Aozhong Zhang

I'm a Ph.D. candidate in Mathematics supervised by Prof. Penghang Yin at SUNY-Albany. Before that, I received my bachelor's degree in Mathematics from Sun Yat-sen University in 2021.

My research focuses on efficient machine learning (Quantization, Pruning, and KV Cache Compression) and Long-Context Extention.

Email  /  Scholar  /  Github

profile photo
Awards
  • 2025 IBM PhD Fellowship
  • NeurIPS 2024 Student Travel Award
Industry Experience
b3do
Waymo · Summer Internship
May 2026 - Aug. 2026, Mountain View, CA
b3do
IBM · Research Internship
Research on KV Cache Compression and Long-Context Extention.
May 2025 - Aug. 2025, Yorktown Heights, NY
Publications
b3do Frayed RoPE and Long Inputs: A Geometric Perspective
Davis Wertheimer, Aozhong Zhang, Derrick Liu, Penghang Yin, Naigang Wang
ICLR 2026
PDF
b3do DiaBlo: Diagonal Blocks Are Sufficient For Finetuning
Selcuk Gurses*, Aozhong Zhang*, Yanxia Deng, Xun Dong, Xin Li, Naigang Wang, Penghang Yin, Zi Yang
ICLR 2026
PDF / Code
b3do CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization
Yanxia Deng*, Aozhong Zhang*, Selcuk Gurses, Naigang Wang, Zi Yang, Penghang Yin
TMLR
PDF / Code
b3do MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization
Aozhong Zhang, Naigang Wang, Yanxia Deng, Xin Li, Zi Yang, Penghang Yin
NeurIPS 2024
PDF / Code
b3do COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization
Aozhong Zhang, Zi Yang, Naigang Wang, Yingyong Qi, Jack Xin, Xin Li, Penghang Yin
IEEE Access
PDF / Code

Academic Service

 Reviewer, NeurIPS 2026, 2025, 2024
Reviewer, ICLR 2026, 2025
Reviewer, ICML 2026, 2025
Reviewer, TMLR