About Me

Hi! My name is Rui Kong. I am currently a senior researcher at Baidu Search Science, collaborating closely with Dr. Yuchen Li. I am also an adjunct researcher in AI+AIoT Group at Institute for AI Industry Research (AIR), Tsinghua University, collaborating with Prof. Yuanchun Li and Prof. Yunxin Liu (IEEE Fellow). I received my Ph.D. degree from the Department of Computer Science and Engineering at Shanghai Jiao Tong University in 2025, under the supervision of Prof. Linghe Kong (Cheung Kong Scholar).
Research Interests:
My research focuses on the training and inference of Large Language Models (LLMs). My interests in training include the optimization of attention mechanisms and Mixture-of-Experts (MoE) during pre-training, as well as post-training techniques for AI agents. For inference, I focus on speculative sampling, KV cache optimization, and the acceleration of reasoning processes.
Prospective Interns:
I am looking for highly self-motivated research or applied interns (PhD or Master students) to join our Baidu Search Science team in Beijing! If you are interested in working with me in the area large language models, please email kongrui02 {at} baidu.com.

Publications

[Technical Report]

  1. [Preprint] Yuchen Li, Hengyi Cai, Rui Kong, Xinran Chen, Jiamin Chen, Jun Yang, Haojie Zhang, Jiayi Li, Jiayi Wu, Yiqun Chen, Changle Qu, Keyi Kong, Wenwen Ye, Lixin Su, Xinyu Ma, Long Xia, Daiting Shi, Lingyong Yan, Jiashu Zhao, Haoyi Xiong, Shuaiqiang Wang, Dawei Yin.
    Towards AI Search Paradigm.
    Arxiv, 2025. [pdf]
  2. [Preprint] Yuanchun Li, Hao Wen, Weijun Wang, Xiangyu Li, Yizhen Yuan, Guohong Liu, Jiacheng Liu, Wenxing Xu, Xiang Wang, Yi Sun, Rui Kong, Yile Wang, Hanfei Geng, Jian Luan, Xuefeng Jin, Zilong Ye, Guanjing Xiong, Fan Zhang, Xiang Li, Mengwei Xu, Zhijun Li, Peng Li, Yang Liu, Ya-Qin Zhang, Yunxin Liu.
    Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security.
    Arxiv, 2024. [pdf]

[Conference]

  1. [AAAI'26] Qiyang Li, Rui Kong, Yuchen Li, Hengyi Cai, Shuaiqiang Wang, Linghe Kong, Guihai Chen, Dawei Yin.
    AdaFuse: Accelerating Dynamic Adapter Inference via Token-Level Pre-Gating and Fused Kernel Optimization.
    The 40th Annual AAAI Conference on Artificial Intelligence, 2026.
  2. [AAAI'26] Shuo Feng, Zihan Wang, Yuchen Li, Rui Kong, Hengyi Cai, Shuaiqiang Wang, Gim Hee Lee, Piji Li, Shuqiang Jiang.
    VPN: Visual Prompt Navigation.
    The 40th Annual AAAI Conference on Artificial Intelligence, 2026.
  3. [EuroSys'25] Liang Mi, Weijun Wang, Wenming Tu, Qingfeng He, Rui Kong, Xinyu Fang, Yazhu Dong, Yikang Zhang, Yuanchun Li, Meng Li, Haipeng Dai, Guihai Chen, Yunxin Liu.
    Empower Vision Applications with LoRA LMM.
    Proceedings of the Twentieth European Conference on Computer Systems, 2025. [pdf]
  4. [ACL'24] Rui Kong, Yuanchun Li, Qingtian Feng, Weijun Wang, Linghe Kong, Yunxin Liu.
    SwapMoE: Efficient Memory-Constrained Serving of Large Sparse MoE Models via Dynamic Expert Pruning and Swapping.
    Annual Meeting of the Association for Computational Linguistics, 2024. [pdf]
  5. [Mobisys'24@Workshop] Yizhen Yuan, Rui Kong, Yuanchun Li, Yunxin Liu.
    Wip: An on-device llm-based approach to query privacy protection.
    Proceedings of the Workshop on Edge and Mobile Foundation Models, 2024. [pdf]
  6. [MM'23] Yizhen Yuan, Rui Kong, Shenghao Xie, Yuanchun Li, Yunxin Liu.
    PatchBackdoor: Backdoor Attack against Deep Neural Networks without Model Modification.
    ACM Multimedia, 2023. [pdf]
  7. [MobiSys'23] Rui Kong, Yuanchun Li, Yizhen Yuan, Linghe Kong.
    ConvReLU++: Reference-based Lossless Acceleration of Conv-ReLU Operations on Mobile CPU.
    ACM International Conference on Mobile Systems, Applications, and Services, 2023. [pdf]

[Journal]

  1. [TC'25] Rui Kong, Yuanchun Li, Weijun Wang, Linghe Kong, Yunxin Liu.
    Serving MoE Models on Resource-constrained Edge Devices via Dynamic Expert Swapping.
    IEEE Transactions on Computers, 2025. [pdf]

Awards

  • Towngas Scholarship
  • The 14th National Smart Car Contest, First Prize
  • The 13th National Smart Car Contest, Second Prize
  • First Prize Scholarship for Outstanding Students of Shandong University (Top 5%)