no code implementations • 27 May 2024 • Zhenyang Li, Yangyang Guo, Kejie Wang, Xiaolin Chen, Liqiang Nie, Mohan Kankanhalli
Visual Commonsense Reasoning (VCR) calls for explanatory reasoning behind question answering over visual scenes.
2 code implementations • 25 Mar 2024 • Daoguang Zan, Ailun Yu, Wei Liu, Dong Chen, Bo Shen, Wei Li, Yafen Yao, Yongshun Gong, Xiaolin Chen, Bei guan, Zhiguang Yang, Yongji Wang, Qianxiang Wang, Lizhen Cui
For feedback-based evaluation, we develop a VSCode plugin for CodeS and engage 30 participants in conducting empirical studies.
no code implementations • 18 Feb 2024 • Federico Becattini, Xiaolin Chen, Andrea Puccia, Haokun Wen, Xuemeng Song, Liqiang Nie, Alberto del Bimbo
Recommending fashion items often leverages rich user profiles and makes targeted suggestions based on past history and previous purchases.
1 code implementation • 25 Jan 2024 • Wei Li, Daoguang Zan, Bei guan, Ailun Yu, Xiaolin Chen, Yongji Wang
Code large language models (Code LLMs) have demonstrated remarkable performance in code generation.
no code implementations • 17 Jan 2024 • Xiaolin Chen, Daoguang Zan, Wei Li, Bei guan, Yongji Wang
Specifically, the malicious participant initially employs semi-supervised learning to train a surrogate target model.
no code implementations • 6 Jul 2023 • Le Xiao, Xiaolin Chen
A News Summary Generator (NSG) is designed to select and evolve the event pattern populations and generate news summaries.
no code implementations • 17 May 2023 • Xiaolin Chen, Xuemeng Song, Yinwei Wei, Liqiang Nie, Tat-Seng Chua
Thereafter, considering that the attribute knowledge and relation knowledge can benefit the responding to different levels of questions, we design a multi-level knowledge composition module in MDS-S2 to obtain the latent composed response representation.
no code implementations • 16 Jul 2022 • Xiaolin Chen, Xuemeng Song, Liqiang Jing, Shuo Li, Linmei Hu, Liqiang Nie
To address these limitations, we propose a novel dual knowledge-enhanced generative pretrained language model for multimodal task-oriented dialog systems (DKMD), consisting of three key components: dual knowledge selection, dual knowledge-enhanced context learning, and knowledge-enhanced response generation.
no code implementations • 20 May 2021 • Xiaolin Chen, Shuai Zhou, Bei guan, Kai Yang, Hao Fan, Hu Wang, Yongji Wang
With this key observation, we protect data privacy and allow the disclosure of feature meaning by concealing decision paths and adapt a communication-efficient secure computation method for inference outputs.