Abstract: Fusing features from different sources is a critical aspect of many computer vision tasks. Existing approaches can be roughly categorized as parameter-free or learnable operations. However, ...

Abstract: Hypercomplex graph convolutions with higher hypercomplex dimensions can extract more complex features in graphs and features with varying levels of complexity are suited for different ...

2024/11/7 We add reproduction code of the two baseline method in this paper. GlitchMiner is a robust framework designed to detect glitch tokens—tokens that cause unexpected behaviors in large language ...

This repo is the official implementation of Efficient 3D Recognition with Event-driven Spike Sparse Convolution. It currently concludes codes and models for the following tasks: 3D Classification: See ...