Shanlei Mu   /   牟善磊

I am currently a Staff Engineer at Douyin Search (ByteDance), focusing on building the next-generation search system through generative models and large-scale recommendation models.

Prior to that, I was an algorithm engineer at Alimam Tech (Alibaba), working on the design of advertising algorithms. I received my master degree in 2022 and B.E. degree in 2019, at Renmin University of China, advised by Professor Wayne Xin Zhao.

Email: shanleimu AT outlook.com / slmu AT alu.ruc.edu.cn

GitHub  /  Google Scholar

I'm interested in recommender system, generative model and LLM agents. More precisely, my research focuses include:

• Large-scale industrial recommendation, exploring the scaling law of recommendation models.
• Generative recommendation, which models user actions using large generative models (LLM base).
• Deep research, integrating LLM reasoning with search technologies to build autonomous, multi-step retrieval agents capable of exploring the web and synthesizing information.

Experience

• Jan. 2025 - Present. Staff Engineer, Douyin Search, ByteDance

  Large-scale recommendation model with 4B dense parameters, 100T sparse features, and 100K sequence lengths.

  End-to-end generative search models based on semantic information.

• Jul. 2022 - Dec. 2024. Advertising Algorithm Engineer, Alimama Tech, Alibaba

  CVR prediction based on multimodal information, user behavior modeling, and multi-scenario multi-task learning.

• Jan. 2021 - Aug. 2021. Research Intern, DAMO Academy, Alibaba

  Data Analytics and Intelligence Lab (Now, Alibaba Tongyi Lab), with Yaliang Li.

Education

• Sep. 2019 - Jun. 2022. M.E., School of Information, Renmin University of China

• Sep. 2015 - Jun. 2019. B.E., School of Information, Renmin University of China

RecBole is developed based on Python and PyTorch for reproducing and developing recommendation algorithms in a unified, comprehensive and efficient framework for research purpose. Welcome to use our toolkit!

Note: Authors marked with * are equal contributions.

• MDL: A Unified Multi-Distribution Learner in Large-scale Industrial Recommendation through Tokenization.
  Shanlei Mu*, Yuchen Jiang*, Shikang Wu*, Shiyong Hong, Tianmu Sha, Junjie Zhang, Jie Zhu, Zhe Chen, Zhe Wang and Jingjian Lin
  KDD, 2026
  

• MSN: A Memory-based Sparse Activation Scaling Framework for Large-scale Industrial Recommendation.
  Shikang Wu*, Hui Lu*, Jinqiu Jin*, Zheng Chai*, Shiyong Hong, Junjie Zhang, Shanlei Mu, Kaiyuan Ma, Tianyi Liu, Yuchao Zheng, Zhe Wang and Jingjian Lin
  KDD, 2026
  

• Hybrid Contrastive Constraints for Multi-Scenario Ad Ranking.
  Shanlei Mu, Penghui Wei, Wayne Xin Zhao, Shaoguo Liu, Liang Wang and Bo Zheng
  CIKM, 2023
  

• ID-Agnostic User Behavior Pre-training for Sequential Recommendation.
  Shanlei Mu, Yupeng Hou, Wayne Xin Zhao, Yaliang Li and Bolin Ding
  CCIR, 2022. Best Paper Candidate.
  

• RecBole 2.0: Towards a More Up-to-Date Recommendation Library.
  Wayne Xin Zhao, Yupeng Hou, Xingyu Pan, Chen Yang, Zeyu Zhang, Zihan Lin, Jingsen Zhang, Shuqing Bian, Jiakai Tang, Wenqi Sun, Yushuo Chen, Lanling Xu, Gaowei Zhang, Zhen Tian, Changxin Tian, Shanlei Mu, Xinyan Fan, Xu Chen and Ji-Rong Wen
  CIKM, 2022, Resource Track. Best Resource Paper Runner-up.
  

• Towards Universal Sequence Representation Learning for Recommender Systems.
  Yupeng Hou*, Shanlei Mu*, Wayne Xin Zhao, Yaliang Li, Bolin Ding, Ji-Rong Wen
  KDD, 2022
  

• Alleviating Spurious Correlations in Knowledge-aware Recommendations through Counterfactual Generator.
  Shanlei Mu, Yaliang Li, Wayne Xin Zhao, Jingyuan Wang, Bolin Ding and Ji-Rong Wen
  SIGIR, 2022
  

• Knowledge-Guided Disentangled Representation Learning for Recommender Systems.
  Shanlei Mu, Yaliang Li, Wayne Xin Zhao, Siqing Li and Ji-Rong Wen
  TOIS, 2022
  

• Debiasing Learning based Cross-domain Recommendation.
  Siqing Li, Liuyi Yao, Shanlei Mu, Wayne Xin Zhao, Yaliang Li, Tonglei Guo, Bolin Ding and Ji-Rong Wen
  KDD, 2021, Applied Data Science Track
  

• RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms.
  Wayne Xin Zhao, Shanlei Mu*, Yupeng Hou*, Zihan Lin, Yushuo Chen, Xingyu Pan, Kaiyuan Li, Yujie Lu, Hui Wang, Changxin Tian, Yingqian Min, Zhichao Feng, Xinyan Fan, Xu Chen, Pengfei Wang, Wendi Ji, Yaliang Li, Xiaoling Wang and Ji-Rong Wen
  CIKM, 2021, Resource Track
  

• An In-Depth Benchmarking Study on Bill of Materials for High-End Manufacturing.
  Yurui Wang, Shanlei Mu, Feiran Huang, Wei Lu and Yueguo Chen
  ER, 2018
  

• Outstanding Graduate, Beijing, 2022.

• National Scholarship for Graduate Students of China (Highest National Scholarship), 2021.

Last update: Jul. 2026      Template