Results for "preference optimization"

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

Maliciously inserting or altering training data to implant backdoors or degrade performance.

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

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

Assigning labels per pixel (semantic) or per instance (instance segmentation) to map object boundaries.

Measures how much information an observable random variable carries about unknown parameters.

Estimating parameters by maximizing likelihood of observed data.

A narrow minimum often associated with poorer generalization.

A wide basin often correlated with better generalization.

Gradually increasing learning rate at training start to avoid divergence.

Attention mechanisms that reduce quadratic complexity.

Recovering training data from gradients.

Inferring sensitive features of training data.

Simultaneous Localization and Mapping for robotics.

Recovering 3D structure from images.

Predicting future values from past observations.

Using production outcomes to improve models.

Cost of model training.

Measures similarity and projection between vectors.

Sensitivity of a function to input perturbations.

Matrix of first-order derivatives for vector-valued functions.

Direction of steepest ascent of a function.

Measures joint variability between variables.

Maximizing reward without fulfilling real goal.

Learned subsystem that optimizes its own objective.

Using limited human feedback to guide large models.

Explicit output constraints (format, tone).

Asking model to review and improve output.

Breaking tasks into sub-steps.

Requirement to provide explanations.