Abstract: Few-shot learning seeks to recognize novel classes from limited examples. Model-agnostic meta-learning (MAML), known for its simplicity and flexibility, learns an effective initialization ...

Abstract: The rapid adoption of large language models (LLMs), such as ChatGPT, in education has intensified the need to differentiate artificial intelligence (AI)-generated from human-authored student ...

New research suggests that the guessing-with-feedback exercises found in language learning apps and programs are effective.

Designing inquiry around student curiosity allows them learn language, math, and SEL skills through investigations of their ...