Hi! I am Zhengyu Hu🤗

I am currently an M.Phil. student (2023.9 – Present) at the Hong Kong University of Science and Technology, where I am fortunate to be advised by Prof. Hui Xiong. My current research interests are Data-Centric AI/ML, particularly in the evaluation, alignment, and optimization of LLMs and VLMs. I am also very fortunate to have the opportunity to collaborate with Jieyu Zhang from the University of Washington and Prof. Kaize Ding from Northwestern University.

I am currently a research intern at Microsoft Research Lab, where I am fortunate to work with Dr. Xing Xie, Dr. Nicholas Jing Yuan, and Dr. Jianxun Lian. Before joining MSRA, I worked at Meituan (Foundation Model Group) as a research intern, supervised by Dr. Jingang Wang and Dr. Zhengyu Chen.

📢 News

• 2025.12 🧑‍💻 I will join Qwen Team (Foundation Model Group) at Alibaba as a research intern, contribute to the development of the Qwen3.5 model family.
• 2025.11 🎉 Our paper Towards Acyclic Preference Evaluation of Language Models via Multiple Evaluators is accepted to AAAI 2026. I will be in Singapore from Jan 20 to Jan 27 — feel free to reach out. See you there!
• 2025.09 🎉 Our cognitive / systemic analysis of LLM learning ability (Unveiling the Learning Mind of Language Models: A Cognitive Framework and Empirical Study) is accepted to NeurIPS 2025. I will be in San Diego from Dec 2 to Dec 7. See you there!
• 2025.08 🎉 Our work on Explaining Length Bias in LLM-Based Preference Evaluations is accepted to EMNLP 2025. I will be in Suzhou from Nov 4 to Nov 9 — feel free to reach out. See you there!
• 2025.05 🎉 Our paper Editable Concept Bottleneck Models is accepted to ICML 2025.
• 2024.09 🎉 Our paper Let’s Ask GNN: Empowering Large Language Model for Graph In-Context Learning is accepted to EMNLP 2024.
• 2024.07 🧑‍💻 I join Microsoft Research Lab as a research intern.

📦 Older news

• 2024.06 🤝 I start a research internship at University of Washington, Seattle with Prof. Ranjay Krishna and Jieyu Zhang.
• 2024.02 🧑‍💻 I join Meituan (Foundation Model Group) as a research intern, supervised by Dr. Zhengyu Chen.
• 2024.01 🤝 I start my research internship at Northwestern University with Prof. Kaize Ding.
• 2023.09 🎉 Our paper On the Trade-off of Intra-/Inter-class Diversity for Supervised Pre-training is accepted to NeurIPS 2023.
• 2023.09 🎓 I start my M.Phil. in AI at HKUST, advised by Prof. Hui Xiong.

---

📝 Selected Publications

(* denotes equal contribution)

Below is a one-slide overview of my research focus for your reference (Links are clickable in the figure):

Preprints

• Population-Aligned Persona Generation for LLM-based Social Simulation
  • Zhengyu Hu, Jianxun Lian, Zheyuan Xiao, Max Xiong, Yuxuan Lei, Tianfu Wang, Kaize Ding, Ziang Xiao, Nicholas Jing Yuan, Xing Xie.
  • Submitted to ACL 2026.

Peer-reviewed

• Towards Acyclic Preference Evaluation of Language Models via Multiple Evaluators
  • Zhengyu Hu, Jieyu Zhang, Zhihan Xiong, Alexander Ratner, Kaize Ding, Ranjay Krishna.
  • Accepted by DATA-FM@ICLR 2025
  • Accepted by AAAI 2026.
• Unveiling the Learning Mind of Language Models: A Cognitive Framework and Empirical Study
  • Zhengyu Hu, Jianxun Lian, Zheyuan Xiao, Seraphina Zhang, Tianfu Wang, Nicholas Jing Yuan, Xing Xie, Hui Xiong.
  • Accepted by NeurIPS 2025.
• Explaining Length Bias in LLM-Based Preference Evaluations
  • Zhengyu Hu, Linxin Song, Jieyu Zhang, Zheyuan Xiao, Tianfu Wang, Nicholas Jing Yuan, Jianxun Lian, Kaize Ding, Hui Xiong.
  • Accepted by DATA-FM@ICLR 2025
  • Accepted by EMNLP 2025 (Findings).
• Editable Concept Bottleneck Models
  • Lijie Hu*, Chenyang Ren*, Zhengyu Hu*, Hongbin Lin, Cheng-Long Wang, Hui Xiong, Di Wang.
  • Accepted by DATA-FM@ICLR 2025
  • Accepted by ICML 2025.
• Let’s Ask GNN: Empowering Large Language Model for Graph In-Context Learning
  • Zhengyu Hu*, Yichuan Li*, Zhengyu Chen, Jingang Wang, Han Liu, Kyumin Lee, Kaize Ding.
  • Accepted by EMNLP 2024 (Findings).
• On the Trade-off of Intra-/Inter-class Diversity for Supervised Pre-training
  • Jieyu Zhang*, Bohan Wang*, Zhengyu Hu, Pang Wei Koh, Alexander Ratner.
  • Accepted by NeurIPS 2023.
• Leveraging Relational Graph Neural Network for Transductive Model Ensemble
  • Zhengyu Hu, Jieyu Zhang, Haonan Wang, Siwei Liu, Shangsong Liang.
  • Accepted by SIGKDD 2023.

---

🎓 Education

• Hong Kong University of Science and Technology - Master of Philosophy in Artificial Intelligence.
• Northeastern University - Bachelor of Engineering in Computer Science and Technology.

---

🏅 Professional Service

Reviewer:

• Conference: SIGKDD 2023, NeurIPS 2023, AISTATS 2024, CVPR 2024, WWW 2024, ICLR 2024, COLING 2024, ACL 2024, ACM MM 2024, SIGKDD 2024, ECCV 2024, EMNLP 2024, NeurIPS 2024, AAAI 2025, SIGKDD 2025, ICLR 2025, AISTATS 2025, NAACL 2025, ICML 2025, ACL 2025, EMNLP 2025, NeurIPS 2025, SIGKDD 2026, AAAI 2026, WWW 2026, ICLR 2026, CVPR 2026, AISTATS 2026
• Journal: DMLR, TNNLS

---

🚀 Dream

As Saint Augustine once said, “The world is a book, and those who do not travel read only one page.”

My dream is to travel around the world one day!