Zhenyuan Zhang

Ph.D. Student at HKUST, AIS, Artificial Intelligence

prof_pic.jpg

Be Better

I am Zhenyuan Zhang, a Ph.D. student in AIS at The Hong Kong University of Science and Technology (HKUST), supervised by Prof. Yike Guo. Before joining HKUST, I was a Ph.D. student (Direct Entry) in Computer Science and Technology at Nanjing University of Science and Technology (NJUST), supervised by Prof. Jianfeng Lu. I received my B.Eng. in Software Engineering from NJUST in 2021.

My research interests center on AI agents and embodied AI, including agent memory, motion generation, and VLA. Previously, I worked on image restoration and adversarial robustness.

news

Apr 04, 2026 ClawNet Check out ClawNet, our human-agent symbiosis framework from HKGAI@HKUST for AI agent governance! Check out our technical report!
Feb 10, 2026 :rocket: Our paper MemFly is accepted by ICLR’26 MemAgent Workshop! Check it out!
Jan 01, 2026 :fire: One paper Motion-R1 is accepted by ICLR 2026!
Sep 01, 2025 :tada: One paper IR3D-Bench is accepted by NeurIPS 2025!
Feb 01, 2025 :star2: Started my Ph.D. in Artificial Intelligence at HKUST, supervised by Prof. Yike Guo.
Jan 01, 2025 :sparkles: One paper on Multi-Scale Semantic-Guidance Networks is accepted by IEEE TIFS (CCF A)!
Feb 01, 2023 :confetti_ball: One paper on RobustSIRR is accepted by CVPR 2023!

selected publications

  1. Preprint
    clawnet.png
    ClawNet: Human-Symbiotic Agent Network for Cross-User Autonomous Cooperation
    Zhiqin Yang*, Zhenyuan Zhang*, Xianzhang Jia, Jun Song, Wei Xue, Yonggang Zhang, and Yike Guo
    2026
  2. Preprint
    memfly.png
    MemFly: On-the-Fly Memory Optimization via Information Bottleneck
    Zhenyuan Zhang, Xianzhang Jia, Zhiqin Yang, Zhenbo Song, Wei Xue, Sirui Han, and Yike Guo
    2026
  3. Motion-R1: Chain-of-Thought Reasoning and Reinforcement Learning for Human Motion Generation
    Runqi Ouyang*, Haoyun Li*, Zhenyuan Zhang*, Xiaofeng Wang, Zheng Zhu, Guan Huang, Hansi Rui, and Xingang Wang
    In International Conference on Learning Representations (ICLR), 2026
  4. IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering
    Parker Liu, Chenxin Li, Zhengxin Li, Yipeng Wu, Wuyang Li, Zhiqin Yang, Zhenyuan Zhang, Yunlong Lin, Sirui Han, and Brandon Y. Feng
    In Advances in Neural Information Processing Systems (NeurIPS), 2025
  5. Multi-Scale Semantic-Guidance Networks: Robust Blind Face Restoration Against Adversarial Attacks
    Zhenyuan Zhang*, Xingqun Qi*, Zhenbo Song, Zhiqin Yang, Jianfeng Lu, Muyi Sun, Man Zhang, and Zhenan Sun
    IEEE Transactions on Information Forensics and Security, 2025
  6. Robust Single Image Reflection Removal Against Adversarial Attacks
    Zhenbo Song*, Zhenyuan Zhang*, Kaihao Zhang, Wenhan Luo, Zhaoxin Fan, Wenqi Ren, and Jianfeng Lu
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023

tools & projects

  1. MioIsland logo
    Your AI agents live in the notch.
    A macOS Dynamic Island companion that monitors, approves, and routes Claude Code agent sessions straight from the MacBook notch — pixel cat included. Built with Swift / SwiftUI; pairs with the Code Light iPhone app for remote control.