State of the Art
Current research focuses on advancing various AI models and algorithms, aiming to improve their performance, efficiency, and applicability across diverse domains. Key areas include enhancing deep learning for time series forecasting and image/video processing, developing more efficient motion planning algorithms for robotics and UAVs, and improving the robustness and interpretability of models for tasks like object detection, scene generation, and medical image analysis. These advancements are significant because they address limitations in existing methods, leading to more accurate, efficient, and reliable AI systems with broad applications in healthcare, manufacturing, robotics, and beyond.
Papers
Your Next State-of-the-Art Could Come from Another Domain: A Cross-Domain Analysis of Hierarchical Text Classification
Nan Li, Bo Kang, Tijl De Bie
CREST: An Efficient Conjointly-trained Spike-driven Framework for Event-based Object Detection Exploiting Spatiotemporal Dynamics
Ruixin Mao, Aoyu Shen, Lin Tang, Jun Zhou
Optimizing Plastic Waste Collection in Water Bodies Using Heterogeneous Autonomous Surface Vehicles with Deep Reinforcement Learning
Alejandro Mendoza Barrionuevo, Samuel Yanes Luis, Daniel Gutiérrez Reina, Sergio L. Toral Marín
SA-GNAS: Seed Architecture Expansion for Efficient Large-scale Graph Neural Architecture Search
Guanghui Zhu, Zipeng Ji, Jingyan Chen, Limin Wang, Chunfeng Yuan, Yihua Huang
A Performance Increment Strategy for Semantic Segmentation of Low-Resolution Images from Damaged Roads
Rafael S. Toledo, Cristiano S. Oliveira, Vitor H. T. Oliveira, Eric A. Antonelo, Aldo von Wangenheim
DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs
Jiahui Liu, Zhenkun Cai, Zhiyong Chen, Minjie Wang