Results for "trigger-based behavior"

Detects trigger phrases in audio streams.

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.

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

Probabilistic energy-based neural network with hidden variables.

Continuous loop adjusting actions based on state feedback.

Sampling-based motion planner.

The text (and possibly other modalities) given to an LLM to condition its output behavior.

Crafting prompts to elicit desired behavior, often using role, structure, constraints, and examples.

A high-priority instruction layer setting overarching behavior constraints for a chat model.

Updating a pretrained model’s weights on task-specific data to improve performance or adapt style/behavior.

Ensuring model behavior matches human goals, norms, and constraints, including reducing harmful or deceptive outputs.

Rules and controls around generation (filters, validators, structured outputs) to reduce unsafe or invalid behavior.

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

Inputs crafted to cause model errors or unsafe behavior, often imperceptible in vision or subtle in text.

Hidden behavior activated by specific triggers, causing targeted mispredictions or undesired outputs.

Coordinating tools, models, and steps (retrieval, calls, validation) to deliver reliable end-to-end behavior.

Ensuring learned behavior matches intended objective.

Required descriptions of model behavior and limits.

Inferring reward function from observed behavior.

Human-like understanding of physical behavior.

Humans assist or override autonomous behavior.

Inferring human goals from behavior.

Mathematical guarantees of system behavior.

System-level behavior arising from interactions.

Collective behavior without central control.

Signals indicating dangerous behavior.

Models that define an energy landscape rather than explicit probabilities.