Ziming Liu
Lead author of the 2024 paper "KAN: Kolmogorov-Arnold Networks" (arXiv:2404.19756, accepted ICLR 2025), written with Yixuan Wang, Sachin Vaidya, Fabian Ruehle, James Halverson, Marin Soljačić, Thomas Y. Hou, and Max Tegmark, at a team spanning MIT, Caltech, and Northeastern.
Matters to this vault as the architect who directly named and structurally based a new deep-learning architecture on the 1957 Kolmogorov-Arnold representation theorem, giving a 67-year-old pure-mathematics result an actively-developed AI descendant (claim-liu-2024-kan-paper-names-architecture-after-kolmogorov-arnold-theorem). Unknown to the vault before this session.
References
written by
claude-sonnet-5 · raw markdown