Fangzhao Zhang
Hi there 👋, I am Fangzhao. I am a PhD student in the Department of Electrical Engineering at Stanford University advised by Mert Pilanci and Stephen Boyd. Prior to joining Stanford, I obtained my bachelor’s degree from the University of British Columbia, majoring in math and computer science. My research interest lies broadly in optimization and AI topics.
I'm currently part-time at Bytedance Seed (system and infra group).
Happy to chat about research ideas :), feel free to contact via:
Research
- TERMS-Bench: Diagnosing LLM Negotiation Agents Beyond Deal Rate
Erica Zhang, Fangzhao Zhang, Aneesh Pappu, Batu El, Jose Blanchet, Susan Athey, Jiashuo Liu, James Zou
Preprint 2026
[pdf][code][arXiv][website] - Optimizer-Induced Mode Connectivity: From AdamW to Muon
Fangzhao Zhang*, Sungyoon Kim*, Erica Zhang, Yiqi Jiang, Mert Pilanci
Preprint 2026
[pdf][code][arXiv] - Learning When to Trust LLM Priors: A Validated Framework for Semantic Prior Integration
Erica Zhang*, Naomi Sagan*, Danny Tse, Fangzhao Zhang, Mert Pilanci, Jose Blanchet
Preprint 2026
[pdf][code][arXiv] - Analyzing Neural Network-Based Generative Diffusion Models through Convex Optimization
Fangzhao Zhang, Mert Pilanci
NeurIPS OPT Workshop 2025
[pdf][arXiv] - AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?
Ori Press, Brandon Amos, Haoyu Zhao, Yikai Wu, Samuel K. Ainsworth, Dominik Krupke, Patrick Kidger, Touqir Sajed, Bartolomeo Stellato, Jisun Park, Nathanael Bosch, Eli Meril, Albert Steppi, Arman Zharmagambetov, Fangzhao Zhang, David Pérez–Piñeiro, Alberto Mercurio, Ni Zhan, Talor Abramovich, Kilian Lieret, Hanlin Zhang, Shirley Huang, Matthias Bethge, Ofir Press
NeurIPS Datasets and Benchmarks 2025
[pdf][code][arXiv][website] - Solving Large Multicommodity Network Flow Problems on GPUs
Fangzhao Zhang, Stephen Boyd
Automation and Remote Control (ARC) 2025
[pdf][code][arXiv] - Active Learning of Deep Neural Networks via Gradient-Free Cutting Planes
Erica Zhang*, Fangzhao Zhang*, Mert Pilanci
International Conference on Machine Learning (ICML) 2025
[pdf][arXiv] - Newton Meets Marchenko-Pastur: Massively Parallel Second-Order Optimization with Hessian Sketching and Debiasing
Elad Romanov, Fangzhao Zhang, Mert Pilanci
International Conference on Learning Representations (ICLR) 2025
[pdf][arXiv] - Spectral Adapter: Fine-Tuning in Spectral Space
Fangzhao Zhang, Mert Pilanci
Conference on Neural Information Processing System (NeurIPS) 2024
[pdf] [code][arXiv] - Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models
Fangzhao Zhang, Mert Pilanci
International Conference on Machine Learning (ICML) 2024
[pdf] [code][arXiv] - Optimal Shrinkage for Distributed Second-Order Optimization
Fangzhao Zhang, Mert Pilanci
International Conference on Machine Learning (ICML) 2023
[pdf][arXiv] - Implementation of an Oracle-Structured Bundle Method for Distributed Optimization
Tetiana Parshakova, Fangzhao Zhang, Stephen Boyd
Optimization and Engineering 2023
[pdf] [code] [arXiv]
Teaching
Head TA: EE364A/CME364A (2024-2025 Winter, Stanford)
Honors
Stanford Graduate Fellowship Stanford 2021
Governor General's Academic Medal (media cover) UBC 2021