Hi, I’m Kehan Guo, a Ph.D student in Computer Science and Engineering at the University of Notre Dame, supervised by Professor Xiangliang Zhang. I am also glad to be a member of the NSF Center for Computer Assisted Synthesis (C-CAS), where we collaborate with chemists and data scientists to develop data-driven approaches that make synthetic chemistry more predictable and efficient.

Previously, I completed my Master’s at Boston University, where I worked with Professor Lei Tian.

I am always open to connecting with colleagues in my field and across interdisciplinary domains, as I strongly believe in the value of collaboration. If my research interests you, please feel free to reach out via email.

📖 Research

My research is centered on three pivotal topics:

• Enhancing Reasoning of Generative Models: Developing robust frameworks to evaluate and improve the reasoning and planning ability of foundational generative models through LLM agent and reinforcement learning.
• Exploring data-centric approaches for scalable model alignment and adaptation , aiming to push LLMs toward greater robustness, efficiency, and generalization across diverse tasks and domains
• Effectiveness in Downstream Applications: Critically assessing the practical impact of current AI technologies on downstream applications, particularly their transformative potential in fields like AI4Science, agentic models, and social sciences.

🔥 News

• 2025.02: 📑📑 Check out latest preprint: AI in Spectroscopy,HHH principle
• 2025.02: 🎉🎉 I will join Amazon AWS as an Applied Scientist Intern in 2025 Summer. See you in NYC!
• 2024.12: 🎉🎉 Thrilled to be awarded OpenAI’s Researcher Access Program.
• 2024.09: 🎉🎉 MolPuzzle has been accepted by NeurIPS 2024 Dataset and Benchmark Track as a spotlight!
• 2024.09: 🎉🎉 One paper has been accepted by main conference of EMNLP 2024!
• 2024.06: 🎉🎉 I passed my Ph.D. Qualification exam!
• 2024.05: 🎉🎉 One paper has been accepted by ACL 2025
• 2023.12: 🎉🎉 One paper has been accepted by AAAI 2024.
• 2023.09: 🎉🎉 One first-author paper has been accepted by NeurIPS 2023
• 2023.04: 🎉🎉 One paper has been accepted by IJCAI 2023

📎 Selected Publications

See more publications in my Google Scholar

NeurIPS 2024 as Spotlight

Can LLMs Solve Molecule Puzzles? A Multimodal Benchmark for Molecular Structure Elucidation

Kehan Guo, Bozhao Nan, Yujun Zhou, Taicheng Guo, Zhichun Guo, Mihir Surve, Zhenwen Liang, Nitesh V. Chawla, Olaf Wiest, Xiangliang Zhang

Code

NeurIPS 2023

What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks

Kehan Guo, Taicheng Guo∗ , Bozhao Nan, Zhenwen Liang, Zhichun Guo, Nitesh V. Chawla, Olaf Wiest, Xiangliang Zhang

Code

• LabSafety Bench: Benchmarking LLMs on Safety Issues in Scientific Labs, Yujun Zhou, Jingdong Yang, Kehan Guo, Pin-Yu Chen, Tian Gao, Werner Geyer, Nuno Moniz, Nitesh V Chawla, Xiangliang Zhang

• Defending Jailbreak Prompts via In-Context Adversarial Game, Yujun Zhou, Yufei Han, Haomin Zhuang, Taicheng Guo, Kehan Guo, Zhenwen Liang, Hongyan Bao, and Xiangliang Zhang

• SceMQA: A Scientific College Entrance Level Multimodal Question Answering Benchmark, Zhenwen Liang, Kehan Guo, Gang Liu, Taicheng Guo, Yujun Zhou, Tianyu Yang, Jiajun Jiao, Renjie Pi,Jipeng Zhang, Xiangliang Zhang

• Uncertainty-aware Yield Prediction with Multi-modal Molecular Features Jiayuan Chen, Kehan Guo, Zhen Liu, Olexandr Isayev, Xiangliang Zhang

• Graph-based Molecular Representation Learning Zhichun Guo, Kehan Guo, Bozhao Nan, Yijun Tian, Roshni G. Iyer, Yihong Ma, Olaf Wiest, Xiangliang Zhang, Wei Wang, Chuxu Zhang, Nitesh V. Chawla

📖 Educations

• 2022.09 - Present, Ph.D, University of Notre Dame
• 2020.09 - 2022.05, M.S, Boston University

💻 Services

• 2025, Reviewer for ICLR 2025, KDD 2025, WWW 2025, ACL 2025
• 2024, Reviewer for ACL 2024, WWW 2024