5 papers
When Does Continual Learning Require Learning
Anne Harrington, Nayan Saxena, Michael Murphy +7
As large language models (LLMs) become increasingly capable, the next question is how can we enable models to continually learn? Today, the field largely frames this as a problem o…
Diffusion Models Preferentially Memorize Prototypical Examples or: Why Does My Diffusion Model Love Slop?
Marta Aparicio Rodriguez, Anastasia Borovykh, Grigorios A. Pavliotis +1
Generative models have a persistent limitation: their tendency to memorize training data can create legal liabilities and erode creative diversity. Understanding which samples are…
Generalization in LLM Problem Solving: The Case of the Shortest Path
Yao Tong, Jiayuan Ye, Anastasia Borovykh +1
Whether language models can systematically generalize remains actively debated. Yet empirical performance is jointly shaped by multiple factors such as training data, training para…
Deep Unlearn: Benchmarking Machine Unlearning for Image Classification
Xavier F. Cadet, Anastasia Borovykh, Mohammad Malekzadeh +2
Machine unlearning (MU) aims to remove the influence of particular data points from the learnable parameters of a trained machine learning model. This is a crucial capability in li…
Concept Reachability in Diffusion Models: Beyond Dataset Constraints
Marta Aparicio Rodriguez, Xenia Miscouridou, Anastasia Borovykh
Despite significant advances in quality and complexity of the generations in text-to-image models, prompting does not always lead to the desired outputs. Controlling model behaviou…