Yuzong Chen

My name is Yuzong Chen, a PhD student in the School of Electrical and Computer Engineering at Cornell University. I am advised by Prof. Mohamed Abdelfattah and affiliated with the Computer Systems Laboratory (CSL). My current research focus on Efficient Hardware Architectures for Sparse and Mixed-Precision Deep Learning Acceleration.

Previously, I received my bachelor’s degree in Electrical & Electronic Engineering from the Nanyang Technological University, Singapore. After graduation, I spent 3 years as a research staff at the Nanyang Technological University (advised by Prof. Tony Tae-Hyoung Kim) and the National University of Singapore (advised by Prof. Heng Chun-Huat).

I am a finalist of the Qualcomm Innovation Fellowship (QiF), 2024.

News

Mar, 2026	Our paper P3-LLM has been accepted to ISCA 2026.
Jan, 2025	I received the Student Travel Grant for HPCA 2025.
Nov, 2024	Our paper BitMoD has been accepted to HPCA 2025.
Jul, 2024	Our paper BBS has been accepted to MICRO 2024.
Oct, 2023	Our paper M4BRAM has been accepted to FPT 2023.
Mar, 2023	Our paper BRAMAC has been accepted to FCCM 2023.
Aug, 2022	Start my PhD study at Cornell University!

Selected Publications

ISCA

P3-LLM: Unlocking Efficient Processing-In-Memory for Edge LLM Inference with Hybrid Numerical Formats

Yuzong Chen, Chao Fang, Xilai Dai, Yuheng Wu, Thierry Tambe, Marian Verhelst, and Mohamed S. Abdelfattah

IEEE/ACM International Symposium on Computer Architecture

arXiv Bib Code

@article{p3llm,
  title = {P3-LLM: Unlocking Efficient Processing-In-Memory for Edge LLM Inference with Hybrid Numerical Formats},
  author = {Chen, Yuzong and Fang, Chao and Dai, Xilai and Wu, Yuheng and Tambe, Thierry and Verhelst, Marian and Abdelfattah, Mohamed S.},
  journal = {IEEE/ACM International Symposium on Computer Architecture},
  year = {2026},
}

HPCA

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration

Yuzong Chen, Ahmed F. AbouElhamayed, Xilai Dai, Yang Wang, Marta Andronic, George A. Constantinides, and Mohamed S. Abdelfattah

IEEE International Symposium on High-Performance Computer Architecture

arXiv Bib Code

@article{bitmod,
  title = {BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration},
  author = {Chen, Yuzong and AbouElhamayed, Ahmed F. and Dai, Xilai and Wang, Yang and Andronic, Marta and Constantinides, George A. and Abdelfattah, Mohamed S.},
  journal = {IEEE International Symposium on High-Performance Computer Architecture},
  year = {2025},
}

MICRO

BBS: Bi-directional Bit-level Sparsity for Deep Learning Acceleration

Yuzong Chen, Jian Meng, Jae-sun Seo, and Mohamed S. Abdelfattah

IEEE/ACM International Symposium on Microarchitecture

arXiv Bib Code

@article{bbs,
  title = {BBS: Bi-directional Bit-level Sparsity for Deep Learning Acceleration},
  author = {Chen, Yuzong and Meng, Jian and Seo, Jae-sun and Abdelfattah, Mohamed S.},
  journal = {IEEE/ACM International Symposium on Microarchitecture},
  year = {2024},
}

FCCM

BRAMAC: Compute-in-BRAM Architectures for Multiply-Accumulate on FPGAs

Yuzong Chen, and Mohamed S. Abdelfattah

IEEE International Symposium on Field-Programmable Custom Computing Machines

arXiv Bib Code

@article{bramac,
  title = {BRAMAC: Compute-in-BRAM Architectures for Multiply-Accumulate on FPGAs},
  author = {Chen, Yuzong and Abdelfattah, Mohamed S.},
  journal = {IEEE International Symposium on Field-Programmable Custom Computing Machines},
  year = {2023},
}