profile image
“和光同尘,与时舒卷”

Jiacong Hu (胡佳聪)

Researcher @Zhejiang University

I am currently a Hundred Talents Researcher and Ph.D. supervisor at the State Key Laboratory of Blockchain and Data Security, Zhejiang University. I am also a member of the VIPA group at Zhejiang University, led by Prof. Mingli Song. Previously, I earned my Ph.D. from the College of Computer Science and Technology at Zhejiang University.

Research Framework

My current research mainly focuses on AI trust and safety, with a particular emphasis on agent, including both single-agent and multi-agent systems. The application scenarios include digital environments, among others.

Research Framework

Another major direction of my research is the fast evaluation and optimization of AI models, including multimodal large language models and conventional models. The application scenarios include wireless communications, among others.

My long-term research goal is to develop correct, safe, and trustworthy artificial intelligence, and to promote its real-world deployment across a wide range of domains.

Outside of research, I enjoy photography 📷 and playing badminton 🏸.

Latest News

View all

Selected Publications

View all
  1. MAD-Bench: How Do Multimodal Agents Deceive You?

    Hao Gu, Mingli Song, Jiacong Hu*
    Advances in Neural Information Processing Systems(NeurIPS)2026Project
  2. V-ERR: Visual Evidence Re-checking Reinforcement in Multimodal Reasoning

    Hao Gu, Zhihui Yang, Hanyang Yuan, Haoze Jiang, Jiacong Hu*
    Underreview(Underreview)2026
  3. Causal Separation: A Theory of Representation and Recursive Self-Improvement

    Zhenyu Li, Zhihui Yang, Jiacong Hu
    Underreview(Underreview)2026
  4. Parameter Manifold Purification

    Jiacong Hu, Jinxun Wu, Shengxuming Zhang, Shunyu Liu, Haofei Zhang, Mingli Song, Zunlei Feng
    International Conference on Machine Learning(ICML)2026ProjectCode
  5. Model LEGO: Creating Models Like Disassembling and Assembling Building Blocks

    Jiacong Hu, Jing Gao, Jingwen Ye, Yang Gao, Xingen Wang, Zunlei Feng, Mingli Song
    Advances in Neural Information Processing Systems(NeurIPS)2024ProjectCode
  6. Transformer Doctor: Diagnosing and Treating Vision Transformers

    Jiacong Hu, Hao Chen, Kejia Chen, Yang Gao, Jingwen Ye, Xingen Wang, Mingli Song, Zunlei Feng
    Advances in Neural Information Processing Systems(NeurIPS)2024ProjectCode
  7. Vision Mamba Mender

    Jiacong Hu, Anda Cao, Zunlei Feng, Shengxuming Zhang, Yi Wang, Lingxiang Jia, Mingli Song
    Advances in Neural Information Processing Systems(NeurIPS)2024ProjectCode
  8. Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models

    Kejia Chen, Jiawen Zhang, Jiacong Hu, Yu Wang, Jian Lou, Zunlei Feng, Mingli Song
    International Conference on Machine Learning(ICML)2025ProjectCode
  9. Improving Adversarial Robustness via Feature Pattern Consistency Constraint

    Jiacong Hu, Jingwen Ye, Zunlei Feng, Jiazhen Yang, Shunyu Liu, Xiaotian Yu, Lingxiang Jia, Mingli Song
    Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence(IJCAI)2024Project
  10. Model doctor: A simple gradient aggregation strategy for diagnosing and treating cnn classifiers

    Zunlei Feng, Jiacong Hu, Sai Wu, Xiaotian Yu, Jie Song, Mingli Song
    Proceedings of the AAAI Conference on Artificial Intelligence(AAAI)2022Project
  11. A location constrained dual-branch network for reliable diagnosis of jaw tumors and cysts

    Jiacong Hu, Zunlei Feng, Yining Mao, Jie Lei, Dan Yu, Mingli Song
    Medical Image Computing and Computer Assisted Intervention(MICCAI)2021

Services

View all

Area Chair

  • International Conference on Learning Representations (ICLR) 2027

Reviewer

  • Neural Information Processing Systems (NeurIPS) 2025, 2026
  • International Conference on Machine Learning (ICML) 2026
  • International Conference on Learning Representations (ICLR) 2026
  • Computer Vision and Pattern Recognition (CVPR) 2025, 2026
  • European Conference on Computer Vision (ECCV) 2026
  • AAAI Conference on Artificial Intelligence (AAAI) 2027

Awards

View all
  • 2026 - NeurIPS 2026 Top Reviewer (Top 8%)
  • 2026 - ICML 2026 Gold Reviewer (Top 25%)
  • 2026 - Zhejiang University Outstanding Doctoral Dissertation (Top 5%)
  • 2025 - NeurIPS 2025 Top Reviewer (Top 8%)
  • 2025 - Outstanding Graduate, Zhejiang Province (Provincial Level, Top 5%)
  • 2025 - Outstanding Graduate, Zhejiang University (University Level)
  • 2021 - National Graduate Scholarship
  • 2019 - National Second Prize, Chinese Collegiate Computing Competition
  • 2019 - Honorable Mention, The Mathematical Contest in Modeling (MCM)
  • 2018 - National Third Prize, Chinese Collegiate Computing Competition

Selected Projects

View all

Comprehensive Multidimensional Evaluation of Deep Models

An online platform for comprehensive evaluation of deep learning model accuracy, robustness, fairness, and transferability.

June 20, 2024

project image