5 papers
RAG or Learning? Understanding the Limits of LLM Adaptation under Continuous Knowledge Drift in the Real World
Hanbing Liu, Lang Cao, Yang Li
Large language models (LLMs) acquire most of their knowledge during pretraining, which ties them to a fixed snapshot of the world and makes adaptation to continuously evolving know…
Reinforced Domain Selection for Continuous Domain Adaptation
Hanbing Liu, Huaze Tang, Yanru Wu +2
Continuous Domain Adaptation (CDA) effectively bridges significant domain shifts by progressively adapting from the source domain through intermediate domains to the target domain.…
Understanding Knowledge Transferability for Transfer Learning: A Survey
Haohua Wang, Jingge Wang, Zijie Zhao +9
Transfer learning has become an essential paradigm in artificial intelligence, enabling the transfer of knowledge from a source task to improve performance on a target task. This a…
Exploiting Task Relationships in Continual Learning via Transferability-Aware Task Embeddings
Yanru Wu, Jianning Wang, Xiangyu Chen +4
Continual learning (CL) has been a critical topic in contemporary deep neural network applications, where higher levels of both forward and backward transfer are desirable for an e…
Enhancing Continuous Domain Adaptation with Multi-Path Transfer Curriculum
Hanbing Liu, Jingge Wang, Xuan Zhang +2
Addressing the large distribution gap between training and testing data has long been a challenge in machine learning, giving rise to fields such as transfer learning and domain ad…