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.
State-Coupled Volatility in Latent Dynamical Systems: Recovery Under Partial Observation
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.
Related stories
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.
arXiv Statistics ML
2d ago
Inferring Multi-Timescale Neural Dynamics with Switching Linear Dynamical Systems
arXiv:2610.01786v1 Announce Type: cross Abstract: Neural activity often exhibits multiple timescales that can vary with behavioral states and task conditions. Identifying these timescales from neural...
arXiv Machine Learning
4d ago
Learning Macroscopic Dynamics without Reconstructing Microscopic States
arXiv:2609.37392v1 Announce Type: new Abstract: Modeling the temporal evolution of macroscopic properties of complex systems is an important scientific task. To predict this evolution without full mi...
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.
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.
arXiv Machine Learning
5d ago
I Act Therefore I Am: When Is JEPA's Action-Conditioning Enough to Learn Causal Mechanisms?
The paper studies when joint-embedding predictive architectures (JEPAs) can recover underlying causal states from high‑dimensional observations. It introduces a latent variable model where observations arise from causal states with action‑conditioned dynamics, and proposes an information‑theoretic objective that maximizes conditional likelihood while preserving state entropy. The authors prove identifiability conditions—particularly sufficient action‑induced variation—and instantiate the objective as an action‑modulated Gaussian additive‑noise model (A‑JEPA), demonstrating theoretical and empirical success in synthetic and visual benchmarks.
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.
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.
arXiv AI
Aug 17
Your Probabilistic JEPA Is Secretly a Hidden Markov Model: A State-Space Interpretation of Joint-Embedding Predictive Learning
arXiv:2608. 13621v1 Announce Type: new Abstract: A hidden Markov model (HMM) combines three roles: inference of a hidden-state belief from observations, propagation through a Markov transition, and emission back to observation space.
arXiv Machine Learning
Jun 3
Trajectory-Aware Node Contributions and the Limits of Static Controllability
arXiv:2606. 03067v1 Announce Type: cross Abstract: A recurring data mining task in complex networks is to determine how individual nodes contribute to system behavior.
Hugging Face Trending Papers
Sep 15
Stable by Construction: Variational Latent Markov Operators for Long-Horizon PDE Prediction
Neural PDE solvers provide efficient surrogates for time-dependent physical systems, but autoregressive prediction over long horizons remains challenging because local errors can induce distribution s...