Showing cs.LGShow all
3 papers · 1 filter
cs.LG2025
INCPrompt: Task-Aware incremental Prompting for Rehearsal-Free Class-incremental Learning
Zhiyuan Wang, Xiaoyang Qu, Jing Xiao +2
This paper introduces INCPrompt, an innovative continual learning solution that effectively addresses catastrophic forgetting. INCPrompt's key innovation lies in its use of adaptiv…
cs.LG2025
P2DT: Mitigating Forgetting in task-incremental Learning with progressive prompt Decision Transformer
Zhiyuan Wang, Xiaoyang Qu, Jing Xiao +2
Catastrophic forgetting poses a substantial challenge for managing intelligent agents controlled by a large model, causing performance degradation when these agents face new tasks.…
cs.LG2024
Task-agnostic Decision Transformer for Multi-type Agent Control with Federated Split Training
Zhiyuan Wang, Bokui Chen, Xiaoyang Qu +3
With the rapid advancements in artificial intelligence, the development of knowledgeable and personalized agents has become increasingly prevalent. However, the inherent variabilit…