IndexCache, a new sparse attention optimizer, delivers 1.82x faster inference on long-context AI models

Researchers at Tsinghua University and Z.ai built IndexCache to eliminate redundant computation in sparse attention models ...
IEEE

Practical Predefined-Time Formation Tracking of MASVs With Lumped Uncertainties via Estimator-Based Adaptive Fuzzy Control Algorithm

Abstract: This article investigates the problem of practical predefined-time formation tracking for multiple autonomous surface vehicles facing the case of lumped uncertainties (namely, model ...
IEEE

Theoretical and Practical Exploration of Load Forecasting Optimization Algorithm for Smart Grid

Abstract: This study hopes to improve the accuracy and robustness of power load forecasting in smart grids. A load forecasting optimization model based on particle swarm optimization (PSO) is built.
GitHub

LLM4AD: Large Language Model for Algorithm Design

LLM4AD is an open-source Python-based Platform leveraging Large Language Models (LLMs) for Automatic Algorithm Design (AD). Please refer to the paper [LLM4AD] for detailed information, including the ...