Results for "weighted sampling"

Stochastic generation strategies that trade determinism for diversity; key knobs include temperature and nucleus sampling.

Samples from the k highest-probability tokens to limit unlikely outputs.

Samples from the smallest set of tokens whose probabilities sum to p, adapting set size by context.

Sampling from easier distribution with reweighting.

Approximating expectations via random sampling.

Sampling-based motion planner.

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

Mechanism that computes context-aware mixtures of representations; scales well and captures long-range dependencies.

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

Local surrogate explanation method approximating model behavior near a specific input.

A single attention mechanism within multi-head attention.

Monte Carlo method for state estimation.

Chooses which experts process each token.

Tradeoff between safety and performance.

GNN using attention to weight neighbor contributions dynamically.

Predicting borrower default risk.

Inferring the agent’s internal state from noisy sensor data.

Selecting the most informative samples to label (e.g., uncertainty sampling) to reduce labeling cost.

Scales logits before sampling; higher increases randomness/diversity, lower increases determinism.

Sampling multiple outputs and selecting consensus.

Learning from data generated by a different policy.

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

Systematic differences in model outcomes across groups; arises from data, labels, and deployment context.

Search algorithm for generation that keeps top-k partial sequences; can improve likelihood but reduce diversity.

Artificially created data used to train/test models; helpful for privacy and coverage, risky if unrealistic.

Raw model outputs before converting to probabilities; manipulated during decoding and calibration.

Structured dataset documentation covering collection, composition, recommended uses, biases, and maintenance.

Variability introduced by minibatch sampling during SGD.

Balancing learning new behaviors vs exploiting known rewards.

Models that learn to generate samples resembling training data.