Interpretable Next-token Prediction via the Generalized Induction Head
Comments NeurIPS 2025
期刊&会议
Conference on Neural Information Processing Systems · 会议 · Machine Learning
Comments NeurIPS 2025
机构 * Czech Technical University in Prague(布拉格捷克技术大学) ; Czech Institute of Informatics, Robotics and Cybernetics(捷克信息学、机器人学与自动化研究所) ; Faculty of Electrical Engineering(电气工程学院)
Comments NeurIPS 2025 D&B; Web: https://jkulhanek.com/nerfbaselines