PaperFlow: Profiling, Recommending, and Adapting Across Daily Paper Streams
Researchers have developed PaperFlow, a new framework designed to improve scientific paper recommendations by mimicking the dynamic nature of daily reading habits. Unlike static ranking systems, PaperFlow dynamically profiles user interests, recommends papers based on daily streams, and adapts to evolving preferences over time. The framework was tested using a longitudinal benchmark simulating 24 users and 1,200 daily episodes, demonstrating superior performance compared to existing recommendation baselines. AI
IMPACT Improves personalized discovery of research papers, potentially accelerating scientific progress.