Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Transformer learns the cross-task prior and regularization for in-context learning
Fei Lu, Yue Yu
Transformers have shown a remarkable ability for in-context learning (ICL), making predictions based on contextual examples. However, while theoretical analyses have explored this…
cs.LG2024
Nonlocal Attention Operator: Materializing Hidden Knowledge Towards Interpretable Physics Discovery
Yue Yu, Ning Liu, Fei Lu +3
Despite the recent popularity of attention-based neural architectures in core AI fields like natural language processing (NLP) and computer vision (CV), their potential in modeling…