Kolmogorov-Arnold Networks
PulseAugur coverage of Kolmogorov-Arnold Networks — every cluster mentioning Kolmogorov-Arnold Networks across labs, papers, and developer communities, ranked by signal.
- instance of alphaXiv 90%
- instance of Gotit.pub 90%
- instance of ScienceCast 90%
- instance of Manchester Literary and Philosophical Society 90%
- instance of Kolmogorov-Arnold representation theorem 90%
- instance of Influence Flower 90%
- instance of CatalyzeX 90%
- developed ScienceCast 90%
- instance of B-spline 90%
- developed CatalyzeX Code Finder for Papers 90%
- instance of Chebyshev 90%
- competes with multilayer perceptron 70%
- 2026-08-12 research_milestone A new method, FS-JEPA, was proposed to improve KANs for medical image segmentation, achieving state-of-the-art results. source
7 day(s) with sentiment data
-
New method restores distance-awareness in high-dimensional KANs
Researchers have identified a failure mode in Distance-Aware Error for Kolmogorov Networks (DAREK), a method for uncertainty quantification in spline-activated Kolmogorov-Arnold Networks (KANs). In high-dimensional sett…
-
Kolmogorov-Arnold Networks show strong scalability in HPC training
A new research paper analyzes the scalability of training Kolmogorov-Arnold Networks (KANs) on high-performance computing systems. The study, conducted on the FinisTerrae III supercomputer using up to 8 NVIDIA A100 GPUs…
-
Kolmogorov-Arnold stability for discontinuous functions explored in new paper
A new paper explores the stability of the Kolmogorov-Arnold representation theorem (KART) when applied to discontinuous and unbounded functions. The research specifically investigates how adversarial reparameterizations…
-
New AI framework forecasts clinical trajectories with joint probabilistic modeling
Researchers have developed PGP-Clinical-TimeKAN, a novel framework for forecasting clinical trajectories by jointly predicting multivariate physiological data. This method incorporates missingness-aware temporal encoder…
-
Developer releases RWKV-7 adapter with KANs for faithful prose rewriting
A developer has created an open-source adapter for the RWKV-7 language model, named RWKV-7 KAN Humanizer v7.2, which aims to improve prose readability without altering factual content. This adapter utilizes Kolmogorov-A…
-
New AI framework enhances interpretable object detection with trustworthy confidence scores
Researchers have developed a novel framework for interpretable object detection using Kolmogorov-Arnold networks and vision-language foundation models. This approach aims to enhance the trustworthiness of AI systems by …
-
New Transformer Framework Predicts Blood Pressure Non-Invasively
Researchers have developed a novel hybrid Transformer framework designed to predict blood pressure non-invasively and continuously. This framework utilizes sequences of physiological and demographic features, rather tha…
-
FlashKAN speeds up Kolmogorov-Arnold Networks with fused GPU kernel
Researchers have introduced FlashKAN, a novel implementation of Kolmogorov-Arnold Networks (KANs) that significantly speeds up the forward-pass computation. By replacing the traditional Cox-de Boor recursion with a trun…
-
RecKAN introduces learnable recursive polynomial basis for enhanced neural networks
Researchers have introduced RecKAN, a novel approach to Kolmogorov-Arnold Networks (KANs) that enhances their ability to learn complex functions. Unlike previous KAN variants that use fixed bases for their learnable fun…
-
Kolmogorov-Arnold Networks robustness against adversarial translations explored
A new paper explores the robustness of the Kolmogorov-Arnold representation theorem (KART) when applied to neural networks, specifically Kolmogorov-Arnold Networks (KANs). The research provides a constructive proof for …
-
New AI framework enhances pediatric tumor diagnosis with multi-scale image analysis
Researchers have developed CoPath, a novel framework designed for accurate and lightweight diagnosis of peripheral neuroblastic tumors (pNTs) using pathological images. CoPath integrates CoHisNet, a multi-scale feature-…
-
Geometry-Constrained KANs Learn Adaptive Edge Functions for Symbolic Regression
Researchers have developed geometry-constrained Kolmogorov-Arnold Networks (KANs) that learn edge geometry through a scalar exponent 'p'. This approach allows for adaptive responses, ranging from sharp, threshold-like b…
-
New benchmark evaluates Kolmogorov-Arnold Network robustness against adversarial attacks
Researchers have developed KAN-Robust-Bench, a new benchmark designed to evaluate the robustness of Kolmogorov-Arnold Networks (KANs) against adversarial evasion attacks. The study explores both certified and empirical …
-
AI models benchmarked for real-time tokamak plasma prediction
Researchers have developed an AI surrogate modeling framework to predict tokamak plasma equilibrium in real-time, addressing the computational cost of traditional Grad-Shafranov solvers. The study benchmarks five neural…
-
Core-KAN: Continuous Vision Kernels with Kolmogorov-Arnold Networks Unveiled
Researchers have introduced Core-KAN, a novel continuous convolution operator designed to enhance computer vision tasks. This operator, based on Kolmogorov-Arnold Networks, decouples geometric scale adaptation from cont…
-
New Polar MKAN Architecture Enhances Interpretable RF Fingerprinting
Researchers have introduced Polar Monotonic Kolmogorov-Arnold Networks (Polar MKAN), a novel deep learning architecture designed for interpretable radio frequency (RF) fingerprinting. This method aims to overcome the op…
-
New KAN method anatomizes Pythia-Herwig differences in physics event generation
Researchers have developed a new method using additive Kolmogorov-Arnold Networks (KANs) to analyze the differences between high-energy physics event generators like Pythia and Herwig. This approach allows for a staged …
-
ER-KANs: New AI Architecture Boosts Robustness in Data-Scarce Scientific ML
Researchers have introduced ER-KANs, a new type of Kolmogorov-Arnold Network designed for data-scarce scientific machine learning tasks. Unlike existing variants such as ChebyKAN and vanilla KAN, ER-KAN demonstrates sig…
-
New CNQ framework ensures valid ordering for survival prediction
Researchers have developed a new framework called Censored Non-crossing Quantile (CNQ) for survival analysis, designed to address limitations in existing methods for handling censored data. This framework ensures that e…
-
Kolmogorov-Arnold Networks show promise in satellite land classification
Researchers have evaluated the effectiveness of Kolmogorov-Arnold Networks (KANs) for land classification using multispectral satellite imagery. In a study comparing KANs with random forest and multilayer perceptron mod…