I am (Andrew) Zhanke Zhou, a Ph.D. student at TMLR group of Hong Kong Baptist University, advised by Prof. Bo Han and working with Prof. Jiangchao Yao. My research focuses on trustworthy machine reasoning with foundation models (LLMs, VLMs) to solve complex problems such as mathematics and coding, as well as to accelerate scientific discovery and application in fields like biology, chemistry, and healthcare. I believe that reasoning is the essential pathway to achieving AGI. Trustworthy machine reasoning encompasses properties such as reasoning capability, robustness, safety, and explainability. My work involves developing systems, methodologies, and benchmarks to advance these areas:

• Reasoning System: How to construct a trustworthy reasoning system and solve complex problems?
  [AlphaApollo]
• Reasoning Methodology: How to boost the reasoning capabilities through learning?
  [GRA] [RGIB] [Subgraph] [ECON] [Neural Atoms] [AdaProp]
• Reasoning Benchmarks and Analysis: Where is the boundary of reasoning capabilities, and why?
  [AR-Bench] [NoRa] [Landscape of thoughts] [DeepInception] [MIA survey]

I am leading the reasoning team in TMLR group and fortunately working with several talented researchers. We welcome potential collaborations in various forms, including visiting PhD students, research assistants, and undergraduate trainees (please read this advertisement). Feel free to email Prof. Bo Han and me to discuss collaboration opportunities. We are also organizing the TMLR Young Scientist Seminars and actively seeking researchers interested in sharing their work. If you would like to give a talk, we encourage you to reach out to us.

E-mail: cszkzhou [at] comp.hkbu.edu.hk / zhanke [at] cs.stanford.edu / andrewzhou924 [at] gmail.com

📖 Education and Experience

• 2022.09 - present, Ph.D. Student, TMLR Group, Hong Kong Baptist University, advised by Prof. Bo Han.
• 2025.01 - 2025.07, Visiting Student, STAIR Lab, Stanford University, advised by Prof. Sanmi Koyejo.
• 2021.01 - 2024.05, Visiting Student, LARS Group, Tsinghua University, advised by Prof. Quanming Yao and Prof. Yongqi Zhang.
• 2017.09 – 2021.06, B.E. in Electronics and Information Engineering (SeedClass), Huazhong University of Science and Technology.

📝 Selected Publications

* Co-first author, ✉️ Corresponding author.

AlphaApollo: Orchestrating Foundation Models and Professional Tools into a Self-Evolving System
for Deep Agentic Reasoning.
Zhanke Zhou, Chentao Cao, Xiao Feng, Xuan Li, Zongze Li, Xiangyu Lu, Jiangchao Yao, Weikai Huang, Linrui Xu,
Tian Cheng, Guanyu Jiang, Yiming Zheng, Brando Miranda, Tongliang Liu, Sanmi Koyejo, Masashi Sugiyama, Bo Han✉️
Technical Report. [paper] [code]

From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?
Zhanke Zhou*, Xiao Feng*, Zhaocheng Zhu, Jiangchao Yao, Sanmi Koyejo, Bo Han✉️
ICML 2025. [paper] [code] [slides] [poster] [EN-video] [CN-video] [CN-blog]

From Debate to Equilibrium: Belief-Driven Multi-Agent LLM Reasoning via Bayesian Nash Equilibrium.
Yi Xie*, Zhanke Zhou*, Chentao Cao, Qiyu Niu, Tongliang Liu, Bo Han✉️
ICML 2025. [paper] [code] [slides] [poster] [EN-video] [CN-video]

Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models.
Zhanke Zhou*, Zhaocheng Zhu*, Xuan Li*, Mikhail Galkin, Xiao Feng, Sanmi Koyejo, Jian Tang, Bo Han✉️
NeurIPS 2025 Workshop / ICML 2025 Workshop. [paper] [code] [tutorial] [slides] [poster] [twitter]

Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond.
Qizhou Wang, Jin Peng Zhou, Zhanke Zhou, Saebyeol Shin, Bo Han✉️, Kilian Q. Weinberger
ICLR 2025. [paper] [code] [poster] [CN-blog]

Noisy Test-Time Adaptation in Vision-Language Models.
Chentao Cao, Zhun Zhong, Zhanke Zhou, Tongliang Liu, Yang Liu, Kun Zhang, Bo Han✉️
ICLR 2025. [paper] [code] [poster] [CN-blog]

Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?
Zhanke Zhou, Rong Tao, Jianing Zhu, Yiwen Luo, Zengmao Wang, Bo Han✉️
NeurIPS 2024. [paper] [code] [slides] [poster] [EN-video] [CN-video] [CN-blog] [twitter]

Mind the Gap Between Prototypes and Images in Cross-domain Finetuning.
Hongduan Tian, Feng Liu, Zhanke Zhou, Tongliang Liu, Chengqi Zhang, Bo Han✉️
NeurIPS 2024. [paper] [code]

