PulseAugur / Brief
EN
LIVE 13:58:29

Brief

last 24h
[1/1] 224 sources

Multi-source AI news clustered, deduplicated, and scored 0–100 across authority, cluster strength, headline signal, and time decay.

  1. 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.