026Tianyu Wang, Ying Wang, Zhihao Liu +2Latent Dynamics Modeling Robot Motion Generation
Department of Production Engineering, KTH Royal Institute of Technology, Stockholm, Sweden · Department of Decision and Control Systems, KTH Royal Institute of Technology, Stockholm, Sweden
When Dynamics Models Read the Wrong Time Steps: Label-Free Event Credit Re-Anchoring for Robust Global Readouts
Jun 16, 2026Yifan WangLatent Dynamics Modeling OOD Generalization
Department of Mechanical Engineering, McGill University Montréal, QC H3A 2T7, Canada
Closing the Approximation Gap in Simulation-free Latent SDEs
Jun 15, 2026Henry D. Smith, Brian L. Trippe, Scott W. LindermanParameter Estimation Stochastic Differential Equations
Stanford University
Phys-JEPA: Physics-Informed Latent World Models for Multivariate Time-Series Forecasting
Jun 15, 2026Weizhi Nie, Weichao Liu, Honglin Guo +1Multivariate Time Series Forecasting Latent Dynamics Modeling
Tianjin University
Physics-conforming Latent Twins
Jun 13, 2026Matthias Chung, Yutong Bu, Deepanshu VermaNeural Surrogate Modeling Surrogate Modeling
Department of Mathematics, Emory University, 400 Dowman Drive, Atlanta, 30322, GA, USA · School of Mathematical and Statistical Sciences, Clemson University, 220 Parkway Drive, Clemson, 29634, SC, USA
Sensitivity Shaping for Latent Modeling
Jun 12, 2026Hongzhan Yu, Chenghao Li, Ruipeng Zhang +2Robotic Control Latent Dynamics Modeling
University of California San Diego
Deep Spectral Learning of Embedded Latent Transfer Operators for Stochastic Dynamical Systems
Jun 12, 2026Ryogo Tanaka, Yoshinobu KawaharaDynamical Systems Stochastic Linear Dynamical Systems
Graduate School of Information Science and Technology, The University of Osaka, Osaka, Japan · Center for Advanced Intelligence Project, RIKEN, Tokyo, Japan
Extracting Governing Equations from Latent Dynamics via Multi-View Contrastive Learning
Jun 11, 2026Paolo Muratore, Mackenzie Weygandt MathisContrastive Learning Parameter Identifiability
EPFL
Embedding Hybrid Systems into Continuous Latent Vector Fields
Jun 9, 2026Sangli Teng, Hang Liu, Koushil SreenathLatent Dynamics Modeling System Identification
University of California, Berkeley, CA, USA · University of Michigan, Ann Arbor, MI, USA
Machine Learning Methods for Studying Latent Neural Activity Dynamics
Jun 9, 2026Shufeng Kong, Fumei Deng, Xinyi Dong +7Dynamical Systems Latent Variable Models
School of Software Engineering, Sun Yat-sen University, Zhuhai, China · School of Computer Science and Artificial Intelligence, Foshan University, Foshan, China · Department of Ecology and Evolutionary Biology, Cornell University, Ithaca, NY, USA +2
Mechanical Field Networks: Structured Neural Dynamics for Multivariate Systems
Jun 8, 2026Xingji CuiMultivariate Time Series Forecasting Dynamical Systems
Xi’an Jiaotong University, China
Graph Mamba Operator: A Latent Simulator for Interacting Particle Systems
Jun 8, 2026Karn Tiwari, Niladri Dutta, N M Anoop Krishnan +1Latent Dynamics Modeling Spatiotemporal GNNs
Department of Electrical Communication Engineering Indian Institute of Science, Bangalore Bengaluru, 560012, India · Department of Computer Science and Automation Indian Institute of Science, Bangalore Bengaluru, 560012, India · Yardi School of Artificial Intelligence Indian Institute of Technology, Delhi New Delhi, 110016, India
Temporally Consistent and Controllable Video Generation of 2D Cine CMR via Latent Space Motion Modeling
Jun 8, 2026Yiheng Cao, Gustavo Andrade-Miranda, Jiatian Zhang +2Latent Dynamics Modeling Text-to-Video Generation
SyCoIA - IMT Mines Alès · Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, China · SyCoIA, IMT Mines Ales, Ales, France
EEGDancer: Dynamic Emotion Latent Space Masked Modeling with Reinforcement Learning for EEG Continuous Emotion Prediction
Jun 4, 2026Zhihao Zhou, Weishan Ye, Li Zhang +2Latent Dynamics Modeling EEG Emotion Recognition
The School of Biomedical Engineering, Medical School, Shenzhen University, Shenzhen, China · The Guangdong Provincial Key Laboratory of Biomedical Measurements and Ultrasound2026 Imaging, Shenzhen, China
Deep Embedded Multiplicative DMD for Algebra-Preserving Koopman Learning
Jun 3, 2026Kelan Gray, Finlay Brown, Nicolas Boullé +1Koopman Operator Learning Latent Dynamics Modeling
Department of Mathematics, Imperial College London, London, SW7 2AZ, UK. · Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Cambridge, CB3 0WA, UK.
Dynamics Are Learned, Not Told: Semi-Supervised Discovery of Latent Dynamics Geometries For Zero-Shot Policy Adaptation
Jun 1, 2026Zhiming Xu, Weitao Zhou, Xianghui Pan +4Robot Policy Adaptation Latent Dynamics Modeling
School of Computer Science and Engineering, Tongji University, Shanghai, China · School of Vehicle and Mobility, Tsinghua University, Beijing, China · Simple AI, Beijing, China +1
State-Coupled Volatility in Latent Dynamical Systems: Recovery Under Partial Observation
Jun 1, 2026Imani BeckettParticle Filtering Latent Dynamics Modeling
The Herbert Wertheim School of Public Health and Human Longevity Science University of California San Diego
Physically-Constrained Mamba-SDE for Remaining Useful Life Prediction under Irregular Observations
Jun 1, 2026Deyu Zhuang, Peiliang Gong, Yang Shao +4Irregular Time-Series Modeling Stochastic Differential Equations
Nanjing University of Aeronautics and Astronautics Nanjing, China · Nanyang Technological University Singapore · Singapore University of Technology and Design Singapore
Computation-Aware Kalman Filtering with Model Selection for Neural Dynamics
May 31, 2026JR Huml, Jonathan Wenger, John P. CunninghamDynamical Systems Bayesian Filtering
Department of Statistics, Columbia University; Zyphra Technologies · Department of Statistics, Columbia University; Zuckerman Institute
GlucoFM: A Dual-Stream Foundation Model for Continuous Glucose Monitoring
May 29, 2026Zechen Li, Keerthana Natarajan, Weizhi Zhang +11Irregular Time-Series Modeling Latent Dynamics Modeling
Google Research · Work done during an internship at Google · University of New South Wales, Sydney
Learning Permutation-invariant Macroscopic Dynamics
May 29, 2026Zhichao Han, Mengyi Chen, Qianxiao LiDynamical Systems Latent Dynamics Modeling
Institute for Functional Intelligent Materials, National University of Singapore · Department of Mathematics, National University of Singapore
Physics from Video: Identifiability of Time-Invariant Second-Order ODEs under Minimal Trajectory Conditions
May 27, 2026Yuanyuan Wang, Wenjie Wang, Kun Zhang +1Parameter Identifiability Latent Dynamics Modeling
Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE · University of Melbourne, Melbourne, Australia · Carnegie Mellon University, Pittsburgh, USA
Chreode: A Cell World Model for One-Step Temporal Dynamics and Perturbation Prediction
May 27, 2026Mufan Qiu, Genhui Zheng, Yinuo Xu +4World Model Learning Latent Dynamics Modeling
University of North Carolina at Chapel Hill · The University of Texas at Austin · University of Pennsylvania
Stabilizing Recurrent Dynamics for Test-Time Scalable Latent Reasoning in Looped Language Models
May 26, 2026Xiao-Wen Yang, Ziyu Han, Xi-Hua Zhang +4Latent Dynamics Modeling Test-Time Scaling
State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, China · School of Artificial Intelligence, Nanjing University, Nanjing, China · School of Intelligence Science and Technology, Nanjing University, Nanjing, China
When Does LeJEPA Learn a World Model?
May 25, 2026David Klindt, Yann LeCun, Randall BalestrieroWorld Model Learning Representation Identifiability
Cold Spring Harbor Laboratory · New York University · Brown University
Learning Latent Dynamical Causal Processes for Single-Cell Perturbation Prediction
May 25, 2026Wenkang Jiang, Yuhang Liu, Erdun Gao +3Causal Representation Learning Latent Dynamics Modeling

