Rethinking Vision Architectures with Gated Linear Attention and KAN
cs.CV
Submitted: 2026-09-18
Updated: 2026-09-29
Code: https://github.com/mehizelali/linear-kan-transformer
Terminology
Sources
- Convolutional Kolmogorov-Arnold Networks
- MatrixKAN: Parallelized Kolmogorov-Arnold Network
- Vision Transformers Need Registers
- Hyb-KAN ViT: Hybrid Kolmogorov-Arnold Networks Augmented Vision Transformer
- Kolmogorov-Arnold Networks are Radial Basis Function Networks
- FlashKAT: Understanding and Addressing Performance Bottlenecks in the Kolmogorov-Arnold Transformer
- Chebyshev Polynomial-Based Kolmogorov-Arnold Networks: An Efficient Architecture for Nonlinear Function Approximation
- RoFormer: Enhanced Transformer with Rotary Position Embedding
- DeiT III: Revenge of the ViT
- ViT-5: Vision Transformers for The Mid-2020s
- Gated Linear Attention Transformers with Hardware-Efficient Training
- Kolmogorov-Arnold Transformer
- Vision KAN: Towards an Attention-Free Backbone for Vision with Kolmogorov-Arnold Networks
- Vision Transformer Pruning
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models