Results for "physical modeling"

Learning structure from unlabeled data, such as discovering groups, compressing representations, or modeling data distributions.

The degree to which predicted probabilities match true frequencies (e.g., 0.8 means ~80% correct).

Iterative method that updates parameters in the direction of negative gradient to minimize loss.

A parameterized function composed of interconnected units organized in layers with nonlinear activations.

Attention where queries/keys/values come from the same sequence, enabling token-to-token interactions.

Injects sequence order into Transformers, since attention alone is permutation-invariant.

Generates sequences one token at a time, conditioning on past tokens.

A model that assigns probabilities to sequences of tokens; often trained by next-token prediction.

Stepwise reasoning patterns that can improve multi-step tasks; often handled implicitly or summarized for safety/privacy.

Framework for reasoning about cause-effect relationships beyond correlation, often using structural assumptions and experiments.

Tracking where data came from and how it was transformed; key for debugging and compliance.

Generating speech audio from text, with control over prosody, speaker identity, and style.

Updating beliefs about parameters using observed evidence and prior distributions.

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.