Jun 20, 2026, cs.AIJ/K move · Enter open · S save

Interpreting Latent CoT Reasoning as Dynamical Systems

Sabari Iyyappan Duraipandian, Shreya Sanjay Boyane, Manju Nagesh, Jerome Francis+2

1San Jose State University. · 2Worcester Polytechnic Institute. · 3George Mason University.+1

Latent Dynamics Modeling LLM Interpretability Mechanistic Interpretability Latent CoT Reasoning Reasoning Trace Analysis

Open paper AskPDF arXiv

Recent latent reasoning methods, such as CODI and COCONUT, face a fundamental interpretability problem: they maintain multiple superimposed candidate traces in the hidden space at each step, unlike explicit- CoT, which follows a single transparent reasoning trace. Existing mechanistic methods show compression, shortcuts, and superposition without explaining how reasoning evolves across latent steps. To address this gap, we model latent token sequences as trajectories in representation space and apply dynamical systems analysis to characterize the evolution of reasoning. Using quantitative measures, such as step-to-step change, direction consistency, and Lyapunov sensitivity, alongside qualitative projections, such as UMAP and DMD/PHATE, we show that latent CoT exhibits structured, non-random dynamics with two distinct stability classes. CODI behaves as a stable attractor, while COCONUT behaves as an unstable expanding system, and SIM-CoT supervision tightens both behaviors without changing the underlying dynamics. This framework advances the interpretability of latent CoT reasoning dynamics and provides actionable insights for improving latent reasoning performance. Code1 and Project page2 available online.

Momentum

Related topics

Latest papers 172