In this paper, we tackle the high computational overhead of transformers for lightweight image super-resolution. (SR). Motivated by the observations of self-attention's inter-layer repetition, we ...

Abstract: Graph Convolution Networks (GCNs) have achieved remarkable success in representation of structured graph data. As we know that traditional GCNs are generally defined on the fixed first-order ...

Abstract: In this paper, we present a novel convolution theorem which encompasses the well known convolution theorem in (graph) signal processing as well as the one related to time-varying filters.

KernelOptimizer is an open-source tool that automates CUDA kernel optimization for PyTorch workloads using large language models (LLMs). Inspired by Stanford CRFM’s fast kernel research, it leverages ...