Kun Zhou (周昆)

Kun Zhou is a 3-rd year Ph.D student at School of Information, Renmin University of China, under the supervision of Wayne Xin Zhao and Ji-Rong Wen. His research interests are in natural language processing (NLP), information retrival (IR) and machine learning (ML), with focuses on pre-trained language model (PLM) and their applications in real-world scenarios. He obtained the master degree from Peking University, and bachelor from Hohai University.

News

We just release a chat-based large language model by fine-tuning on high-quality instructions, YuLan-Chat.

My paper is accepted by ECML-PKDD 2023. Thanks for my comrades!

Selected Publications

Here I select several my favorite papers, the whole publication list is in Publication

A Survey of Large Language Models Arxiv

A very very comprehensive survey for the recent progressive of large language models

Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, Yifan Du, Chen Yang, Yushuo Chen, Zhipeng Chen, Jinhao Jiang, Ruiyang Ren, Yifan Li, Xinyu Tang, Zikang Liu, Peiyu Liu, Jian-Yun Nie, Ji-Rong Wen

SimANS: Simple Ambiguous Negatives Sampling for Dense Text Retrieval (EMNLP2022)

Simple and effective. It has been applied in Microsoft Bing Search online system.

Kun Zhou, Yeyun Gong, Xiao Liu, Wayne Xin Zhao, Yelong Shen, Anlei Dong, Jingwen Lu, Rangan Majumder, Ji-Rong Wen, Nan Duan, Weizhu Chen

Debiased Contrastive Learning of Unsupervised Sentence Representations (ACL2022)

The First Attempt on Debiased Sentence Representations

Kun Zhou, Beichen Zhang, Wayne Xin Zhao and Ji-Rong Wen

Filter-enhanced MLP is All You Need for Sequential Recommendation (WWW2022)

A Cool Model with Fast Fourier Transform, Learnable Filters and All-MLP Architecture

Kun Zhou*, Hui Yu*, Wayne Xin Zhao and Ji-Rong Wen

S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization (CIKM2020)

This paper is selected as the most influential CIKM papers by Paperdigest, and also applied in Meituan online recommender system

Kun Zhou*, Hui Wang*, Wayne Xin Zhao, Yutao Zhu, Sirui Wang, Fuzheng Zhang, Zhongyuan Wang and Ji-Rong Wen (*equal contribution)

Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion (KDD2020)

This paper is selected as the most influential KDD papers by Paperdigest

Kun Zhou, Wayne Xin Zhao, Shuqing Bian, Yuanhang Zhou, Ji-Rong Wen and Jingsong Yu

Open Source Projects

Most of my research work are open-source. Here are some my preferable projects!

  • YuLan-Chat
    • YuLan-Chat is a chat-based large language model developed based on fine-tuning LLaMA with high-quality English and Chinese instructions. YuLan-Chat can chat with users to well follow English or Chinese instructions, and can be deployed on an GPU (A800-80G or RTX3090) after quantization. YuLan (Simplified Chinese 玉兰), which represents Yulan Magnolia, is the campus flower of Renmin University of China.
  • CRSLab
    • CRSLab is an open-source toolkit for building Conversational Recommender System (CRS). It contains comprehensive benchmark models and datasets, extensive and standard evaluation protocols, general and extensible structure, human-machine interaction interfaces, and is easy to get started.
  • TG-ReDial
    • We released a Multi-turn Topic-guided Conversation Recommendation dataset for research on conversational/interactive recommender systems: TG-ReDial. It is a Semi-automatic Annotated Dataset and leverages Detailed User Background Information.
  • S3-Rec
    • Code for our CIKM 2020 Paper “S3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization”. It is well-formed and has been used by many researchers.

Experiences

2022.4 - 2023.6, Research Intern, NLC Group, MSRA.

Mentor: Yeyun Gong, Nan Duan

Start a new adventure on Dense Retrieval and Large-scale Pre-training Model !!!

2021.9 - 2022.4, Research Intern, iFLYTEK Research.

Mentor: Jing Sha, Shijin Wang

I led a team to develop the first Chinese Mathematical Pre-trained Language Model, Jiuzhang. We are also persisting to advance the development of this area.

2019.12 - 2021.5, Research Intern, NLP center, Meituan Dianping.

Mentor: Sirui Wang, Fuzheng Zhang

My several papers were accepted during my internship, and one paper S3-Rec has been deployed in Meituan Online recommender system.

2018.8 - 2019.6, Research Intern, XiaoIce, Microsoft Asia.

Mentor: Kai Zhang, Yu Wu

I published my first top-conference paper during my internship, and deployed my first model on XiaoIce online system, thanks for everyone in XiaoIce.

Rewards and Honors

  • 2022 Baidu Scholarship (10 PhD Students) Link
  • 2022 Bytedance Scholarship (10 PhD Students in China Mainland) Link
  • 2022 MSRA Fellowship (12 PhD Students in Asia-Pacific-region) Link
  • 2022 Baogang Scholarship (12 Students in RUC).
  • 2022 National Scholarship.
  • LIC2021 Multi-Skill Dialog Challenge Link
    • Ranked 1st in Automatic Metrics Track, 3rd in Human Evaluation Track
  • LIC2020 Conversational Recommendation Challenge Link
    • Ranked 2st in Automatic Metrics Track, 4rd in Human Evaluation Track
  • 2018 Jane Street Electronic Trading Challenges
    • Ranked 1st
  • 2018 The Data Open Challenges Citadel Datathen
    • Ranked 2nd
  • 2016 American Mathematical Contest in Modeling
    • Honorable Mention
  • 2015 China Undergraduate Mathematical Contest in Modeling
    • National Second Prize
  • 2015 National Zhou Peiyuan college student mechanics competition
    • National Third Prize
  • 2015 Jiangsu Province Undergraduate Mechanical Competition
    • The First Prize

Service

  • IJCAI 2021
    • Senior PC Reviewer
  • AAAI, IJCAI, KDD, SIGIR, WWW, WSDM, ACL, EMNLP, COLING, TOIS, TORS
    • PC Reviewer

Zhihu Posts

I love writing blogs in my free time. Here are some my favorite posts!

BERT meet Knowledge Graph:预训练模型与知识图谱相结合的研究进展

BERT meet KG第二弹:新训练方式,新问题视角

CRSLab:可能是最适合你的对话推荐系统开源库