Jie Zhou

Prof. Jie Zhou

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 February 2023 in Frontiers of Information Technology & Electronic Engineering
Verified
Journal Article
Closed access
PDF file
Jie ZhouJie Zhou
Jie Zhou
PKPei Ke
Pei Ke
XQXipeng Qiu
Xipeng Qiu
MHMinlie Huang
Minlie Huang
JZJunping Zhang
Junping Zhang

21 September 2023 in Information Processing & Management
Verified
Journal Article
Closed access
LXLuwei Xiao
Luwei Xiao
XWXingjiao Wu
Xingjiao Wu
SYShuwen Yang
Shuwen Yang
JXJunjie Xu
Junjie Xu
Jie ZhouJie Zhou
Jie Zhou
LHLiang He
Liang He

9 January 2025 in ACM Computing Surveys
Verified
Journal Article
Open access
YYYutao Yang
Yutao Yang
Jie ZhouJie Zhou
Jie Zhou
XDXuanwen Ding
Xuanwen Ding
THTianyu Huai
Tianyu Huai
SLShunyu Liu
Shunyu Liu
Liang HeLiang He
Liang He
Recently, foundation language models (LMs) have marked significant achievements in the domains of natural language processing and computer vision. Unlike traditional neural network models, foundation LMs obtain a great ability for transfer learning by acquiring rich common sense knowledge through pre-training on extensive unsupervised datasets with a vast number of parameters. Despite these capabilities, LMs still struggle with catastrophic forgetting, hindering their ability to learn continuously like humans. To address this, continual learning (CL) methodologies have been introduced, allowing LMs to adapt to new tasks while retaining learned knowledge. However, a systematic taxonomy of existing approaches and a comparison of their performance are still lacking. In this article, we delve into a comprehensive review, summarization, and classification of the existing literature on CL-based approaches applied to foundation language models, such as pre-trained language models, large language models, and vision-language models. We divide these studies into offline and online CL, which consist of traditional methods, parameter-efficient-based methods, instruction tuning-based methods and continual pre-training methods. Additionally, we outline the typical datasets and metrics employed in CL research and provide a detailed analysis of the challenges and future work for LMs-based continual learning.

19 October 2022 in Knowledge-Based Systems
Verified
Journal Article
Closed access
JYJunjie Ye
Junjie Ye
Jie ZhouJie Zhou
Jie Zhou
JTJunfeng Tian
Junfeng Tian
RWRui Wang
Rui Wang
JZJingyi Zhou
Jingyi Zhou
XHXuanjing Huang
Xuanjing Huang

24 March 2024 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
LYLang Yu
Lang Yu
QCQin Chen
Qin Chen
Jie ZhouJie Zhou
Jie Zhou
LHLiang He
Liang He
Large language models (LLMs) have shown great success in various Natural Language Processing (NLP) tasks, whist they still need updates after deployment to fix errors or keep pace with the changing knowledge in the world. Researchers formulate such problem as Model Editing and have developed various editors focusing on different axes of editing properties. However, current editors can hardly support all properties and rely on heavy computational resources. In this paper, we propose a plug-in Model Editing method based on neuron-indexed dynamic LoRA (MELO), which alters the behavior of language models by dynamically activating certain LoRA blocks according to the index built in an inner vector database. Our method satisfies various editing properties with high efficiency and can be easily integrated into multiple LLM backbones. Experimental results show that our proposed MELO achieves state-of-the-art editing performance on three sequential editing tasks (document classification, question answering and hallucination correction), while requires the least trainable parameters and computational cost.

1 March 2020 in Information Sciences
Verified
Journal Article
Closed access
Jie ZhouJie Zhou
Jie Zhou
QCQin Chen
Qin Chen
JHJimmy Huang
Jimmy Huang
QHQinmin Vivian Hu
Qinmin Vivian Hu
LHLiang He
Liang He