arXiv:2604. 24662v2 Announce Type: replace-cross Abstract: Identifying the dynamical state variables of a system from high-dimensional observations is a central problem across physical sciences.
arXiv:2607. 05127v1 Announce Type: cross Abstract: Understanding the physics of many-body complex dynamical systems is typically non-trivial.
arXiv:2606. 07770v1 Announce Type: new Abstract: Self-supervised methods that learn representations and predict dynamics fully in the latent space, such as JEPA, have been shown to confuse slowly varying noise with the dynamical signals they aim to capture.
In the physical world we inhabit, space and time are fundamentally continuous. However, existing machine learning paradigms for world modeling are largely confined to discrete-time prediction, thereby exhibiting significant inefficiency in capturing the dynamics of physical world.
arXiv:2607. 09801v1 Announce Type: new Abstract: Governing equations provide compact descriptions of physical systems, yet the variables in which they are simple are often hidden in high-dimensional measurements.
arXiv:2410. 11894v3 Announce Type: replace-cross Abstract: Dynamical systems form the foundation of scientific discovery, traditionally modeled with predefined state variables such as the angle and angular velocity, and differential equations such as the equation of motion for a single pendulum.
arXiv:2607. 27924v1 Announce Type: new Abstract: In the physical world we inhabit, space and time are fundamentally continuous.
The paper introduces a latent dataset distillation framework for human motion prediction, addressing the limitations of traditional gradient matching by incorporating a learned motion prior. Motions are compressed using a residual‑quantized variational autoencoder, and distillation updates only a latent bank while keeping the decoder frozen, ensuring synthetic motions remain plausible. Experiments on Human3.6M, CMU, and 3DPW datasets demonstrate that this method outperforms direct gradient matching in most settings and yields more realistic synthetic motions.
arXiv:2608.22112v1 Announce Type: cross Abstract: We present a machine learning framework for identifying sparse, interpretable models of dynamical systems directly from time-series data. Our approac...
WorldTS is a new forecasting framework that models latent dynamics conditioned on multimodal covariates to improve time‑series prediction. It uses a two‑stage training process: first learning latent state dynamics from historical data and covariates, then training a decoder to map predicted latent states back to future observations. Experiments on 21 real‑world datasets demonstrate the effectiveness of this approach.
arXiv:2412. 12036v2 Announce Type: replace Abstract: System identification, the process of deriving mathematical models of dynamical systems from observed input-output data, has undergone a paradigm shift with the advent of learning-based methods.
arXiv:2508. 12448v2 Announce Type: replace-cross Abstract: In-context learning (ICL) lets large language models (LLMs) solve new tasks from prompts alone, across an ever-widening range of domains, yet the mechanisms underlying this ability remain poorly understood.
arXiv:2601. 22328v2 Announce Type: replace Abstract: Real-world scientific systems are rarely observed through complete, regularly sampled state trajectories.