Ziyang Huang

PhD Student, Computer Science · Johns Hopkins University

I am a PhD student in Computer Science at Center for Language and Speech Processing, Johns Hopkins University, co-advised by Prof. Benjamin Van Durme and Prof. Daniel Khashabi. I am broadly interested in the advancement and application of AI across the scientific community, with a focus on code generation and autonomous agents in service of scientific discovery.

Before the PhD, I completed my master's degree in Computer Science at Johns Hopkins University. I did my undergraduate studies at Purdue University with a dual major in Computer Science and Data Science, where I worked as a research assistant with Samuel Conte Professor Xiangyu Zhang and Zian Su on the pre-training and post-training of large language models for code learning, understanding, and generation.

Outside the lab I travel with a camera — see the photography page for where I have been :D

Publications

2026

FEROM: Frontier Endogenous Reveal-Order Marginal Policy Optimization for Masked Diffusion LMs

Zian Su, Ziyang Huang, Kaiyuan Zhang, Xiangyu Zhang

NeurIPS 2026

Can Coding Agents Reproduce Findings in Computational Materials Science?

Ziyang Huang, Yi Cao*, Ali K. Shargh*, Jing Luo, Ruidong Mei, Mohd Zaki, Zhan Liu, Wyatt Bunstine, William Jurayj, Somdatta Goswami, Tyrel McQueen, Michael Shields, Jaafar El-Awady, Paulette Clancy, Benjamin Van Durme, Nicholas Andrews, William Walden, Daniel Khashabi (*equal contribution)

COLM 2026

PDF Code Dataset Website

2025

μKE: Matryoshka Unstructured Knowledge Editing of Large Language Models

Zian Su*, Ziyang Huang*, Kaiyuan Zhang, Xiangyu Zhang (*equal contribution)

COLM 2025

PDF Code

Symbol Preference Aware Generative Models for Recovering Variable Names from Stripped Binary