• One paper is accepted by ICLR2026.
• One paper is accepted by WWW2026.
• One paper is accepted by AAAI2026.
• One paper is accepted by CIKM2025.
• One paper is accepted by NeurIPS2025 workshop.
• One paper is accepted by COLM2025.
• One paper is accepted by ICLR2025 workshop
• One paper is accepted by TMLR2024.
• One paper is accepted by CIKM2024.
• I have finished my PhD defense (June 20th, 2024).
• One paper is accepted as findings of ACL2024.
• One paper is relased on arXiv. Mixture of Experts Using Tensor Products
• One paper MBC+arrow is accepted by ICML 2024. Simple, clear and solid!
• Our paper MoPEs is accepted by NeurIPS 2023 workshop.
• Visiting University of Montreal. RALI Lab, supervised by Jian-Yun Nie. (2023.10-2024.2)
• Our paper MHR get accepted by NeurIPS 2023.
• Starting a research internship at MSR Montreal supervised by Alessandro Sordoni (2023.8-2024.2).
• Visiting Chinese University of Honkong (ShenZhen) (CUHK) supervised by Benyou Wang. (2023.9-2023.10)

• PhD (2021/02~2024/6)
  Computer Science
  University of Copenhagen, Copenhagen, Denmark
  Advisor: Prof. Jakob Grue Simonsen and Prof. Rasmus Helles
  
  

• Master (2016/09~2019.2)
  Computer Science
  Tianjin University, Tianjin, China
  Advisor: Prof. Peng Zhang
  
  

• B.Eng. (2012/09~2016/07)
  Computer Science
  North University of China, Taiyuan, China
  
  

(Co) First authored publications

• Zhan Su, Fengran Mo, Prayag Tiwari, Benyou Wang, Jian-Yun Nie, Jakob Grue Simonsen. Mixture of Experts Using Tensor Products. (TMLR2024) [code]
• Zhan Su*, Oleksiy Ostapenko*, Edoardo M. Ponti, Laurent Charlin, Nicolas Le Roux, Matheus Pereira, Lucas Caccia*, Alessandro Sordoni*. Towards Modular LMs by Building and Reusing a Library of LoRAs. (ICML2024)[code]
• Zhan Su*, Michael Antonios Kruse Ayoub*, Qiuchi Li A Case Study of Enhancing Sparse Retrieval using LLMs. (WWW2024 workshop)
• Zhan Su*, Yuqin Zhou*, Fengran Mo, Jakob Grue Simonsen. Language Modeling Using Tensor Trains. (arXiv)
• Zhan Su, Rasmus Helles, Ali Al-Laith, Antti Veilahti, Akrati Saxena, Jakob Grue Simonsen. Privacy Lost in online Education: Analysis of Web Tracking Evolution. (ADMA2023 oral)
• Zhan Su, Benyou Wang, Jiabin Niu, Shuchang Tao, Peng Zhang , Dawei Song. Enhanced Embedding Based Attentive Pooling Network for Answer Selection. National CCF Conference on Natural Language Processing and Chinese Computing. (NLPCC2017)

co-authored publications

• Fengran Mo, Chen Qu, Kelong Mao, Yihong Wu, Zhan Su, Kaiyu Huang, Jian-Yun Nie. Aligning Query Representation with Rewritten Query and Relevance Judgments in Conversational Search. (CIKM2024)
• Fengran Mo, Chen Qu, Kelong Mao, Tianyu Zhu, Zhan Su, Kaiyu Huang, Jian-Yun Nie.History-Aware Conversational Dense Retrieval. (Findings of ACL2024)
• Oleksiy Ostapenko, Lucas Caccia, Zhan Su, Nicolas Le Roux, Laurent Charlin, Alessandro Sordoni. A Case Study of Instruction Tuning with Mixture of Parameter-Efficient Experts. (NeurIPS2023 workshop)
• Lucas Caccia, Edoardo Ponti, Zhan Su, Matheus Pereira, Nicolas Le Roux, Alessandro Sordoni. Multi-Head Adapter Routing for Cross-Task Generalization. (NeurIPS2023) [code]
• Lipeng Zhang, Peng Zhang, Xindian Ma, Shuqin Gu, Zhan Su, Dawei Song. A generalized language model in tensor space. (AAAI2019)
• Peng Zhang, Zhan Su, Lipeng Zhang, Benyou Wang, Dawei Song. A quantum many-body wave function inspired language modeling approach. (CIKM2018)
• Peng Zhang, Jiabin Niu, Zhan Su, Benyou Wang, Liqun Ma, Dawei Song. End-to-end quantum-like language models with application to question answering. (AAAI2018)
• Pengqing Zhang, Yuexian Hou, Zhan Su, Yi Su. Two-Step Multi-factor Attention Neural Network for Answer Selection. Pacific Rim International Conference on Artificial Intelligence. (PRICAI2018)

Teaching Assistant:

PC member: