Results for "latent space"

Diffusion performed in latent space for efficiency.

Modeling environment evolution in latent space.

Model that compresses input into latent space and reconstructs it.

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

Space of all possible robot configurations.

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

Probabilistic model for sequential data with latent states.

Autoencoder using probabilistic latent variables and KL regularization.

The shape of the loss function over parameter space.

Encodes positional information via rotation in embedding space.

Temporary reasoning space (often hidden).

All possible configurations an agent may encounter.

Set of all actions available to the agent.

Models time evolution via hidden states.

Set of vectors closed under addition and scalar multiplication.