AI RESEARCH
UniPrompt-CL: Sustainable Continual Learning in Medical AI with Unified Prompt Pools
arXiv CS.AI
•
ArXi:2508.10954v2 Announce Type: replace-cross Modern AI models are typically trained on static datasets, limiting their ability to continuously adapt to rapidly evolving real-world environments. While continual learning (CL) addresses this limitation, most CL methods are designed for natural images and often underperform or fail to transfer to medical data due to domain bias, institutional constraints, and subtle inter-stage boundaries.