Results for "learning like humans"

PEFT method injecting trainable low-rank matrices into layers, enabling efficient fine-tuning.

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.

Attacks that infer whether specific records were in training data, or reconstruct sensitive training examples.

Mechanisms for retaining context across turns/sessions: scratchpads, vector memories, structured stores.

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

Measures a model’s ability to fit random noise; used to bound generalization error.

Optimization with multiple local minima/saddle points; typical in neural networks.

Variability introduced by minibatch sampling during SGD.

A narrow minimum often associated with poorer generalization.

Early architecture using learned gates for skip connections.

Chooses which experts process each token.

Empirical laws linking model size, data, compute to performance.

Formal framework for sequential decision-making under uncertainty.

Set of all actions available to the agent.

Expected cumulative reward from a state or state-action pair.

Fundamental recursive relationship defining optimal value functions.

Inferring sensitive features of training data.

Embedding signals to prove model ownership.

Models that define an energy landscape rather than explicit probabilities.

Models that learn to generate samples resembling training data.

Learns the score (∇ log p(x)) for generative sampling.

Assigning category labels to images.

Joint vision-language model aligning images and text.

Predicting future values from past observations.

End-to-end process for model training.

Centralized repository for curated features.

Running predictions on large datasets periodically.

Mathematical foundation for ML involving vector spaces, matrices, and linear transformations.

Using production outcomes to improve models.