Portrait of Meng Li

Meng Li （李猛）

Assistant Professor
School of Computer Science, Nanjing University

Email: meng@nju.edu.cn
Office: CS Building 312

I am an Assistant Professor at Nanjing University’s School of Computer Science and lead the on-device intelligence subgroup within LANDS. I develop models and systems for On-Device Agents (端侧智能体), spanning efficient training and inference, agent memory, and scalable coordination, with the goal of making intelligent agents practical on everyday devices.

I received my B.S. (2016) and Ph.D. (2023) from Nanjing University. My doctoral dissertation received outstanding dissertation awards from the Chinese Institute of Electronics (CIE), Jiangsu Province, and Nanjing University. I have published over 40 papers in venues including ISCA, SIGMOD, VLDB, and EuroSys, and held visiting research appointments at Alibaba DAMO Academy and NTU.

Recent News

  • Congrats to Mingxin! Our paper “Scaling LLM Agent Tool Access: The MCP Gateway” has been accepted to ATC 2026.

  • Our paper “Continual Quadruped Robots Coordination via Semantic Skill Discovery” has been accepted to CoRL 2026.

  • Congrats to Zhipeng and Junhan (undergraduate) for their learned index paper accepted by VLDB 2027!

  • Congrats to Ruiben (undergraduate) for his MobileOC paper accepted by UbiComp 2026 Student Research Competition!

  • Congrats to Guoying for his Edge MoE paper (SMoE) accepted by ISCA 2026!

Earlier updates

  • Congrats to Ning Zhang and co-authors for SecFinder receiving the Best Paper Award from ICPADS 2025!

  • Our work on Edge MoE LLM inference was featured by MIT tech review (Asia) and Deeptech.

  • Congrats to Tao Li and Shizhe for their papers accepted by ICDE 2026!

  • Congrats to Junfeng for his learned index evaluation paper accepted by EDBT 2026!

  • Congrats to Keran and Hancheng for their papers accepted by TMC and TPDS!

  • Congrats to Feifan for his adaptive range filter paper accepted by SIGMOD 2026!

  • Congrats to Ruiben (undergraduate) and Yihuan for their APWeb 2025 NUMA-aware learned index paper!

  • Congrats to Guoying for his ICDE 2025 cloud sync paper!

  • Congrats to Liang Mi for his VaLoRA paper accepted by EuroSys 2025!

Preprints

Selected PublicationsFull list

  • [ATC'26]Scaling LLM Agent Tool Access: The MCP GatewayMingxin Li, Enge Song, Yueshang Zuo, Xiaodong Liu, Rong Wen, Qiang Fu, Gianni Antichi, Jian He, Jing Tie, Zhou Shao, Xiaobo Xue, Xiong Xiao, Luyao Zhong, Shaokai Zhang, Jiangu Zhao, Jianyuan Lu, Shize Zhang, Xiaoqing Sun, Changgang Zheng, Zihao Fan, Haonan Li, Tian Pan, Xiaomin Wu, Yang Song, Xing Li, Biao Lyu, Meng Li, Haipeng Dai, Guihai Chen and Shunmin Zhu. Accepted to the ACM SIGOPS Annual Technical Conference (ATC), 2026.

  • [CoRL'26]Continual Quadruped Robots Coordination via Semantic Skill DiscoveryDaoqing Wang, Yuchen Xiao, Weixuan Huang, Zhilong Zhang, Shenghua Wan, Meng Li, Lei Yuan and Yang Yu. Accepted to the Conference on Robot Learning (CoRL), 2026.

  • [VLDB'27]Replace or Augment: Rethinking the Role of Learned Indexes in Relational DatabasesZhipeng Chen, Meng Li, Hancheng Wang, Junhan Lv, Haipeng Dai and Siqiang Luo. In Proceedings of the 53rd International Conference on Very Large Data Bases (VLDB, CCF-A), Athens, Greece, Aug 23-27, 2027. (*Corresponding Author*)

  • [ISCA'26]SMoE: An Algorithm-System Co-Design for Pushing MoE to the Edge via Expert SubstitutionGuoying Zhu, Meng Li, Haipeng Dai, Xuechen Liu, Weijun Wang, Keran Li, Jun Xiao, Ligeng Chen and Wei Wang. In Proceedings of the 53rd Annual International Symposium on Computer Architecture (ISCA, CCF-A), Raleigh, USA, June 27-July 1, 2026. (*Corresponding Author*)

  • [SIGMOD'26]Hourglass: An Adaptive Range Filter with Lightweight Hybrid EncodingFeifan Liu, Rong Gu, Meng Li, Haipeng Dai, Baohan Wang, Jie Tao, Dian Shen. The 52th ACM SIGMOD/PODS International Conference on Management of Data (SIGMOD, CCF-A), 2026. (*Corresponding Author*)

  • [EuroSys'25]Empower Vision Applications with LoRA LMMLiang 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. In Proceedings of the 20th ACM European Conference on Computer Systems (EuroSys, CCF-A), Rotterdam, The Netherlands, March 30-April 3, 2025. (*Corresponding Author*)

  • [SIGMOD'25]VEGA: An Active-tuning Learned Index with Group-Wise Learning GranularityMeng Li, Huayi Chai, Siqiang Luo, Haipeng Dai, Rong Gu, Jiaqi Zheng and Guihai Chen. In Proceedings of the ACM Conference on Management of Data (SIGMOD, CCF-A), Berlin, Germany, June 22-27, 2025.

  • [VLDB'24]Oasis: An Optimal Disjoint Segmented Learned Range FilterGuanduo Chen, Zhenying He, Meng Li, Siqiang Luo. In Proceedings of the 50th International Conference on Very Large Data Bases (VLDB), Guangzhou, China, Aug 28-Sep 1, 2024.

  • [INFOCOM'24]The Reinforcement Cuckoo FilterMeng Li, Wenqi Luo, Haipeng Dai, Huayi Chai, Rong Gu, Xiaoyu Wang and Guihai Chen. In Proceedings of the 23rd IEEE International Conference on Computer Communications (INFOCOM), Vancouver, Canada, May 20-23, 2024.

  • [VLDB'23]ShadowAQP: Efficient Approximate Group-by and Join Query via Attribute-oriented Sample Size Allocation and Data GenerationRong Gu, Han Li, Haipeng Dai, Wenjie Huang, Jie Xue, Meng Li, Jiaqi Zheng, Haoran Cai, Yihua Huang and Guihai Chen. In Proceedings of the 49rd International Conference on Very Large Data Bases (VLDB), Vancouver, Canada, Aug 28-Sep 1, 2023. (*Corresponding Author*)

  • [WWW'22]Seesaw Counting Filter: An Efficient Guardian for Vulnerable Negative Keys During Dynamic FilteringMeng Li, Deyi Chen, Haipeng Dai, Rongbiao Xie, Siqiang Luo, Rong Gu, Tong Yang and Guihai Chen. In Proceedings of the World Wide Web Conference (WWW), Lyon, France, April 25–29, 2022.

  • [VLDBJ'22]A Pareto Optimal Bloom Filter Family with Hash AdaptivityMeng Li, Rongbiao Xie, Deyi Chen, Haipeng Dai, Rong Gu, He Huang, Wanchun Dou and Guihai Chen. The VLDB Journal (VLDBJ), 2022.