avatar

Ziyu Guo

Ph.D. Candidate
The Department of Computer Science and Engineering,
The Chinese University of Hong Kong

SHB 903, CUHK, Hong Kong S.A.R., China

 guoziyu86@gmail.com


About Me

I am a third-year PhD student at The Chinese University of Hong Kong supervised by Prof. Pheng-Ann Heng. Before that, I received my bachelor’s degree in Computer Science from Peking University supervised by Prof. Bin Cui.

I’m now joining Meta as a research intern. I previously worked as a research intern at Amazon AWS AI Lab, Roblox, Tencent, and Shanghai AI Laboratory.

My research interests mainly include Multi-modal Learning, Large Language/Vision Models, and 3D Vision.

Selected Publications and Preprints

* Equal contribution, # Corresponding author
CoT Reasoning for Visual Generation
  1. arXiv25
    Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step
    Ziyu Guo*, Renrui Zhang*, Chengzhuo Tong*, Zhizheng Zhao*, Peng Gao, Hongsheng Li#, Pheng-Ann Heng#.
    Under Review
    PDF Code


  2. NeurIPS25
    T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT
    Dongzhi Jiang*, Ziyu Guo*, Renrui Zhang*, Zhuofan Zong, Hao Li, Le Zhuo, Shilin Yan, Pheng-Ann Heng#, Hongsheng Li#.
    NeurIPS 2025
    PDF Code


  3. NeurIPS25
    Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO
    Chengzhuo Tong*, Ziyu Guo*, Renrui Zhang*, Wenyu Shan*, Xinyu Wei, Zhenghao Xing, Hongsheng Li#, Pheng-Ann Heng#.
    NeurIPS 2025
    PDF
    CoT Reasoning for Visual Understanding
  4. ACL25
    SciVerse: Unveiling the Knowledge Comprehension and Visual Reasoning of LMMs on Multi-modal Scientific Problems
    Ziyu Guo*, Renrui Zhang*, Hao Chen*, Jialin Gao*, Dongzhi Jiang, Jiaze Wang, Pheng-Ann Heng#.
    ACL 2025
    Webpage Benchmark


  5. ICML25
    MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency
    Dongzhi Jiang*, Renrui Zhang*, Ziyu Guo, Yanwei Li, Yu Qi, Xinyan Chen, Liuhui Wang, Jianhan Jin, Claire Guo, Shen Yan, Bo Zhang, Chaoyou Fu, Peng Gao, Hongsheng Li#.
    ICML 2025
    PDF Code Webpage Benchmark


  6. ICLR25
    MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine
    Renrui Zhang, Xinyu Wei, Dongzhi Jiang, Ziyu Guo, Shicheng Li, Yichi Zhang, Chengzhuo Tong, Jiaming Liu, Aojun Zhou, Bin Wei, Shanghang Zhang, Peng Gao, Chunyuan Li, Hongsheng Li#.
    ICLR 2025
    PDF Code


  7. ECCV24
    MathVerse: Does your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?
    Renrui Zhang, Dongzhi Jiang, Yichi Zhang, Haokun Lin, Ziyu Guo, Pengshuo Qiu, Aojun Zhou, Pan Lu, Kai-Wei Chang, Yu Qiao, Peng Gao, Hongsheng Li.
    ECCV 2024
    Webpage Benchmark


  8. ICLR25
    MMSearch: Benchmarking the Potential of Large Models as Multi-modal Search Engines
    Dongzhi Jiang*, Renrui Zhang*, Ziyu Guo, Yanmin Wu, Jiayi Lei, Pengshuo Qiu, Pan Lu, Zehui Chen, Guanglu Song, Peng Gao, Yu Liu, Chunyuan Li, Hongsheng Li#.
    ICLR 2025
    PDF Code Webpage Dataset
    3D Large Models
  9. arXiv23
    Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following
    Ziyu Guo*, Renrui Zhang*, Xiangyang Zhu, Yiwen Tang, Xianzheng Ma, Jiaming Han, Kexin Chen, Peng Gao, Xianzhi Li#, Hongsheng Li, Pheng-Ann Heng.
    Under Review
    PDF Code


  10. arXiv25
    Exploring the Potential of Encoder-free Architectures in 3D LMMs
    Yiwen Tang*, Ziyu Guo*, Zhuhao Wang*, Renrui Zhang, Qizhi Chen, Junli Liu, Delin Qu, Zhigang Wang, Dong Wang, Xuelong Li, Bin Zhao.
    Under Review
    PDF Code


  11. arXiv24
    SAM2Point: Segment Any 3D as Videos in Zero-shot and Promptable Manners
    Ziyu Guo*, Renrui Zhang*, Xiangyang Zhu*, Chengzhuo Tong, Peng Gao, Chunyuan Li, Pheng-Ann Heng#.
    Technical Report
    PDF Code Webpage Demo


  12. CVPR22
    PointCLIP: Point Cloud Understanding by CLIP
    Renrui Zhang*, Ziyu Guo*, Wei Zhang, Kunchang Li, Xupeng Miao, Bin Cui, Yu Qiao, Peng Gao, Hongsheng Li#.
    CVPR 2022
    PDF Code


  13. NeurIPS22
    Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training
    Renrui Zhang, Ziyu Guo, Rongyao Fang, Bin Zhao, Dong Wang, Yu Qiao, Hongsheng Li, Peng Gao#.
    NeurIPS 2022
    PDF Code
    3D & Multi-modality Learning
  14. ICCV25
    StyleMotif: Multi-Modal Motion Stylization using Style-Content Cross Fusion
    Ziyu Guo, Young Yoon Lee, Joseph Liu, Yizhak Ben-Shabat, Victor Zordan, Mubbasir Kapadia#.
    ICCV 2025
    Webpage


  15. ICLR24
    Personalize Segment Anything Model with One Shot
    Renrui Zhang, Zhengkai Jiang*, Ziyu Guo*, Shilin Yan, Junting Pan, Hao Dong, Peng Gao, Hongsheng Li#.
    ICLR 2024
    PDF Code


  16. ICCV23
    ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance
    Ziyu Guo*, Yiwen Tang*, Renrui Zhang*, Dong Wang, Zhigang Wang, Bin Zhao.
    ICCV 2023
    PDF Code


  17. AAAI23
    CALIP: Zero-Shot Enhancement of CLIP with Non-Parametric Attention
    Ziyu Guo*, Renrui Zhang*, Longtian Qiu*, Xupeng Miao, Bin Cui#.
    AAAI 2023 Oral
    PDF Code


  18. IJCAI23
    Joint-MAE: 2D-3D Joint Masked Autoencoders for 3D Point Cloud Pre-training
    Ziyu Guo*, Renrui Zhang*, Longtian Qiu, Xianzhi Li#, Pheng-Ann Heng.
    IJCAI 2023 Oral
    PDF


  19. WACV23
    Nearest Neighbors Meet Deep Neural Networks for Point Cloud Analysis
    Renrui Zhang, Liuhui Wang, Ziyu Guo, Jianbo Shi#.
    WACV 2023
    PDF

    Services

      Conference Reviewers
        NeurIPS 2023, ACM MM 2023, ICCV 2023, ICLR 2024, CVPR 2024, ICASSP 2024, ACL 2024, ECCV 2024, NeurIPS 2024, EMNLP 2024, ACL 2024, ICASSP 2025, ICLR 2025, CVPR 2025, NeurIPS 2025, WACV 2026
      Journal Reviewers
        TPAMI, IJCV, TCSVT, Neurocomputing, RA-L, Access