AI Agent

Thomson: Continual Learning of Frontier Models for SovereignAI

Thomson：面向主权人工智能的前沿模型持续学习

Shengzhuang Chen, Jerrod Parker, Yejin Bang, Andrew M. Bean, Nabeel Seedat, Stefan Winzeck, Daniil Glazko, Jannik Zgraggen, Fangyi Yu, Scott Arnott, Dietrich Trautmann, Luca Ciuffreda, Guglielmo Bonifazi, Davide Romano, Bradley Bell, Kirsty Fielding, Daniele Giofrè, Tom Zielund, Ipshita Chatterjee, Sneha Murthy Ghantasala, Manpreet Nanreh, John Scoville, Maciej Sakowicz, Wassim Seifeddine, Lukas Thede, Jonathan Richard Schwarz

机构 * Imperial College London（帝国理工学院） ； DatologyAI ； Lambda 纠错

专题命中 其他Agent ：agentic(abstract)；分类 cs.AI

AI总结 该研究提出Thomson，通过对开放权重模型的持续学习，以低预算实现前沿模型性能，可帮助更多机构构建主权人工智能，且在多任务表现优异，几乎消除了遗忘问题。

Comments Open-weight model: this https URL (https://huggingface.co/thomsonreuters/Thomson-1.0-Small)