Results for "compute-data-performance"

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

Architecture that retrieves relevant documents (e.g., from a vector DB) and conditions generation on them to reduce hallucinations.

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

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

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

A hidden variable influences both cause and effect, biasing naive estimates of causal impact.

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

System design where humans validate or guide model outputs, especially for high-stakes decisions.

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

Constraining model outputs into a schema used to call external APIs/tools safely and deterministically.

AI focused on interpreting images/video: classification, detection, segmentation, tracking, and 3D understanding.

Error due to sensitivity to fluctuations in the training dataset.

A measure of randomness or uncertainty in a probability distribution.

The range of functions a model can represent.

Encodes token position explicitly, often via sinusoids.

Models trained to decide when to call tools.

Categorizing AI applications by impact and regulatory risk.

Logged record of model inputs, outputs, and decisions.

Graphs containing multiple node or edge types with different semantics.

Compromising AI systems via libraries, models, or datasets.

Combining signals from multiple modalities.

Extension of convolution to graph domains using adjacency structure.

Simultaneous Localization and Mapping for robotics.

Predicting future values from past observations.

Models time evolution via hidden states.

Monte Carlo method for state estimation.

Low-latency prediction per request.

Models accessible only via service APIs.

Set of vectors closed under addition and scalar multiplication.

Vector whose direction remains unchanged under linear transformation.