FlashKAN introduces a new implementation of Kolmogorov‑Arnold Networks (KANs) that replaces the traditional Cox‑de Boor recursion with a truncated power form, allowing each uniform cubic B‑spline to be expressed as five shifted −(x)−^3 terms. The torch.compile‑fused implementation collapses these operations into a single GPU kernel, eliminating recursion, span lookup, and scatter‑gather steps. Additionally, the method includes a bounded‑coordinate stabilization to clamp inputs to [0, k+1], preventing catastrophic cancellation, and provides a production‑ready, open‑source package (pip install flashkan) as a drop‑in replacement for existing KAN layers.
By Naveen Mysore
arXiv:2608. 01490v1 Announce Type: new Abstract: Binarizing a polynomial Kolmogorov--Arnold Network (KAN) not only changes parameter precision, but also alters the function space available to each layer.
By Kazi Ahmed Asif Fuad, Lizhong Chen
arXiv:2607. 15525v1 Announce Type: cross Abstract: Kolmogorov--Arnold Networks (KANs) replace fixed node activations with learned one-dimensional edge functions, offering an explicit interface for interpretation and a possible alternative to transformer feed-forward networks.
By Felippe Alves, Renato Vicente
arXiv:2512. 12850v3 Announce Type: replace-cross Abstract: Low-latency, resource-efficient neural network inference on FPGAs is essential for applications demanding real-time capability and low power.
By Duc Hoang, Aarush Gupta, Philip Harris
arXiv:2609.26067v1 Announce Type: new
Abstract: Kolmogorov--Arnold Networks (KANs) replace scalar edge weights with learnable univariate functions, increasing flexibility but also parameter memory be...
By Kazi Ahmed Asif Fuad, Lizhong Chen
arXiv:2608. 00737v1 Announce Type: new Abstract: Hard-constrained recurrent physics-informed networks (HRPINNs) embed known dynamics inside a recurrent numerical integrator and restrict a neural branch to learning only the residual dynamics that the first-principles model does not capture.
By Enzo Nicolas Spotorno, Josafat Leal Filho
arXiv:2604. 21174v3 Announce Type: replace-cross Abstract: Kolmogorov-Arnold Networks (KANs) replace fixed activations with learnable univariate edge functions whose behavior depends strongly on the chosen basis.
By Amir Noorizadegan, Sifan Wang, Leevan Ling
arXiv:2512. 09084v3 Announce Type: replace Abstract: The Kolmogorov-Arnold representation theorem offers a theoretical alternative to Multi-Layer Perceptrons (MLPs) by placing learnable univariate functions on edges rather than nodes.
By Oscar Eliasson
arXiv:2608. 12194v1 Announce Type: cross Abstract: Kolmogorov-Arnold Networks (KANs) enhance nonlinear function approximation by replacing scalar weights with learnable univariate functions.
By Zhao Su, Yuxin Xia, Haoran Li, Jun Shen, Qi Zhu, Qingguo Zhou, Binbin Yong
arXiv:2609.15274v1 Announce Type: new
Abstract: Kolmogorov-Arnold Networks (KANs) with spline activations have recently shown promise for interpretable function approximation. Distance-Aware Error fo...
By Masoud Ataei, Mohammad Javad Khojasteh, Vikas Dhiman
arXiv:2602. 02056v3 Announce Type: replace-cross Abstract: Ultrafast online learning is essential for high-frequency systems, such as controls for quantum computing and nuclear fusion, where adaptation must occur on sub-microsecond timescales.
By Duc Hoang, Aarush Gupta, Philip Harris
arXiv:2608. 25807v1 Announce Type: new Abstract: Kolmogorov-Arnold Networks (KANs) replace fixed activations in deep architectures with learnable univariate edge functions, making the choice of edge parametrisation central.
By K S Sesh Kumar