Lucheng Fu.

Ph.D. CSE · Georgia Tech
Atlanta, GA

About

Hello there! My name is Lucheng Fu.

I am a Ph.D. student in Computational Science and Engineering at the Georgia Institute of Technology, advised by Prof. B. Aditya Prakash.

My research is focused on AI for Science, Large Language Models, Robust Machine Learning, Agentic AI, and Prompt Optimization. I am passionate about exploring the application of these technologies to solve complex problems and build innovative systems.

News

Oct 2026

Two new preprints out — SourceLearn and Science Utopia.

Jun 2026

Three new preprints out — TextReg, UniSD, and a study on conformity in LLM revision.

Jan 2026

Beyond Magic Words accepted to ICLR 2026.

Publications

2026ICLR

Beyond Magic Words: Sharpness-Aware Prompt Evolving for Robust Large Language Models with TARE

Guancheng Wan*, Lucheng Fu*, Haoxin Liu, Yiqiao Jin, Hui Yi Leong, Eric Hanchen Jiang, Hejia Geng, Jinhe Bi, Yunpu Ma, Xiangru Tang†, B. Aditya Prakash†, Yizhou Sun†, Wei Wang†

Paper ↗ Code ↗

Textual Sharpness-Aware Evolving (TARE) framework

2026arXiv

From Knowledge Access to Source Learning: Developing Source-Specific Competence

Lucheng Fu, Kejing Xia, Yiyang Wang, Yiqiao Jin, Jinjin He, Xiyuan Yang, Haoxin Liu, Ye Yu, Haibo Jin, Yijia Xiao, Wenke Lee, B. Aditya Prakash, Haohan Wang

Paper ↗ Code ↗ Website ↗

2026arXiv

Science Utopia? Closed-Loop LLM Simulation of Academic Research Ecosystems

Yiqiao Jin, Yiyang Wang, Lucheng Fu, Bing He, Siheng Xiong, Yijia Xiao, B. Aditya Prakash, Josiah Hester, Srijan Kumar, James Evans, Jindong Wang

Paper ↗ Code ↗ Website ↗

Science Utopia closed-loop research ecosystem simulation

2026arXiv

TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization

Lucheng Fu, Ye Yu, Yiyang Wang, Yiqiao Jin, Haibo Jin, B. Aditya Prakash, Haohan Wang

Paper ↗ Code ↗ Website ↗

2026arXiv

UniSD: Towards a Unified Self-Distillation Framework for Large Language Models

Yiqiao Jin, Yiyang Wang, Lucheng Fu, Yijia Xiao, Yinyi Luo, Haoxin Liu, B. Aditya Prakash, Josiah Hester, Jindong Wang, Srijan Kumar

Paper ↗ Code ↗ Website ↗

UniSD unified self-distillation framework

2026arXiv

Easier to Mislead Than to Correct: Harmful and Beneficial Revision in LLM Conformity

Jiaming Qu, Lucheng Fu, Yibo Hu

Paper ↗ Code ↗

Beneficial vs harmful revision in LLM conformity

Education

2026 —

Ph.D., Computational Science & Engineering

Georgia Institute of Technology

2025 —

M.S., Computational Science & Engineering

Georgia Institute of Technology

2021 – 25

B.S., Computer Science

Wuhan University

Lucheng Fuluchengfu@gatech.edu