Results for "probability over text"
Observing model inputs/outputs, latency, cost, and quality over time to catch regressions and drift.
Persistent directional movement over time.
Architecture based on self-attention and feedforward layers; foundation of modern LLMs and many multimodal models.
Mechanism that computes context-aware mixtures of representations; scales well and captures long-range dependencies.
Human or automated process of assigning targets; quality, consistency, and guidelines matter heavily.
Inputs crafted to cause model errors or unsafe behavior, often imperceptible in vision or subtle in text.
Attacks that manipulate model instructions (especially via retrieved content) to override system goals or exfiltrate data.
Models that process or generate multiple modalities, enabling vision-language tasks, speech, video understanding, etc.
AI subfield dealing with understanding and generating human language, including syntax, semantics, and pragmatics.
Prevents attention to future tokens during training/inference.
Combining signals from multiple modalities.
Generates audio waveforms from spectrograms.
Attention between different modalities.
AI supporting legal research, drafting, and analysis.
A model is PAC-learnable if it can, with high probability, learn an approximately correct hypothesis from finite samples.
Probability of treatment assignment given covariates.
Two-network setup where generator fools a discriminator.
Sample mean converges to expected value.
Variable whose values depend on chance.
Sampling from easier distribution with reweighting.
Predicting borrower default risk.
Raw model outputs before converting to probabilities; manipulated during decoding and calibration.
Model-generated content that is fluent but unsupported by evidence or incorrect; mitigated by grounding and verification.
Converts logits to probabilities by exponentiation and normalization; common in classification and LMs.
Formal framework for sequential decision-making under uncertainty.
Fundamental recursive relationship defining optimal value functions.
Generative model that learns to reverse a gradual noise process.
Simultaneous Localization and Mapping for robotics.
Storing results to reduce compute.
Maximum expected loss under normal conditions.