REVIEW 6 cited by
Kolmogorov-Arnold Transformer
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Transformers stand as the cornerstone of mordern deep learning. Traditionally, these models rely on multi-layer perceptron (MLP) layers to mix the information between channels. In this paper, we introduce the Kolmogorov-Arnold Transformer (KAT), a novel architecture that replaces MLP layers with Kolmogorov-Arnold Network (KAN) layers to enhance the expressiveness and performance of the model. Integrating KANs into transformers, however, is no easy feat, especially when scaled up. Specifically, we identify three key challenges: (C1) Base function. The standard B-spline function used in KANs is not optimized for parallel computing on modern hardware, resulting in slower inference speeds. (C2) Parameter and Computation Inefficiency. KAN requires a unique function for each input-output pair, making the computation extremely large. (C3) Weight initialization. The initialization of weights in KANs is particularly challenging due to their learnable activation functions, which are critical for achieving convergence in deep neural networks. To overcome the aforementioned challenges, we propose three key solutions: (S1) Rational basis. We replace B-spline functions with rational functions to improve compatibility with modern GPUs. By implementing this in CUDA, we achieve faster computations. (S2) Group KAN. We share the activation weights through a group of neurons, to reduce the computational load without sacrificing performance. (S3) Variance-preserving initialization. We carefully initialize the activation weights to make sure that the activation variance is maintained across layers. With these designs, KAT scales effectively and readily outperforms traditional MLP-based transformers.
Forward citations
Cited by 6 Pith papers
-
Kolmogorov--Arnold Networks for Small Language Models
In small language models, KAN feed-forward blocks are auditable and pruneable, but on standardized benchmarks and scale tests they show no consistent accuracy, quality, or latency advantage over MLP baselines.
-
The AudioMOS Challenge 2025
The first AudioMOS challenge compared automatic predictors of human quality scores for synthetic audio across three tracks, and most of the 24 participating teams outperformed the organizers' baselines.
-
Improving Memory Efficiency for Training KANs via Meta Learning
MetaKANs generates each KAN activation function from a shared prompt-conditioned meta-learner, cutting trainable parameters toward MLP level while retaining comparable or better accuracy on tested benchmarks.
-
Toroidal area-preserving parameterizations of genus-one closed surfaces
Four Riemannian optimization algorithms (projected/Riemannian gradient and conjugate gradient) are proposed to compute toroidal area-preserving parameterizations by minimizing stretch energy on a power manifold of ring tori.
-
"KAN you hear me?" Exploring Kolmogorov-Arnold Networks for Spoken Language Understanding
Placing a KAN layer between two linear layers improves spoken language understanding accuracy over linear-only baselines on several speech-intent datasets.
-
Pushing the Performance of Synthetic Speech Detection with Kolmogorov-Arnold Networks and Self-Supervised Learning Models
Swapping the MLP projector for a GR-KAN layer in XLSR-Conformer reduces equal error rates on ASVspoof 2021 LA and DF, reaching 0.70% EER on the variable-length LA set.
Discussion (0). Sign in to comment.