no code implementations • ECNLP (ACL) 2022 • Lvxing Zhu, Hao Chen, Chao Wei, Weiru Zhang
To solve the above problem, we propose a novel method that leverages an auxiliary module to enhance the representations of long-tail queries by taking advantage of reliable supervised information of variant frequent queries.
no code implementations • 27 Dec 2023 • Zaifan Jiang, Xing Huang, Chao Wei
Reinforcement Learning from Human Feedback (RLHF) is a model-based algorithm to optimize preference learning, which first fits a reward model for preference scores and then optimizes the generating policy with an on-policy PPO algorithm to maximize the reward.
no code implementations • 16 Apr 2023 • Laurent Kloeker, Chenghua Liu, Chao Wei, Lutz Eckstein
The use of smart roadside infrastructure sensors is highly relevant for future applications of connected and automated vehicles.
no code implementations • 14 Dec 2021 • Boxuan Zhang, Chao Wei, Yan Jin, Weiru Zhang
In detail, ACE-BERT leverages the patch features and pixel features as image representation.
no code implementations • 29 Sep 2019 • Chao Wei, Weiru Zhang, Shengjie Sun, Fei Li, Xiaonan Meng, Yi Hu, Hao Wang
Online advertising in E-commerce platforms provides sellers an opportunity to achieve potential audiences with different target goals.
no code implementations • 12 Oct 2018 • Shengjie Sun, Dong Yang, Hongchun Zhang, Yanxu Chen, Chao Wei, Xiaonan Meng, Yi Hu
The knowledge graph(KG) composed of entities with their descriptions and attributes, and relationship between entities, is finding more and more application scenarios in various natural language processing tasks.