arXiv AI July 20, 2026 By Felippe Alves, Renato Vicente

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.

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 AI.

arXiv Machine Learning

Aug 4

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

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

efficiency

arXiv Machine Learning

Sep 11

LILA: Calibration-Free Structured Pruning of Large Language Models via Latent Spectral Geometry

LILA (Latent-Informed Layer Analysis) introduces a calibration‑free method for structured pruning of large language models by scoring neuron importance using the Kolmogorov–Smirnov distance between singular value distributions of full and neuron‑ablated feed‑forward network weight matrices. The approach requires no training, calibration data, or auxiliary networks, and outperforms existing methods such as PruneNet and SliceGPT on LLaMA‑2‑7B and Phi‑2 at various sparsity levels. After a single epoch of LoRA fine‑tuning, LILA matches heavily calibrated baselines, and a Neural Tangent Kernel analysis provides theoretical support for its spectral importance criterion. Additionally, LILA can dynamically allocate sparsity budgets, achieving state‑of‑the‑art generative preservation and revealing architectural bottlenecks at higher compression.

By Sankar Behera, Dhruv Singh, Anshika Agnihotri, Raj Kumar Choudhary, Satyadev Ahlawat, Yamuna Prasad

llms reinforcement-learning fine-tuning 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

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 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

One email a morning, machine-written

Related stories

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

LILA: Calibration-Free Structured Pruning of Large Language Models via Latent Spectral Geometry

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

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

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