Search

Meng Li's Homepage
Meng Li's Homepage
  • Home
  • News
  • Talks
  • Publications
  • Projects
  • Students
  • Contact
  • Light Dark Automatic
  • English
    中文 (简体)

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)

Latest

  • OptiPrime: Optimizing Private Inference through protocol-hardware codesign
  • Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head Collapse
  • MPCache: MPC-Friendly KV Cache Eviction for Efficient Private LLM Inference
  • H2EAL: Hybrid-Bonding Architecture with Hybrid Sparse Attention for Efficient Long-Context LLM Inference
  • UniCAIM: A Unified CAM/CIM Architecture with Static-Dynamic KV Cache Pruning for Efficient Long-Context LLM Inference
  • FlexHE: A flexible Kernel Generation Framework for Homomorphic Encryption-Based Private Inference
  • PrivQuant: Communication-Efficient Private Inference with Quantized Network/Protocol Co-Optimization
  • CoPriv: Network/Protocol Co-Optimization for Communication-Efficient Private Inference
  • MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attention

© 2026 Me. This work is licensed under CC BY NC ND 4.0

Published with Wowchemy — the free, open source website builder that empowers creators.

Cite
Copy Download