Proceedings of the National Academy of Sciences of the United States of America
40343991
What mechanisms underlie linguistic generalization in large language models (LLMs)? This question has attracted considerable attention, with most studies analyzing the extent to which the language skills of LLMs resemble rules. As of yet, it is not k...
High-resolution imagery and deep learning models have gained increasing importance in land-use mapping. In recent years, several new deep learning network modeling methods have surfaced. However, there has been a lack of a clear understanding of the ...
Proceedings of the National Academy of Sciences of the United States of America
38913896
Humans and animals excel at generalizing from limited data, a capability yet to be fully replicated in artificial intelligence. This perspective investigates generalization in biological and artificial deep neural networks (DNNs), in both in-distribu...
Neural networks : the official journal of the International Neural Network Society
39084171
Person re-identification (ReID) has made good progress in stationary domains. The ReID model must be retrained to adapt to new scenarios (domains) as they emerge unexpectedly, which leads to catastrophic forgetting. Continual learning trains the mode...
Proceedings of the National Academy of Sciences of the United States of America
38968113
Humans and animals routinely infer relations between different items or events and generalize these relations to novel combinations of items. This allows them to respond appropriately to radically novel circumstances and is fundamental to advanced co...
Neural networks : the official journal of the International Neural Network Society
39153401
Domain Generalization (DG) focuses on the Out-Of-Distribution (OOD) generalization, which is able to learn a robust model that generalizes the knowledge acquired from the source domain to the unseen target domain. However, due to the existence of the...
Neural networks : the official journal of the International Neural Network Society
39662199
Adversarial pairwise learning has become the predominant method to enhance the discrimination ability of models against adversarial attacks, achieving tremendous success in various application fields. Despite excellent empirical performance, adversar...
Neural networks : the official journal of the International Neural Network Society
39426036
Graph Neural Networks (GNNs) have emerged as a powerful tool for data-driven learning on various graph domains. They are usually based on a message-passing mechanism and have gained increasing popularity for their intuitive formulation, which is clos...
Neural networks : the official journal of the International Neural Network Society
40112637
Neural models produce promising results when solving Vehicle Routing Problems (VRPs), but may often fall short in generalization. Recent attempts to enhance model generalization often incur unnecessarily large training cost or cannot be directly appl...
Neural networks : the official journal of the International Neural Network Society
40068498
Face forgery detection aims to distinguish AI generated fake faces with real faces. With the rapid development of face forgery creation algorithms, a large number of generative models have been proposed, which gradually reduce the local distortion ph...