Results for "user modeling"

Using same parameters across different parts of a model.

Prevents attention to future tokens during training/inference.

Allows model to attend to information from different subspaces simultaneously.

Routes inputs to subsets of parameters for scalable capacity.

Formal framework for sequential decision-making under uncertainty.

Multiple agents interacting cooperatively or competitively.

Coordination arising without explicit programming.

Graphs containing multiple node or edge types with different semantics.

Models that define an energy landscape rather than explicit probabilities.

Probabilistic model for sequential data with latent states.

Models that learn to generate samples resembling training data.

Diffusion performed in latent space for efficiency.

Autoencoder using probabilistic latent variables and KL regularization.

Exact likelihood generative models using invertible transforms.

Two-network setup where generator fools a discriminator.

Changing speaker characteristics while preserving content.

Temporal and pitch characteristics of speech.

Generates audio waveforms from spectrograms.

Repeating temporal patterns.

Belief before observing data.

Eliminating variables by integrating over them.

Differences between training and inference conditions.

Privacy risk analysis under GDPR-like laws.

Storing results to reduce compute.

Hardware components that execute physical actions.

Devices measuring physical quantities (vision, lidar, force, IMU, etc.).

Equations governing how system states change over time.

Mathematical representation of friction forces.

Robots made of flexible materials.

High-fidelity virtual model of a physical system.