Yuxin Wang

Lifelong Embedding Learning and Transfer for Growing Knowledge Graphs

2022 · arXiv (Cornell University)

Existing knowledge graph (KG) embedding models have primarily focused on static KGs. However, real-world KGs do not remain static, but rather evolve and grow in tandem with the development of KG applications. Consequently, new facts …

Master-Slave INS Transfer Alignment Based on State-Transformation Extended Kalman Filter

2023

In this study, a fast transfer alignment algorithm that fuses the velocity-attitude-position of the Master-Slave INS is proposed. A state-transformation extended Kalman filter (ST-EKF) with better filtering robustness is used instead of the conventional extended …

Reinforcement Learning with Decoupled State Representation for Robot Manipulations

2024 · Neural Processing Letters

Abstract Deep reinforcement learning has significantly advanced robot manipulations by providing an alternative solution for designing control strategies using raw images as direct inputs. While images offer additional environmental information, the end-to-end policy training manner …

A Survey of Deep Learning Techniques for Neural Machine Translation

2020 · arXiv (Cornell University)

In recent years, natural language processing (NLP) has got great development with deep learning techniques. In the sub-field of machine translation, a new approach named Neural Machine Translation (NMT) has emerged and got massive attention …