I am currently a second-year MS student at the College of Computer Science and Technology, Zhejiang University, under the supervision of Prof. Kun Kuang and Shengyu Zhang.
My research primarily focuses on the generalizability and personalization of recommender systems. I also tackle the distinctive challenges related to the seamless integration of heterogeneous models across various computational environments, including both mobile devices and cloud servers. Recently, I am interested in the recommendations with large language models and the efficient inference of large recommenders when facing much longer user interaction sequences.
I am actively seeking job opportunities and will graduate in March 2026. Please feel free to contact me if there are any suitable positions available.
π₯ News
- 2025.09: Β π°π° One paper has been deployed in Taobao and available on Arxiv about generative retrieval with semantic identifiers.
- 2025.07: Β ππ One co-first-author paper has been accepted to MM 2025.
- 2025.07: Β ππ One paper has been accepted to MM 2025.
- 2025.07: Β ππ Forward-OFA has been deployed in the Ascend Community of Huawei using NPU.
- 2025.05: Β π°π° One paper has been available on Arxiv about LLM thinking-enhanced recommendation.
- 2024.12: Β ππ One co-first-author paper has been accepted to AAAI 2025.
- 2024.11: Β ππ One first-author paper has been accepted to KDD 2025 August Cycle (Research Track).
- 2024.08: Β π₯³π₯³ I went to Barcelona, Spain, to attend the KDD conference to deliver an oral presentation of our paper DIET.
- 2024.05: Β ππ One first-author paper has been accepted to KDD 2024 (Research Track).
- 2023.07: Β π₯³π₯³ I went to Fuzhou, China, to attend the CICAI conference to deliver an oral presentation and won the Best Paper Award.
- 2023.06: Β ππ One first-author paper has been accepted to CICAI 2023.
π Publications
* denote the authors contributed equally.
FORGE: Forming Semantic Identifiers for Generative Retrieval in Industrial Datasets
Kairui Fu, Tao Zhang, Shuwen Xiao, Ziyang Wang, Xinming Zhang, Chenchi Zhang, Yuliang Yan, Junjun Zheng, Yu Li, Zhihong Chen, Jian Wu, Xiangheng Kong, Shengyu Zhang, Kun Kuang, Yuning Jiang, Bo Zheng
- The first industrial benchmark about generative retrieval with semantic identifiers, which contains 14 billion user interactions and multimodal features of 250 million items sampled from Taobao.
- Subsequent proposed optimizations of data modality and ID collisions are validated with both offline (15\% improvements on HitRate) and online (0.35% improvements on transaction count) experiments in the βGuess You Likeβ Section of Taobao.
TianQi Liu*, Kairui Fu*, Shengyu Zhang, Wenyan Fan, Zhaocheng Du, Jieming Zhu, Fan Wu, Fei Wu
- A framework for device-cloud collaborative personalized mixed-precision quantization that generates lightweight networks for heterogeneous mobile devices.
Tackling Device Data Distribution Real-time Shift via Prototype-based Parameter Editing
Zheqi Lv, Wen Qiao Zhang, Kairui Fu, Qi Tian, Shengyu Zhang, Jiajie Su, Jingyuan Chen, Kun Kuang, Fei Wu
- The composition of coarse and fine-grained intersts for tackling the on-device continuous data distribution shift in both vision and recommendation tasks.
ThinkRec: Thinking-based recommendation via LLM
Qihang Yu*, Kairui Fu*, Shengyu Zhang, Zheqi Lv, Fan Wu, Fei Wu
- Almost the first emphasizes the importance of activating the thinking of LLMs to make recommendations more interpretable and effective.
Kairui Fu, Zheqi Lv, Shengyu Zhang, Fan Wu, Kun Kuang
- An early attempt to investigate the joint customization of both structure and parameters, analyzing the challenges of interest heterogeneity, network transmission, and on-device inference simultaneously.
MergeNet: Knowledge Migration across Heterogeneous Models, Tasks, and Modalities
Kunxi Li*, Tianyu Zhan*, Kairui Fu*, Shengyu Zhang, Kun Kuang, Jiwei Li, Zhou Zhao, Fan Wu, Fei Wu
- Leverage parameters as the medium to achieve knowledge transfer between heterogeneous models, tasks, and modalities.
DIET: Customized Slimming for Incompatible Networks in Sequential Recommendation
Kairui Fu, Shengyu Zhang, Zheqi Lv, Jingyuan Chen, Jiwei Li
- Tackle both the parameter personalization and the communication efficiency under strict device constraints in device-cloud collaborative recommendation.
Kairui Fu, Qiaowei Miao, Shengyu Zhang, Kun Kuang, Fei Wu
- Investigate the inconsistent distribution of users in recommender system and the difficulty in causal structure learning accompanied by the intervention of recommender system.
π Honors and Awards
- 2024.12 Huawei Jingying Scholarship (Top 1%)
- 2023.7 Best Paper Award in CICAI 2023 (Top 1)
- 2023.6 Outstanding Graduates of Zhejiang University
- 2022.10 Scholarship of Zhejiang University
- 2021.10 Scholarship of Zhejiang University
- 2020.10 Scholarship of Zhejiang University
π Educations
- 2023.09 - present, Master, Computer Science and Technology, Zhejiang University, Hangzhou.
- 2019.09 - 2023.06, Undergraduate, Turing Class(Chu Kochen Honors College), Computer Science and Technology, Zhejiang University, Hangzhou
π» Internships
- 2025.02 - 2025.05, Huawei Noahβs Ark Lab, China.
- 2025.05 - Present, Taobao & Tmall Group of Alibaba, China.