arXiv Machine Learning August 4, 2026 By Kazi Ahmed Asif Fuad, Lizhong Chen

BiKAN: Restoring Collapsed Basis of Binary Kolmogorov--Arnold Networks

Read the original on arXiv Machine Learning →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 20

Kolmogorov--Arnold Networks for Small Language Models

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

llms efficiency benchmarks

arXiv Machine Learning

Sep 23

FuncCode: Compressing Kolmogorov--Arnold Networks in Function Space with Hardware-Aware Quantization

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

efficiency benchmarks

arXiv Machine Learning

Aug 4

SparseKAN: Compressing Kolmogorov--Arnold Networks Across Basis Functions, Neurons, and Bits

arXiv:2608. 00859v1 Announce Type: new Abstract: Kolmogorov--Arnold Networks (KANs) replace scalar edge weights with learnable univariate functions parameterized by multiple basis coefficients.

By Kazi Ahmed Asif Fuad, Lizhong Chen

efficiency

arXiv Machine Learning

Jun 3

Pruning Deep Neural Networks via the Marchenko--Pastur Distribution

arXiv:2606. 02608v1 Announce Type: new Abstract: We study a Marchenko--Pastur (MP) random-matrix approach to pruning deep neural networks with very small post-pruning fine-tuning budgets.

By Leonid Berlyand, Theo Bourdais, Houman Owhad, Yitzchak Shmalo

fine-tuning efficiency

arXiv Machine Learning

Sep 3

FlashKAN: B-Spline KANs via Truncated Power Form

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 Machine Learning

Aug 27

Geometry-Constrained Kolmogorov-Arnold Networks: Learning Edge Geometry via Banach Duality

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

benchmarks

One email a morning, machine-written

Related stories

Kolmogorov--Arnold Networks for Small Language Models

FuncCode: Compressing Kolmogorov--Arnold Networks in Function Space with Hardware-Aware Quantization

SparseKAN: Compressing Kolmogorov--Arnold Networks Across Basis Functions, Neurons, and Bits

Pruning Deep Neural Networks via the Marchenko--Pastur Distribution

FlashKAN: B-Spline KANs via Truncated Power Form

Geometry-Constrained Kolmogorov-Arnold Networks: Learning Edge Geometry via Banach Duality