Hanlin Zhang

Logo

About

I am a CS PhD student at Harvard ML Foundations Group, advised by Sham Kakade.

I am interested in foundations and social implications of machine learning.

I received my Master's degree in Machine Learning at CMU and Bachelor's degree in Computer Science from SCUT, advised by Eric Xing.

Selected Works

How Does Critical Batch Size Scale in Pre-training?
Preprint, 2024. [Paper] [Blog] [Code]

Hanlin Zhang, Depen Morwani, Nikhil Vyas, Jingfeng Wu, Difan Zou, Udaya Ghai, Dhruv Madeka, Dean Foster, Sham Kakade.

Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models
ICML, 2024. [Paper] [Website] [Blog] [Code]
Hanlin Zhang, Benjamin L Edelman*, Danilo Francati*, Daniele Venturi, Giuseppe Ateniese, and Boaz Barak

A Study on the Calibration of In-context Learning
NAACL, 2024. NeurIPS workshop (Oral), 2023. [Paper] [Code]
Hanlin Zhang, Yi-Fan Zhang, Yaodong Yu, Dhruv Madeka, Dean Foster, Eric Xing, Himabindu Lakkaraju, Sham Kakade

Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark
ICML, 2023. (Oral) [Paper] [Website] [Code]
Alexander Pan, Chan Jun Shern, Andy Zou, Nathaniel Li, Steven Basart, Thomas Woodside, Jonathan Ng, Hanlin Zhang, Scott Emmons, Dan Hendrycks

Improved Logical Reasoning of Language Models via Differentiable Symbolic Programming
Findings of ACL, 2023. [Paper] [Code]
Hanlin Zhang*, Jiani Huang*, Ziyang Li, Mayur Naik, Eric Xing

Towards Principled Disentanglement for Domain Generalization
CVPR, 2022. (Oral) [Paper] [Code]
Hanlin Zhang*, Yi-Fan Zhang*, Weiyang Liu, Adrian Weller, Bernhard Schölkopf, Eric Xing

Theme by orderedlist