avatar

Jiarui Yang (BU BU)

FUDAN
jryang24@m.fudan.edu.cn


About Me

I’m a second-year Ph.D. student in school of computer science at Fudan University, supervised by Prof. Jingjing Chen and Prof. Yu-Gang Jiang. Before that, I obtained B.E. degree in Computer Science and Technology from Zhejiang University, advised by Prof. Kejun Zhang and M.S. degree at the Institute of Information Engineering (IIE), Chinese Academy of Sciences, advised by Prof. Chuan Wang.

My current research interests lie at the intersection of Embodied Intelligence and Reinforcement Learning, with a particular focus on real-world robot reinforcement learning, real-world RL infrastructure, and reinforcement learning algorithms. I am also broadly interested in embodied agents and embodied recursive self-improvement (RSI). I am dedicated to building autonomous learning systems for robots, with the ultimate goal of enabling agents to acquire complex skills and adapt to dynamic, real-world environments with minimal human intervention.

Preprints

  1. StructRL paper teaser arXiv
    StructRL: Structured Action-Space Exploration for Flow-Based VLAs
    Jiarui Yang, Bin Zhu, Jingjing Chen, Na Zou, Yanwei Fu, Jianggang Zhu, Yu-Gang Jiang
    arXiv preprint, 2026.
    arXiv

  2. RAPolicy paper teaser arXiv
    Stable and Efficient Real-World Online VLA Post-Training via Asynchronous Replay-Anchored Policy Improvement
    Jiarui Yang, Jiajin Zhang, Bin Zhu, Jingjing Chen, Yu-Gang Jiang
    arXiv preprint, 2026.
    arXiv

Publications

  1. CVPR
    RC-NF: Robot-Conditioned Normalizing Flow for Real-Time Anomaly Detection in Robotic Manipulation
    Shijie Zhou, Bin Zhu, Jiarui Yang, Xiangyu Zhao, Jingjing Chen, Yu-Gang Jiang
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026.

  2. AAAI
    Actor-Critic for Continuous Action Chunks: A Reinforcement Learning Framework for Long-Horizon Robotic Manipulation with Sparse Reward
    Jiarui Yang, Bin Zhu, Jingjing Chen, Yu-Gang Jiang
    Association for the Advancement of Artificial Intelligence (AAAI), 2026 (oral).

  3. AAAI
    Semi-Supervised Clustering Framework for Fine-grained Scene Graph Generation
    Jiarui Yang, Chuan Wang, Jun Zhang, Shuyi Wu, Zhao Jinjing, Zeming Liu, Liang Yang
    Association for the Advancement of Artificial Intelligence (AAAI), 2025.

  4. MM
    Focusing on Flexible Masks: A Novel Framework for Panoptic Scene Graph Generation with Relation Constraints
    Jiarui Yang, Chuan Wang, Zeming Liu, Jiahong Wu, Dongsheng Wang, Liang Yang, Xiaochun Cao
    ACM International Conference on Multimedia (ACM MM), 2023.

  5. TIP
    Adaptive Feature Learning for Unbiased Scene Graph Generation
    Jiarui Yang, Chuan Wang, Liang Yang, Yuchen Jiang, Angelina Cao
    IEEE Transactions on Image Processing (TIP), 2023.

Internship Experience

Shanghai AI Laboratory, Research Intern (Feb. 2026 – Aug. 2026)


Awards


Academic Services

Paper Review



Powered by Jekyll and Minimal Light theme.