Chentao Cao

Chentao Cao

Ph.D. student at TMLR Group of HKBU.

I am Chentao Cao, a second-year Ph.D. student at TMLR group of Hong Kong Baptist University, advised by Prof. Bo Han and working with Prof. Zhun Zhong. My research focuses on trustworthy machine reasoning with foundation models. I hope my research can help machines collaborate with humans for the common good.

My recent work includes:

Education

  • 2024.09 - present, Ph.D. Student, TMLR Group, Hong Kong Baptist University, advised by Prof. Bo Han, worked closely with Prof. Zhun Zhong.
  • 2020.09 - 2023.06, M.E. in Computer Technology, University of Chinese Academy of Sciences, advised by Prof. Yanjie Zhu and Prof. Dong Liang, worked closely with Prof. Zhuo-Xu Cui.
  • 2016.09 – 2020.06, B.E. in Communication Engineering, Harbin Institute of Technology.

Selected Publications

* Co-first author, † Corresponding author.

Selected Preprint

  • 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]

Selected Conference

  • Reasoned Safety Alignment: Ensuring Jailbreak Defense via Answer-Then-Check
    Chentao Cao, Xiaojun Xu, Bo Han†, Hang Li.
    In ICLR 2026. [Paper] [Website] [Dataset]

  • DualCnst: Enhancing Zero-Shot Out-of-Distribution Detection via Text-Image Consistency in Vision-Language Models
    Fayi Le, Wenwu He†, Chentao Cao, Dong Liang†, Zhuo-Xu Cui†.
    In NeurIPS 2025. [Paper] [Code]

  • 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†.
    In ICML 2025. [Paper] [Code]

  • Noisy Test-Time Adaptation in Vision-Language Models
    Chentao Cao, Zhun Zhong†, Zhanke Zhou, Tongliang Liu, Yang Liu, Kun Zhang, Bo Han†.
    In ICLR 2025. [Paper] [Code]

  • Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection
    Chentao Cao, Zhun Zhong†, Zhanke Zhou, Yang Liu, Tongliang Liu, Bo Han†.
    In ICML 2024. [Paper] [Code]

Selected Journal

  • SPIRiT-Diffusion: Self-Consistency Driven Diffusion Model for Accelerated MRI
    Zhuo-Xu Cui*, Chentao Cao*, Yue Wang*, Sen Jia, Jing Cheng, Xin Liu, Hairong Zheng, Dong Liang†, Yanjie Zhu†
    IEEE Transactions on Medical Imaging, 2024. [Paper] [Code]

  • High-Frequency Space Diffusion Model for Accelerated MRI
    Chentao Cao*, Zhuo-Xu Cui*, Yue Wang*, Shaonan Liu, Taijin Chen, Hairong Zheng, Dong Liang, Yanjie Zhu†
    IEEE Transactions on Medical Imaging, 2024. [Paper] [Code]

Awards

  • 2024.06, ICML Travel Award.

Talks

  • 2025.03, Noisy Test-Time Adaptation in Vision-Language Models @AI Time, Online.
  • 2024.06, Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection @AI Time, Online.

Tutorials Organizer

  • AAAI 2026 Tutorial on Trustworthy Machine Reasoning with Foundation Models. [Website] [Slides]

Program Committee/Reviewer

  • Program Committee/Reviewer: NeurIPS, ICML, ICLR.
  • Journal Reviewer: TPAMI, IJCV, JAIR, NEUNET.

Teaching

  • Teaching Assistant for COMP3065 (UG) Artificial Intelligence Application Development, Sem. 2, 2025.
  • Teaching Assistant for COMP7025 (G) Artificial Intelligence for Digital Transformation, Sem. 1, 2025.
  • Teaching Assistant for COMP7025 (G) Artificial Intelligence for Digital Transformation, Sem. 2, 2024.