Dongqi Cai (蔡栋琪)

I’m an incoming Assistant Professor at the Nanjing University. Previously, I obtained my Ph.D. from BUPT, co-advised by Prof. Mengwei Xu and Prof. Shangguang Wang. Meanwhile, I work closely with Prof. Felix Xiaozhu Lin. I was a visiting scholar at the University of Cambridge from 2024 to 2025, working with Prof. Nicholas D. Lane.

📢 I’m actively looking for self-motivated PhD students, Master students, and research interns. If you are interested in efficient AI systems and embodied intelligence, please feel free to contact me!

Email: nju DOT cdq AT gmail DOT com

Here is my Curriculum Vitae.

---

Research Interests

• On-device Learning: Zero-order optimization, memory-efficient training, edge AI
• Distributed AI Systems: Federated learning, multi-agent collaboration, embodied intelligence
• Resource-Constrained AI: Mobile computing, IoT systems, drone/robot intelligence

---

News!

• [2026-03] 🔥 I will join the School of Intelligent Science and Technology, Nanjing University as an Assistant Professor! Welcome to contact me for potential collaborations!
• [2026-03] Our paper about accelerating forward-only federated LLMs has been accepted by TMC!
• [2026-02] Our paper about auditing unauthorized training data from AIGC was published in Nature Communications
• [2026-01] Our paper about knowledge editing for on-device LLMs has been accepted by ICLR‘26
• [2025-10] Honored to serve on the Technical Program Committee at MobiSys’26
• [2025-07] Our work on Efficient Model Editing received the Best Poster Award at MobiUK
• [2025-06] Our paper on Efficient Multimodal Embedding was published in Nature Communications
• [2025-05] Honored to be selected as a MobiSys 2025 Rising Star
• [2025-01] Invited to deliver a seminar speech at Cambridge ML Systems Seminar Series

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

• [Nature Communications’25] Ubiquitous Memory Augmentation via Mobile Multimodal Embedding System [pdf][supplementary][peer review]

  Dongqi Cai, Shangguang Wang, Chen Peng, Zeling Zhang, Zhenyan Lu, Tao Qi, Nicholas Lane, Mengwei Xu

• [NeurIPS’24] SILENCE: Protecting Privacy in Offloaded Speech Understanding on Resource-constrained Devices [pdf] [slides]

  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] [slides] [Distinguished Artifact Nomination]

  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] [Most Cited Paper of MobiCom’23 (1/91)]

  Dongqi Cai, Yaozong Wu, Shangguang Wang, Felix Xiaozhu Lin, Mengwei Xu

Visiting & Internship

• [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 Experience

• Teaching Assistant, Principles of Machine Learning Systems, Cambridge (Michaelmas Term 2024)

Academic Service

• PC member: [MobiSys’2026][EIS’25][MobiSys’24 AE][MobiCom’24 AE][TURC-SIGBED-China’23] [NCSC-edge’22]
• Reviewer: [Scientific Reports] [TSC] [TMC] [TKDE] [TECS] [IoTJ] [ICASSP’24] [ICASSP’25] [SAGC’22]
• External reviewer: [MLSys’25] [ICWS’24] [IEEE EDGE’24] [IEEE EDGE’23] [ICWS’23] [EIS’21]

Awards & Honors

• [Best Poster Award], 2025, MobiUK (1/35)
• [MobiSys Rising Star], 2025, SigMobile
• [Young Elite Scientists Sponsorship: PhD student Special Program] 2024, CAST
• [Travel Grant] EuroSys’24/MobiSys’24/ATC’24/NeurIPS’24/MobiSys’25/MobiUK’25
• [National Scholarship] 2024, Ministry of Education
• [CSC Scholarship] 2024, China Scholarship Council
• [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