From Few-Shot Learning to Data-Efficient Intelligence
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (47) · 39834-39835
DOI: 10.1609/aaai.v40i47.41356 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yaqing Wang.
Abstract (Originalsprache)
Modern artificial intelligence performs impressively in data-rich settings but still struggles to learn and adapt from only a few examples—a capability central to human intelligence. My research seeks to understand and enable data-efficient generalization, unifying principles across few-shot learning, meta-learning, in-context learning in large language models (LLMs), and adaptive agent behavior. First, I revisit few-shot learning from a foundational perspective, showing why conventional supervised learning breaks down under sparse data and how prior knowledge enables reliable adaptation. I then discuss how these principles extend to real-world scenarios such as scientific discovery and cold-start recommendation, where data are scarce, costly, or dynamically evolving. Finally, I explore how LLMs perform in-context learning and how their adaptive behaviors connect to meta-learning mechanisms. Building on these insights, I develop data-efficient, preference-adaptive agents that quickly align to user needs with minimal interaction.This talk presents a cohesive view of data-efficient intelligence and outlines future directions toward more reliable, human-like learning systems.
Zitieren
APA
Wang, Y. (2026). From Few-Shot Learning to Data-Efficient Intelligence. Proceedings of the AAAI Conference on Artificial Intelligence, 40(47), 39834-39835. https://doi.org/10.1609/aaai.v40i47.41356
Vancouver
Wang Y. From Few-Shot Learning to Data-Efficient Intelligence. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(47):39834-39835. doi:10.1609/aaai.v40i47.41356
BibTeX
@article{Wang2026,
author = {Wang, Yaqing},
title = {From Few-Shot Learning to Data-Efficient Intelligence},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {47},
pages = {39834--39835},
doi = {10.1609/aaai.v40i47.41356}
}
EUVIMED