Abstract: Sparse Bayesian learning (SBL) is an advanced statistical framework that dominantly enhances the sparse features of targets of interest in radar imagery. A widely adopted strategy for ...

Abstract: Sparse matrix-vector multiplication (SpMV) is a fundamental operation in machine learning, scientific computing, and graph algorithms. In this paper, we investigate the space, time, and ...

TensorRT Edge-LLM is NVIDIA's high-performance C++ inference runtime for Large Language Models (LLMs) and Vision-Language Models (VLMs) on embedded platforms. It enables efficient deployment of ...

Dual-Level Refinement (DLR) with CLIP for Few-Shot Learning. This project implements advanced multi-module fusion techniques for improving CLIP performance on few-shot learning tasks through ...