Výsledky vyhledávání - "Liu, Junning"

Report

A Data-Driven Approach to Geometric Modeling of Systems with Low-Bandwidth Actuator Dynamics

Autor: Deng, Siming, Liu, Junning, Datta, Bibekananda, Pantula, Aishwarya, Gracias, David H., Nguyen, Thao D., Bittner, Brian A., Cowan, Noah J.

It is challenging to perform system identification on soft robots due to their underactuated, high-dimensional dynamics. In this work, we present a data-driven modeling framework, based on geometric mechanics (also known as gauge theory) that can be

Externí odkaz: http://arxiv.org/abs/2307.01062

Zobrazit plný text záznamu

Report

Multi-Task Fusion via Reinforcement Learning for Long-Term User Satisfaction in Recommender Systems

Autor: Zhang, Qihua, Liu, Junning, Dai, Yuzhuo, Qi, Yiyan, Yuan, Yifan, Zheng, Kunlun, Huang, Fan, Tan, Xianfeng

Recommender System (RS) is an important online application that affects billions of users every day. The mainstream RS ranking framework is composed of two parts: a Multi-Task Learning model (MTL) that predicts various user feedback, i.e., clicks, li

Externí odkaz: http://arxiv.org/abs/2208.04560

Zobrazit plný text záznamu

Report

Multi-Faceted Hierarchical Multi-Task Learning for a Large Number of Tasks with Multi-dimensional Relations

Autor: Liu, Junning, Xia, Zijie, Lei, Yu, Li, Xinjian, Wang, Xu

There has been many studies on improving the efficiency of shared learning in Multi-Task Learning(MTL). Previous work focused on the "micro" sharing perspective for a small number of tasks, while in Recommender Systems(RS) and other AI applications,

Externí odkaz: http://arxiv.org/abs/2110.13365

Zobrazit plný text záznamu