Wenxuan Zeng

Tencent Inc (Talent Program)

Tencent Inc (Talent Program)

Interests
  • Privacy-Preserving AI
Education

  • M.S. (Co-advised with Prof. Runsheng Wang), 2026

    Peking University

  • B.S. in Software Engineering, 2023

    University of Electronic Science and Technology of China (UESTC)

Publications

Jiangrui Yu, Ye Yu, Si Chen, Chenqi Lin, Wenxuan Zeng, Junfeng Fan, Mingyu Gao, Meng Li (2026). OptiPrime: Optimizing Private Inference through protocol-hardware codesign. In MICRO 2026.

Zizhuo Fu, Wenxuan Zeng, Runsheng Wang, Meng Li (2026). Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head Collapse. In International Conference on Machine Learning (ICML) 2026.

Paper

Wenxuan Zeng, Ye Dong, Jinjin Zhou, Jin Tan, Lei Wang, Tao Wei, Runsheng Wang, Meng Li (2025). MPCache: MPC-Friendly KV Cache Eviction for Efficient Private LLM Inference. In Conference on Neural Information Processing Systems (NeurIPs) 2025.

Paper

Zizhuo Fu, Xiaotian Guo, Wenxuan Zeng, Shuzhang Zhong, Yadong Zhang, Peiyu Chen, Runsheng Wang, Le Ye, Meng Li (2025). H2EAL: Hybrid-Bonding Architecture with Hybrid Sparse Attention for Efficient Long-Context LLM Inference. In International Conference on Computer-Aided Design (ICCAD) 2025.

Paper

Weikai Xu, Wenxuan Zeng, Qianqian Huang, Meng Li, Ru Huang (2025). UniCAIM: A Unified CAM/CIM Architecture with Static-Dynamic KV Cache Pruning for Efficient Long-Context LLM Inference. In Design Automation Conference (DAC) 2025.

Paper Slides

Jiangrui Yu, Wenxuan Zeng, Tianshi Xu, Renze Chen, Yun (Eric) Liang, Runsheng Wang, Ru Huang, Meng Li (2024). FlexHE: A flexible Kernel Generation Framework for Homomorphic Encryption-Based Private Inference. In International Conference on Computer-Aided Design (ICCAD) 2024.

Paper

Tianshi Xu, Shuzhang Zhong, Wenxuan Zeng, Runsheng Wang, Meng Li (2024). PrivQuant: Communication-Efficient Private Inference with Quantized Network/Protocol Co-Optimization. In International Conference on Computer-Aided Design (ICCAD) 2024.

Paper

Wenxuan Zeng, Meng Li, Haichuan Yang, Wen-Jie Lu, Runsheng Wang, Ru Huang (2023). CoPriv: Network/Protocol Co-Optimization for Communication-Efficient Private Inference. In Conference on Neural Information Processing Systems (NeurIPs) 2023.

Paper

Wenxuan Zeng, Meng Li, Wenjie Xiong, Tong Tong, Wen-Jie Lu, Jin Tan, Runsheng Wang, Ru Huang (2023). MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attention. In International Conference on Computer Vision (ICCV) 2023.

Paper