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 at the State Key Laboratory of Blockchain and Data Security, Zhejiang University, and also a member of the VIPA group, led by Prof. Mingli Song. Prior to this, I obtained my Ph.D. from the College of Computer Science and Technology at Zhejiang University.

My current research mainly focuses on AI safety and trustworthiness, 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 efficient optimization, analysis, and evaluation of AI models, covering multimodal large language models, large language models, and conventional models. The application scenarios include wireless communications, among others.

Research Framework

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 🏸.

News

Selected Publications

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

    Hao Gu, Mingli Song, Jiacong Hu*
    Underreview(Underreview)2026
  2. Parameter Manifold Purification

    Jiacong Hu, Jinxun Wu, Shengxuming Zhang, Shunyu Liu, Haofei Zhang, Mingli Song, Zunlei Feng
    International Conference on Machine Learning(ICML)2026
  3. Improving Multimodal Reasoning via Recurrent Partitioned Evidence Reinforcement

    Hao Gu, Hanyang Yuan, Haoze Jiang, Mingli Song, Jiacong Hu*
    Underreview(Underreview)2026
  4. 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)2024
  5. 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)2024
  6. Vision Mamba Mender

    Jiacong Hu, Anda Cao, Zunlei Feng, Shengxuming Zhang, Yi Wang, Lingxiang Jia, Mingli Song
    Advances in Neural Information Processing Systems(NeurIPS)2024
  7. Association Pattern-aware Fusion for Biological Entity Relationship Prediction

    Lingxiang Jia, Yuchen Ying, Zunlei Feng, Zipeng Zhong, Shaolun Yao, Jiacong Hu, Mingjiang Duan, Xingen Wang, Jie Song, Mingli Song
    Advances in Neural Information Processing Systems(NeurIPS)2024
  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)2025
  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)2024
  10. Hundredfold Accelerating for Pathological Images Diagnosis and Prognosis through Self-reform Critical Region Focusing

    Xiaotian Yu, Haoming Luo, Jiacong Hu, Xiuming Zhang, Yuexuan Wang, Wenjie Liang, Yijun Bei, Mingli Song, Zunlei Feng
    Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence(IJCAI)2024
  11. 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)2022
  12. 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

Awards

Selected Projects

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