Meng Li

Assistant Professor, Peking University

Joined

October 2017

Names

Meng Li

Emails

****@utexas.edu (Confirmed)

****@fb.com (Confirmed)

****@pku.edu.cn (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Assistant Professor

Peking University (pku.edu.cn)

2022 – Present

Researcher

Facebook (fb.com)

2018 – 2022

PhD

University of Texas, Austin (utexas.edu)

2013 – 2018

Advisors, Relations & Conflicts

PhD Advisor

David Z. Pan

2013 – 2018

Expertise

Efficient Deep Learning

2018 – Present

Computer Vision

2016 – Present

Publications

CLEANER: Self-Purified Trajectories Boost Agentic Reinforcement Learning
Tianshi Xu, Yuteng Chen, Meng Li
- SPOT
- Readers: Everyone
Attention is Not Always Needed: Attention Sink Forges a Native MoE in Attention Layers
Zizhuo Fu, Wenxuan Zeng, Runsheng Wang, Meng Li
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
DySL-VLA: Efficient Vision-Language-Action Model Inference via Dynamic-Static Layer-Skipping for Robot Manipulation
Zebin Yang, Yijiahao Qi, Tong Xie, Bo Yu, Shaoshan Liu, Meng Li
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrieval
Zebin Yang, Sunjian Zheng, Tong Xie, Tianshi Xu, Bo Yu, Fan Wang, Jie Tang, Shaoshan Liu, Meng Li
- NeurIPS 2025 poster
- Readers: Everyone
MPCache: MPC-Friendly KV Cache Eviction for Efficient Private LLM Inference
Wenxuan Zeng, Ye Dong, Jinjin Zhou, Jin Tan, Lei Wang, Tao Wei, Runsheng Wang, Meng Li
- NeurIPS 2025 poster
- Readers: Everyone
CryptoMoE: Privacy-Preserving and Scalable Mixture of Experts Inference via Balanced Expert Routing
Yifan Zhou, Tianshi Xu, Jue Hong, Ye Wu, Meng Li
- NeurIPS 2025 poster
- Readers: Everyone
MPCache: MPC-Friendly KV Cache Eviction for Efficient Private LLM Inference
Wenxuan Zeng, Ye Dong, Jinjin Zhou, Junming Ma, Jin Tan, Runsheng Wang, Meng Li
- Submitted to ICLR 2025
- Readers: Everyone
CopyLens: Dynamically Flagging Copyrighted Sub-Dataset Contributions to LLM Outputs
Qichao Ma, Rui-Jie Zhu, Peiye Liu, Renye Yan, Fahong Zhang, Ling Liang, Meng Li, Zhaofei Yu, Zongwei Wang, Yimao Cai, Tiejun Huang
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction
Renze Chen, Zhuofeng Wang, Beiquan Cao, Tong Wu, Size Zheng, Xiuhong Li, Xuechao Wei, Shengen Yan, Meng Li, Yun Liang
- NeurIPS 2024 poster
- Readers: Everyone
PrivCirNet: Efficient Private Inference via Block Circulant Transformation
Tianshi Xu, Lemeng Wu, Runsheng Wang, Meng Li
- NeurIPS 2024 poster
- Readers: Everyone

View all 91 publications

Co-Authors

View all 191 co-authors