Kexun Zhang

I am a second-year Ph.D. student in language technologies at Carnegie Mellon University, working with Lei Li and William Wang(UC Santa Barbara). I got my bachelor's in CS from Zhejiang University. I'm interested in natural/formal language processing and computational linguistics.

Email  /  GitHub  /  Scholar  /  Twitter

profile photo

Selected Research

* denotes equal contribution. † denotes project lead.

project image

HardTests: Synthesizing High-Quality Test Cases for LLM Coding


硬测:合成高质量测试盒子为了大语言模型写代码


Zhongmou He*, Yee Man Choi*, Kexun Zhang*†, et al.
preprint, 2025
paper / code GitHub Repo stars / website /

project image

Integrating Expertise of Software Engineering Agents


整合专长来自软件工程特工


Kexun Zhang, Weiran Yao, Zuxin Liu, et al.
ICLR, 2025
paper / code GitHub Repo stars /

project image

Scaling LLM Inference with Optimized Sample Compute Allocation


扩大大语言模型推理使用优化过的样本计算分配


Kexun Zhang, Shang Zhou, Danqing Wang, William Yang Wang, Lei Li
NAACL, 2025
paper / code GitHub Repo stars /

project image

SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement


穗搜:加强软件特工使用莫奈特卡洛树搜索和逐步改进


Antonis Antoniades*, Albert Örwall*, Kexun Zhang, Yuxi Xie, Anirudh Goyal, William Wang
ICLR, 2025
paper / code GitHub Repo stars /

project image

ALGO: Synthesizing Algorithmic Programs with LLM-Generated Oracle Verifiers


阿尔戈:合成算法程序使用大语言模型生成的神谕验证器


Kexun Zhang, Danqing Wang, Jingtao Xia, William Yang Wang, Lei Li
NeurIPS, 2023
paper / code GitHub Repo stars /




Fun stuff

I was a competitive programmer in Olympiad in Informatics and International Collegiate Programming Contests. I'm a silver medalist at CNOI, a gold medalist at ICPC Asia Regional, and a Master at Codeforces.

I'm an amateur performer of Xiangsheng (aka crosstalk), which is a Chinese stand-up comedy performed by two people.

Other than Mandarin Chinese, I'm a native speaker of Taizhou Wu. I'd be really happy to chat with you in it.


Design and source code from Jon Barron's website