Results for "model-based"

A measure of a model class’s expressive capacity based on its ability to shatter datasets.

A function measuring prediction error (and sometimes calibration), guiding gradient-based optimization.

Architecture based on self-attention and feedforward layers; foundation of modern LLMs and many multimodal models.

Retrieval based on embedding similarity rather than keyword overlap, capturing paraphrases and related concepts.

A preference-based training method optimizing policies directly from pairwise comparisons without explicit RL loops.

Probabilistic energy-based neural network with hidden variables.

Continuous loop adjusting actions based on state feedback.

Sampling-based motion planner.

Models that define an energy landscape rather than explicit probabilities.

Learns the score (∇ log p(x)) for generative sampling.

Exact likelihood generative models using invertible transforms.

RL using learned or known environment models.

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

A high-capacity language model trained on massive corpora, exhibiting broad generalization and emergent behaviors.

Model trained to predict human preferences (or utility) for candidate outputs; used in RLHF-style pipelines.

Central system to store model versions, metadata, approvals, and deployment state.

Reconstructing a model or its capabilities via API queries or leaked artifacts.

Framework for identifying, measuring, and mitigating model risks.

Embedding signals to prove model ownership.

Probabilistic model for sequential data with latent states.

Generative model that learns to reverse a gradual noise process.

Diffusion model trained to remove noise step by step.

Formal model linking causal mechanisms and variables.

Required descriptions of model behavior and limits.

Optimizes future actions using a model of dynamics.

RL without explicit dynamics model.

Learned model of environment dynamics.

Learning where data arrives sequentially and the model updates continuously, often under changing distributions.

Training one model on multiple tasks simultaneously to improve generalization through shared structure.

A mismatch between training and deployment data distributions that can degrade model performance.