Výsledky vyhledávání - "Zhou Yuanhang"

Report

ECAT: A Entire space Continual and Adaptive Transfer Learning Framework for Cross-Domain Recommendation

Autor: Hou, Chaoqun, Zhou, Yuanhang, Cao, Yi, Liu, Tong

In industrial recommendation systems, there are several mini-apps designed to meet the diverse interests and needs of users. The sample space of them is merely a small subset of the entire space, making it challenging to train an efficient model. In

Externí odkaz: http://arxiv.org/abs/2407.02542

Zobrazit plný text záznamu

Report

JiuZhang 2.0: A Unified Chinese Pre-trained Language Model for Multi-task Mathematical Problem Solving

Autor: Zhao, Wayne Xin, Zhou, Kun, Zhang, Beichen, Gong, Zheng, Chen, Zhipeng, Zhou, Yuanhang, Wen, Ji-Rong, Sha, Jing, Wang, Shijin, Liu, Cong, Hu, Guoping

Although pre-trained language models~(PLMs) have recently advanced the research progress in mathematical reasoning, they are not specially designed as a capable multi-task solver, suffering from high cost for multi-task deployment (\eg a model copy f

Externí odkaz: http://arxiv.org/abs/2306.11027

Zobrazit plný text záznamu

Report

JiuZhang: A Chinese Pre-trained Language Model for Mathematical Problem Understanding

Autor: Zhao, Wayne Xin, Zhou, Kun, Gong, Zheng, Zhang, Beichen, Zhou, Yuanhang, Sha, Jing, Chen, Zhigang, Wang, Shijin, Liu, Cong, Wen, Ji-Rong

This paper aims to advance the mathematical intelligence of machines by presenting the first Chinese mathematical pre-trained language model~(PLM) for effectively understanding and representing mathematical problems. Unlike other standard NLP tasks,

Externí odkaz: http://arxiv.org/abs/2206.06315

Zobrazit plný text záznamu

Report

C2-CRS: Coarse-to-Fine Contrastive Learning for Conversational Recommender System

Autor: Zhou, Yuanhang, Zhou, Kun, Zhao, Wayne Xin, Wang, Cheng, Jiang, Peng, Hu, He

Conversational recommender systems (CRS) aim to recommend suitable items to users through natural language conversations. For developing effective CRSs, a major technical issue is how to accurately infer user preference from very limited conversation

Externí odkaz: http://arxiv.org/abs/2201.02732

Zobrazit plný text záznamu