Dongqi Cai (蔡栋琪)

I’m a 4th-year PhD student in Beijing University of Posts and Telecommunications (BUPT), co-advised by Prof. Mengwei Xu and Prof. Shangguang Wang. Currently, I am visiting the University of Cambridge under the supervision of Prof. Nicholas D. Lane. Additionally, I feel fortunate to receive remote guidance from Prof. Felix Xiaozhu Lin in the development of efficient mobile systems. Here is my Curriculum Vitae.

Email: cdq AT bupt DOT edu DOT cn

Selected Publications (*=Co-first/Corr. Author)

[arXiv] A Survey of Resource-Efficient LLM and Multimodal Foundation Models [pdf] [paper list]

Mengwei Xu, Wangsong Yin, Dongqi Cai, Rongjie Yi, Daliang Xu, Qipeng Wang, Bingyang Wu, Yihao Zhao, Chen Yang, Shihe Wang, Qiyang Zhang, Zhenyan Lu, Li Zhang, Shangguang Wang, Yuanchun Li, Yunxin Liu, Xin Jin, Xuanzhe Liu
[arXiv] Small Language Models: Survey, Measurements, and Insights [pdf] [leader board]

Zhenyan Lu, Xiang Li, Dongqi Cai, Rongjie Yi, Fangming Liu, Xiwen Zhang, Nicholas D. Lane, Mengwei Xu
[arXiv] Recall: Empowering Multimodal Embedding for Edge Devices [pdf]

Dongqi Cai, Shangguang Wang, Chen Peng, Zeling Zhang, Mengwei Xu
[NeurIPS’24] SILENCE: Protecting privacy in offloaded speech understanding on wimpy devices [pdf]

Dongqi Cai, Shangguang Wang, Zeling Zhang, Felix Xiaozhu Lin, Mengwei Xu

[USENIX ATC’24] FwdLLM: Efficient Federated Finetuning of Large Language Models with Perturbed Inferences [pdf] [code] [slides]

Mengwei Xu, Dongqi Cai*, Yaozong Wu, Xiang Li, Shangguang Wang
[MobiCom’24] Mobile Foundation Model as Firmware [pdf] [code]

Jinliang Yuan*, Chen Yang*, Dongqi Cai*, Shihe Wang, Xin Yuan, Zeling Zhang, Xiang Li, Dingge Zhang, Hanzi Mei, Xianqing Jia, Shangguang Wang, Mengwei Xu
[MobiCom’23] Federated Few-shot Learning for Mobile NLP [pdf] [slides] [code]

Dongqi Cai, Shangguang Wang, Yaozong Wu, Felix Xiaozhu Lin, Mengwei Xu
[MobiCom’23] Efficient Federated Learning for Modern NLP [pdf] [poster] [slides] [code]

Dongqi Cai, Yaozong Wu, Shangguang Wang, Felix Xiaozhu Lin, Mengwei Xu
[IEEE TBD’22] Accelerating Vertical Federated Learning [pdf]

Dongqi Cai, Tao Fan, Yan Kang, Lixin Fan, Mengwei XU, Shangguang Wang, Qiang Yang

[University of Cambridge] 09/2024 - 09/2025, Visiting PhD Student.

Advisor: Prof. Nicholas D. Lane
[WeBank] 07/2021 - 12/2021, AI Researcher on Federated Learning.

Mentor: Dr. Lixin Fan

Teaching Assistant, Principles of Machine Learning Systems, Cambridge (Autumn 2024)

[Scholar Award] 2024, NeurIPS
[CSC Scholarship] 2024, China Scholarship Council
[Travel Grant] 2024, EuroSys/MobiSys/ATC
[National Scholarship] 2023, Ministry of Education
[Outstanding Graduate Student] 2023, BUPT
[Excellent Ph.D. Students Foundation] 2023, BUPT
[Outstanding Graduate Student] 2022/2023, State Key Laboratory of Networking and Switching Technology
[First-class academic scholarship] 2022, BUPT