arXiv Machine Learning August 4, 2026 By Enzo Nicolas Spotorno, Josafat Leal Filho

An Embedded RISC-V Evaluation of Kolmogorov--Arnold Networks in Hard-Constrained Recurrent Physics-Informed Models

Read the original on arXiv Machine Learning →

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.

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.

efficiency

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

Jun 16

QuantKAN: A Unified Quantization Framework for Kolmogorov Arnold Networks

arXiv:2511. 18689v3 Announce Type: replace Abstract: Kolmogorov--Arnold Networks (KANs) replace linear weights with spline-based functions, offering strong expressivity but posing challenges for low-precision deployment due to heterogeneous parameter distributions.

By Kazi Ahmed Asif Fuad, Lizhong Chen

efficiency benchmarks

arXiv AI

Jun 30

Agile Reinforcement Learning through Separable Neural Architecture and Applications

arXiv:2601. 23225v2 Announce Type: replace-cross Abstract: Deep reinforcement learning (RL) is increasingly deployed in resource-constrained environments, yet go-to function approximators - multilayer perceptrons (MLPs) - are often parameter-inefficient due to an imperfect inductive bias for the smooth structure of many value functions.

By Rajib Mostakim, Reza T. Batley, Sourav Saha

reinforcement-learning efficiency benchmarks safety

arXiv AI

Aug 18

ER-KANs: Efficient and Robust Kolmogorov-Arnold Networks for Data-Scarce Scientific Machine Learning

arXiv:2608. 14773v1 Announce Type: cross Abstract: The efficient-KAN literature---covering Chebyshev, wavelet, and radial-basis-function variants of the original Kolmogorov-Arnold Network---has been benchmarked almost entirely on clean data.

By Harshil Lodhiya

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

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

One email a morning, machine-written

Related stories

Kolmogorov--Arnold Networks for Small Language Models

QuantKAN: A Unified Quantization Framework for Kolmogorov Arnold Networks

Agile Reinforcement Learning through Separable Neural Architecture and Applications

ER-KANs: Efficient and Robust Kolmogorov-Arnold Networks for Data-Scarce Scientific Machine Learning

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

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