Guangyao Chen

CGY.jpeg

I’m currently a Postdoctoral Researcher at AI for Science Institute, Cornell University. I received my Ph.D. degree at School of Computer Science, Peking University. I received my Bachelor degree in Computer Science from Wuhan University in 2018.

My research interests lie in open-world vision-language models and agentic reasoning systems that remain robust under distribution shift and unseen concepts. I focus on verification harnesses and deploy these agents to scientific problems. I’m always open to collaborations. Feel free to contact me if you are interested in collaborating or discussing research ideas.

news

2025.11  🎉🎉 Five papers (two oral papers) are accepted by the conference AAAI 2026.
2025.09  🎉🎉 One paper on crystal graph neural network is accepted by the journal JCIM.
2025.09  🎉🎉 One paper on few-shot learning is accepted by the conference NeurIPS 2025.
2025.08  🎉🎉 One paper on particle vision analysis is accepted by the journal Engineering.
2025.06  🎉🎉 One paper on symbolic reasoning is accepted by the conference ICCV 2025.
2025.05  🎉🎉 Three papers (two spotlight papers) are accepted by the conference ICML 2025.
2025.04  🎉🎉 One paper on LLMs for material is accepted by the journal Advanced Materials.
2025.03  🎉🎉 One workshop paper (spotlight presentation) is accepted by the conference CVPR 2025.
2024.11  🎉🎉 I awared the CSIG 2024 Outstanding PhD Thesis Award (10 people nationwide).
2024.09  🎉🎉 One paper on visual RL are accepted by the conference NeurIPS 2024.
2024.07  🎉🎉 Two papers on few-shot Learning are accepted by the conference ACMMM 2024.
2024.04  🎉🎉 One paper on autonomous agent is accepted by the conference IJCAI 2024.
2023.12  🎉🎉 One paper on incremental novel class discovery is accepted by the conference AAAI 2024.
2023.11 Invited talk at Qingyuan Workshop (Online).
2023.11 Invited talk at RLChina 2023 in Suzhou.
2023.06 I receive my Ph.D. degree in computer science from Peking University with Outstanding Doctoral Dissertation Award.
2022.09  🎉🎉 Two papers on image-based reinforcement learning and out-of-distribution detection are accepted by the conference NeurIPS 2022.

selected publications

  1. AAAI
    Start Small, Think Big: Curriculum-based Relative Policy Optimization for Visual Grounding
    Qingyang Yan*, Guangyao Chen*†, and Yixiong Zou
    In The Fortieth AAAI Conference on Artificial Intelligence, 2026 (Oral Presentation)
    arXiv
  2. AAAI
    Connecting the Dots: Training-Free Visual Grounding via Agentic Reasoning
    Liqin Luo*, Guangyao Chen*†, Xiawu Zheng, Yongxing Dai, Yixiong Zou, and 1 more author
    In The Fortieth AAAI Conference on Artificial Intelligence, 2026
    arXiv Code
  3. ICCV
    From Objects to Events: Unlocking Complex Visual Understanding in Object Detectors via LLM-guided Symbolic Reasoning
    Yuhui Zeng, Haoxiang Wu, Wenjie Nie, Guangyao Chen†, Xiawu Zheng, and 4 more authors
    In International Conference on Computer Vision, 2025
    arXiv Code
  4. ICML
    When Every Millisecond Counts: Real-Time Anomaly Detection via the Multimodal Asynchronous Hybrid Network
    Dong Xiao*, Guangyao Chen*†, Peixi Peng, Yangru Huang, Yifan Zhao, and 2 more authors
    In Forty-second International Conference on Machine Learning, 2025 (Spotlight Poster, Acceptance Rate: < 2.6%)
    Paper
  5. JCIM
    PSCG-Net: A Multi-Scale Crystal Graph Neural Network for Accelerated Materials Discovery
    Guangyao Chen*, Zhilong Wang*, and Fengqi You
    Journal of Chemical Information and Modeling, 2025 (Front cover)
    Paper Cover Code
  6. IJCAI
    AutoAgents: A Framework for Automatic Agent Generation
    Guangyao Chen*, Siwei Dong*, Yu Shu*, Ge Zhang, Sesay Jaward, and 3 more authors
    In The 33rd International Joint Conference on Artificial Intelligence, 2024 (Acceptance Rate: 15%)
    arXiv Code
  7. ACMMM
    MICM: Rethinking Unsupervised Pretraining for Enhanced Few-shot Learning
    Zhenyu Zhang*, Guangyao Chen*, Yixiong Zou, Zhimeng Huang, Yuhua Li, and 1 more author
    In ACM Multimedia, 2024 (Oral Presentation, Acceptance Rate: < 3.97%)
    Paper
  8. TPAMI
    Adversarial Reciprocal Points Learning for Open Set Recognition
    Guangyao Chen, Peixi Peng, Xiangqian Wang, and Yonghong Tian
    IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022 (Academician Shi Qingyun’s Outstanding Paper Award, Highly Cited Paper)
    arXiv Paper Code
  9. ICCV
    Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domain
    Guangyao Chen, Peixi Peng, Li Ma, Jia Li, Lin Du, and 1 more author
    In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Oct 2021
    arXiv Paper Code