Shuzhang Zhong
Scholar

Shuzhang Zhong

Google Scholar ID: PpRWetwAAAAJ
Peking University
Machine Learning System
Citations & Impact
All-time
Citations
46
 
H-index
4
 
i10-index
1
 
Publications
9
 
Co-authors
6
list available
Resume (English only)
Academic Achievements
  • Recent Publications include:
  • - H2EAL: Hybrid-Bonding Architecture with Hybrid Sparse Attention for Efficient Long-Context LLM Inference (ICCAD 2025)
  • - HD-MoE: Hybrid and Dynamic Parallelism for Mixture-of-Expert LLMs with 3D Near-Memory Processing (ICCAD 2025)
  • - HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference (DAC 2025)
  • - SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding (DAC 2025)
  • - AdapMoE: Adaptive Sensitivity-based Expert Gating and Management for Efficient MoE Inference (ICCAD 2024)
Research Experience
  • Currently a second-year Ph.D. student at the School of Integrated Circuit, Peking University, advised by Prof. Meng Li.
Education
  • PhD in Integrated Circuit, 2023-present, Peking University, Advisor: Prof. Meng Li; BSc in Computer Science, 2019-2023, Beihang University.
Background
  • Research Interests: Efficient Multi-Modality Artificial Intelligence, Algorithm/System/Hardware Co-Design/Co-Optimization. Previously served as the captain of the SuperComputer Team at Beihang University under the supervision of Prof. Hailong Yang.
Miscellany
  • Contact: test@example.org, 888 888 88 88, 450 Serra Mall, Stanford, CA 94305.