dynamical systems
In the context of AI, dynamical systems are mathematical models that describe the evolution of a system over time, which can be used in modeling complex phenomena, making predictions, and understanding the behavior of agents in various environments.
- Align-DA: Align Score-based Atmospheric Data Assimilation with Multiple Preferences
- CausalDynamics: A large‐scale benchmark for structural discovery of dynamical causal models
- Constrained Optimization From a Control Perspective via Feedback Linearization
- Environment Inference for Learning Generalizable Dynamical System
- Go With the Flow: Fast Diffusion for Gaussian Mixture Models
- In-context Learning of Linear Dynamical Systems with Transformers: Approximation Bounds and Depth-separation
- LaM-SLidE: Latent Space Modeling of Spatial Dynamical Systems via Linked Entities
- Learning Stochastic Multiscale Models
- Lost in Latent Space: An Empirical Study of Latent Diffusion Models for Physics Emulation
- One Filters All: A Generalist Filter For State Estimation
- Position: Biology is the Challenge Physics-Informed ML Needs to Evolve
- Predictability Enables Parallelization of Nonlinear State Space Models
- Predicting partially observable dynamical systems via diffusion models with a multiscale inference scheme
- RNNs perform task computations by dynamically warping neural representations
- Revisiting Orbital Minimization Method for Neural Operator Decomposition
- SING: SDE Inference via Natural Gradients
- True Zero-Shot Inference of Dynamical Systems Preserving Long-Term Statistics
- Two‑Stage Learning of Stabilizing Neural Controllers via Zubov Sampling and Iterative Domain Expansion