Nature

Sparse Modeling delivers fast, energy efficient and explainable AI solutions for cutting-edge medical applications

Japanese AI specialist HACARUS Inc. is successfully utilizing its proprietary Sparse Modeling AI technology in joint projects including phenotype drug discovery, medical imaging and ECG monitors for ...
IEEE

Sparse LaneFormer: End-to-End Lane Detection With Sparse Proposals and Interactions

Abstract: Lane detection is a challenging task due to the inherently sparse nature of lanes, which are characterized by their thin and long structures. However, existing lane detection methods often ...
IEEE

Robust Sparse Unmixing via Continuous Mixed Norm to Address Mixed Noise

Abstract: Sparse unmixing, a critical task in hyperspectral image interpretation, aims to identify an optimal subset of endmembers from a predefined library and estimate the fractional abundances for ...
GitHub

BMSSP (Python) — Bounded Multi-Source Shortest Path

An efficient and faithful Python implementation of the Bounded Multi-Source Shortest Path (BMSSP) algorithm, along with baselines using pure-Python Dijkstra and SciPy-accelerated Dijkstra. This ...
GitHub

InstantSfM: Fully Sparse and Parallel Structure-from-Motion

Note: The project requires an NVIDIA GPU with CUDA support. The code is tested on Ubuntu 20.04 with CUDA 12.1 and PyTorch 2.3.1. Windows system is strongly ...