End to End
"End-to-end" systems aim to streamline complex processes by integrating multiple stages into a single, unified model, eliminating the need for intermediate steps and potentially improving efficiency and performance. Current research focuses on applying this approach across diverse fields, utilizing architectures like transformers, reinforcement learning, and spiking neural networks to tackle challenges in autonomous driving, robotics, speech processing, and natural language processing. This approach offers significant potential for improving the accuracy, speed, and robustness of various applications, while also simplifying development and deployment.
Papers
AutoRD: An Automatic and End-to-End System for Rare Disease Knowledge Graph Construction Based on Ontologies-enhanced Large Language Models
Lang Cao, Jimeng Sun, Adam Cross
End-to-End Graph-Sequential Representation Learning for Accurate Recommendations
Vladimir Baikalov, Evgeny Frolov
Post-decoder Biasing for End-to-End Speech Recognition of Multi-turn Medical Interview
Heyang Liu, Yu Wang, Yanfeng Wang
VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning
Shaoyu Chen, Bo Jiang, Hao Gao, Bencheng Liao, Qing Xu, Qian Zhang, Chang Huang, Wenyu Liu, Xinggang Wang
Learning Exceptional Subgroups by End-to-End Maximizing KL-divergence
Sascha Xu, Nils Philipp Walter, Janis Kalofolias, Jilles Vreeken
Any2Graph: Deep End-To-End Supervised Graph Prediction With An Optimal Transport Loss
Paul Krzakala, Junjie Yang, Rémi Flamary, Florence d'Alché-Buc, Charlotte Laclau, Matthieu Labeau
Kernel KMeans clustering splits for end-to-end unsupervised decision trees
Louis Ohl, Pierre-Alexandre Mattei, Mickaël Leclercq, Arnaud Droit, Frédéric Precioso