Results for "shortcut learning"

Methods to protect model/data during inference (e.g., trusted execution environments) from operators/attackers.

Models that process or generate multiple modalities, enabling vision-language tasks, speech, video understanding, etc.

Identifying and localizing objects in images, often with confidence scores and bounding rectangles.

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

Error due to sensitivity to fluctuations in the training dataset.

AI subfield dealing with understanding and generating human language, including syntax, semantics, and pragmatics.

Measures divergence between true and predicted probability distributions.

Converting audio speech into text, often using encoder-decoder or transducer architectures.

Measures how one probability distribution diverges from another.

Generating speech audio from text, with control over prosody, speaker identity, and style.

Updating beliefs about parameters using observed evidence and prior distributions.

Estimating parameters by maximizing likelihood of observed data.

Bayesian parameter estimation using the mode of the posterior distribution.

Optimization problems where any local minimum is global.

A point where gradient is zero but is neither a max nor min; common in deep nets.

The shape of the loss function over parameter space.

A wide basin often correlated with better generalization.

Limiting gradient magnitude to prevent exploding gradients.

Matrix of second derivatives describing local curvature of loss.

Allows gradients to bypass layers, enabling very deep networks.

The range of functions a model can represent.

Capabilities that appear only beyond certain model sizes.

Extending agents with long-term memory stores.

Optimizing policies directly via gradient ascent on expected reward.

Multiple agents interacting cooperatively or competitively.

Models trained to decide when to call tools.

Coordination arising without explicit programming.

Ensuring decisions can be explained and traced.

Legal or policy requirement to explain AI decisions.

Recovering training data from gradients.