Results for "latent dynamics"

Diffusion performed in latent space for efficiency.

Modeling environment evolution in latent space.

The internal space where learned representations live; operations here often correlate with semantics or generative factors.

Model that compresses input into latent space and reconstructs it.

Autoencoder using probabilistic latent variables and KL regularization.

Motion of solid objects under forces.

Automatically learning useful internal features (latent variables) that capture salient structure for downstream tasks.

Motion considering forces and mass.

Predicts next state given current state and action.

Modeling interactions with environment.

Collective behavior without central control.

Generative model that learns to reverse a gradual noise process.

Optimizes future actions using a model of dynamics.

Equations governing how system states change over time.

RL without explicit dynamics model.

Physical form contributes to computation.

Probabilistic energy-based neural network with hidden variables.

Probabilistic model for sequential data with latent states.

Exact likelihood generative models using invertible transforms.

Models time evolution via hidden states.

Decomposes a matrix into orthogonal components; used in embeddings and compression.

Eliminating variables by integrating over them.

Inferring human goals from behavior.

Stored compute or algorithms enabling rapid jumps.

The physical system being controlled.

Software simulating physical laws.

RL using learned or known environment models.

Learned model of environment dynamics.

Competition arises without explicit design.

Agents copy others’ actions.