arXiv Machine Learning June 3, 2026 By Imani Beckett

State-Coupled Volatility in Latent Dynamical Systems: Recovery Under Partial Observation

Read the original on arXiv Machine Learning →

arXiv:2606. 02664v1 Announce Type: cross Abstract: Latent state-space models are widely used to study partially observed dynamical systems, yet most formulations assume that process variability is independent of latent-state position.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 29

Emergent Latent-State Computation under Stochastic Volatility

arXiv:2607. 25459v1 Announce Type: cross Abstract: Mechanistic interpretability has largely focused on language models and deterministic toy tasks.

By Xiaoyu Huang, Lulu Wang

llms benchmarks safety

arXiv Machine Learning

Jun 16

Conditional Score-Based Modeling of Effective Langevin Dynamics

arXiv:2604. 23952v2 Announce Type: replace-cross Abstract: Stochastic reduced-order models are widely used to represent the effective dynamics of complex systems, but estimating their drift and diffusion coefficients from data remains challenging.

By Ludovico T. Giorgini

diffusion

arXiv Machine Learning

Jun 2

Knowledge-Informed Kernel State Reconstruction from Heterogeneous Partial Observations

arXiv:2601. 22328v2 Announce Type: replace Abstract: Real-world scientific systems are rarely observed through complete, regularly sampled state trajectories.

By Luca Muscarnera, Silas Ruhrberg Est\'evez, Samuel Holt, Evgeny Saveliev, Mihaela van der Schaar

benchmarks

arXiv Machine Learning

Jun 2

Large-scale Uncertainty Quantification for Latent Variable Models Using Subsampling Markov Chain Monte Carlo

arXiv:2606. 00309v1 Announce Type: new Abstract: Stochastic gradient Langevin dynamics combined with Gibbs updates (SGLD--Gibbs) provides a highly scalable approach to approximate Bayesian inference in latent variable models.

By Xiaoyu Wang, Jonathan H. Huggins

diffusion

arXiv Machine Learning

Jun 29

Disentangling Continuous-Time Latent Dynamics: Identifiability of Latent SDEs via Diffusion Shifts

arXiv:2606. 28228v1 Announce Type: new Abstract: Causal representation learning for time series has developed strong identifiability results in discrete-time latent causal models, but identifiability in continuous-time latent stochastic differential equation (SDE) models remains largely open.

By Yuanyuan Wang, Wenjie Wang, Haoxuan Li, Mingming Gong, Kun Zhang

diffusion efficiency

arXiv Machine Learning

Jun 16

Closing the Approximation Gap in Simulation-free Latent SDEs

arXiv:2606. 16138v1 Announce Type: cross Abstract: Recovering dynamical systems from noisy observations is a recurring challenge across scientific domains, including neuroscience and physics.

By Henry D. Smith, Brian L. Trippe, Scott W. Linderman

Related stories

Emergent Latent-State Computation under Stochastic Volatility

Conditional Score-Based Modeling of Effective Langevin Dynamics

Knowledge-Informed Kernel State Reconstruction from Heterogeneous Partial Observations

Large-scale Uncertainty Quantification for Latent Variable Models Using Subsampling Markov Chain Monte Carlo

Disentangling Continuous-Time Latent Dynamics: Identifiability of Latent SDEs via Diffusion Shifts

Closing the Approximation Gap in Simulation-free Latent SDEs