DeepInception: Hypnotize Large Language Model to Be Jailbreaker.
Xuan Li*, Zhanke Zhou*, Jianing Zhu*, Jiangchao Yao, Tongliang Liu, Bo Han✉️
NeurIPS 2024 SafeGenAI Workshop. [paper] [code] [slides] [twitter] [CN-video] [CN-blog] [DeepTech]

Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection.
Chentao Cao, Zhun Zhong, Zhanke Zhou, Yang Liu, Tongliang Liu, Bo Han✉️
ICML 2024. [paper] [code] [slides] [poster] [CN-video] [CN-blog]

Less is More: One-shot Subgraph Reasoning on Large-scale Knowledge Graphs.
Zhanke Zhou, Yongqi Zhang, Jiangchao Yao, Quanming Yao, Bo Han✉️
ICLR 2024. [paper] [code] [slides] [poster] [EN-video]

Neural Atoms: Propagating Long-range Interaction in Molecular Graphs
through Efficient Communication Channel.
Xuan Li*, Zhanke Zhou*, Jiangchao Yao, Yu Rong, Lu Zhang, Bo Han✉️
ICLR 2024. [paper] [code] [slides] [poster] [EN-video] [CN-video]

Understanding Fairness Surrogate Functions in Algorithmic Fairness.
Wei Yao*, Zhanke Zhou*, Zhicong Li, Bo Han, Yong Liu✉️
TMLR 2024. [paper] [code]

Model Inversion Attacks: A Survey of Approaches and Countermeasures.
Zhanke Zhou*, Jianing Zhu*, Fengfei Yu*, Xuan Li, Xiong Peng, Tongliang Liu, Bo Han✉️
Arxiv 2024. [paper] [code] [CN-blog]

Combating Bilateral Edge Noise for Robust Link Prediction.
Zhanke Zhou, Jiangchao Yao✉️, Jiaxu Liu, Xiawei Guo, Quanming Yao,
Li He, Liang Wang, Bo Zheng, Bo Han✉️
NeurIPS 2023. [paper] [code] [slides] [poster] [EN-video] [CN-video] [CN-blog]

On Strengthening and Defending Graph Reconstruction Attack with Markov Chain Approximation.
Zhanke Zhou, Chenyu Zhou, Xuan Li, Jiangchao Yao✉️, Quanming Yao, Bo Han✉️
ICML 2023. [paper] [code] [slides] [poster] [EN-video] [CN-video] [CN-blog]

Adaprop: Learning Adaptive Propagation for Graph Neural Network Based Knowledge Graph Reasoning.
Yongqi Zhang*, Zhanke Zhou*, Quanming Yao✉️, Xiaowen Chu, Bo Han
KDD 2023. [paper] [code] [slides] [poster] [EN-video] [CN-video]

KGTuner: Efficient Hyper-parameter Search for Knowledge Graph Learning.
Yongqi Zhang, Zhanke Zhou, Quanming Yao✉️, Yong Li
ACL 2022 (long paper). [paper] [code] [slides] [poster] [EN-video] [CN-blog]

🎖 Awards

• 2025.03, Madam Hui Tang Shing Yan Fellowship (only two awardees in HKBU).
• 2024.11, Research Performance Award by COMP of HKBU.
• 2024.10, Excellent Research Gold Award of TMLR Group.
• 2024.06, Best Poster Award by COMP of HKBU.
• 2024.05, Best Research Performance Award by COMP of HKBU.
• 2023.11, Research Excellence Award by COMP of HKBU.
• 2021.06, Honorary degree of HUST (Top 2%, highest honour for undergrad).
• 2021.06, Outstanding Graduate Award of HUST.

💬 Talks

• 2025.10, Towards Trustworthy Reasoning Agents: Understanding, Learning, and Systematizing, @LARS Group, THU.
• 2025.07, Towards Trustworthy Machine Reasoning: Noisy Rationales, Incomplete Information, and Interpretability, @Rose ML Lab, UCSD.
• 2025.06, Can Large Language Models Ask the Right Questions under Incomplete Information?, @AI Time, Online. [Video]
• 2024.11, Seminar on Trustworthy Machine Learning and Foundation Models @AI Time, Online. [Video]
• 2023.11, Seminar on Trustworthy Machine Learning with Imperfect Data @TechBeat, Online. [Video]
• 2023.11, Youth PhD Talk on Trustworthy Machine Learning @AI Time, Online. [Video]

💻 Services

• Conference Reviewer for NeurIPS, ICML, ICLR, AISTATS, ACML, AAAI, IJCAI, COLM, ARR, CIKM, SIGKDD.
• Journal Reviewer for TPAMI, TMLR, NEUNET, TNNLS, TKDE.

🏫 Teaching

• Teaching Assistant for COMP7250: Machine Learning.
• Teaching Assistant for COMP3015: Data Communications and Networking.
• Teaching Assistant for COMP7070: Advanced Topics in Artificial Intelligence and Machine Learning.