avatar

Zhi Gao (高志)

Associate Professor (tenure-track)
Beijing Institute of Technology
gaozhibit@bit.edu.cn


About Me

I am an associate professor (tenure-track) at the School of Computer Science and Technology, Beijing Institute of Technology (BIT). Before that, I was a postdoctoral research fellow at the School of Intelligence Science and Technology, Peking University, with Prof. Song-Chun Zhu.

E-mail: gaozhibit@bit.edu.cn, gaozhi_2017@126.com, and gaozhibit@gmail.com

Recruitment

I am always looking for highly motivated Master and Ph.D. students who have excellent mathematic and programming skills to work on machine learning, vision and language modeling, and Riemannian manifold analytics. Please do not hesitate to send me your CV, if you are interested in our group. (欢迎对计算机视觉、多媒体分析、机器学习等领域研究有兴趣的同学联系我，每年招收硕士生3-4名，博士生3-4名)[详细招生信息]

同时欢迎对计算机视觉、机器学习的本科生同学到实验室进行科研实习！

Education

I received my B.S. degree in computer science from the Beijing Institute of Technology (BIT), Beijing, China, in 2017.

I received my Ph.D. degree in computer science from the Beijing Institute of Technology (BIT), Beijing, China, in 2023, under the supervision of Prof. Yuwei Wu and Prof. Yunde Jia.

Research Interests

I am interested in computer vision and machine learning, including AI Agent, Multimodal Learning, Open-Environment Learning, and Riemannian Geometry. You can click them for more details.

AI Agents

  1. GUI KNOWLEDGE BENCH: REVEALING THE KNOWLEDGE GAP BEHIND VLM FAILURES IN GUI TASKS
    Chenrui Shi*, Zedong Yu*, Zhi Gao*, Ruining Feng, Enqi Liu, Yuwei Wu, Yunde Jia, Liuyu Xiang, Zhaofeng He, Qing Li
    PDF Code Project Page

  2. MULTI-STEP REASONING FOR EMBODIED QUESTION ANSWERING VIA TOOL AUGMENTATION
    Mingliang Zhai, Hansheng Liang, Xiaomeng Fan, Zhi Gao, Chuanhao Li, Che Sun, Xu Bin, Yuwei Wu, Yunde Jia
    PDF Project Page

  3. EFFICIENT MULTI-TURN RL FOR GUI AGENTS VIA DECOUPLED TRAINING AND ADAPTIVE DATA CURATION
    Pengxiang Li*, zechenhu*, Zirui Shang*, Jingrong Wu*, Yang Liu, Hui Liu, Zhi Gao, Chenrui Shi, Bofei Zhang, Zihao Zhang, Xiaochuan Shi, Zedong Yu, Yuwei Wu, Xinxiao Wu, Yunde Jia, Liuyu Xiang, Zhaofeng He, Qing Li
    PDF Project Page

  4. Long-Horizon Visual Imitation Learning via Plan and Code Reflection
    Quan Chen*, Chenrui Shi*, Qi Chen, Yuwei Wu, Zhi Gao, Xintong Zhang, Rui Gao, Kun Wu, Yunde Jia
    PDF Code Project Page

  5. Memory-Centric Embodied Question Answer
    Mingliang Zhai, Zhi Gao, Yuwei Wu, Yunde Jia
    PDF Code Project Page

  6. NeurIPS 2025
    Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning
    Pengxiang Li*, Zhi Gao*, Bofei Zhang, Yapeng Mi, Xiaojian Ma, Chenrui Shi, Tao Yuan, Yuwei Wu, Yunde Jia, Song-Chun Zhu, Qing Li
    Advances in Neural Information Processing Systems (NeurIPS), 2025
    PDF Code Project Page

  7. AAAI 2026
    TongUI: Internet-Scale Trajectories from Multimodal Web Tutorials for Generalized GUI Agents
    Bofei Zhang*, Zirui Shang*, Zhi Gao*, Wang Zhang, Rui Xie, Xiaojian Ma, Tao Yuan, Xinxiao Wu, Song-Chun Zhu, Qing Li (*Co-first author)
    AAAI Conference on Artificial Intelligence (AAAI), 2026
    PDF Code Project Page

  8. Building LLM Agents by Incorporating Insights from Computer Systems
    Yapeng Mi, Zhi Gao, Xiaojian Ma, Qing Li
    PDF

  9. ICLR 2025
    Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage
    Zhi Gao*, Bofei Zhang*, Pengxiang Li*, Xiaojian Ma, Yue Fan, Tao Yuan, Yuwei Wu,Yunde Jia, Song-Chun Zhu, Qing Li (*Co-first author)
    International Conference on Learning Representations (ICLR), 2025
    PDF Code Project Page

  10. ECCV 2024
    VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding
    Yue Fan*, Xiaojian Ma*, Rujie Wu, Yuntao Du, Jiaqi Li, Zhi Gao, Qing Li
    European Conference on Computer Vision (ECCV), 2024
    PDF Code Project Page

  11. CVPR 2024
    CLOVA: A Closed-LOop Visual Assistant with Tool Usage and Update
    Zhi Gao, Yuntao Du, Xintong Zhang, Xiaojian Ma, Wenjuan Han, Song-Chun Zhu, Qing Li
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
    PDF Code Project Page

Multimodal Learning

  1. KORE: ENHANCING KNOWLEDGE INJECTION FOR LARGE MULTIMODAL MODELS VIA KNOWLEDGEORIENTED AUGMENTATIONS AND CONSTRAINTS
    Kailin Jiang, Hongbo Jiang, Ning Jiang, Zhi Gao, Jinhe Bi, Yuchen Ren, Bin Li, Yuntao Du, Lei Liu, Qing Li
    PDF Project Page

  2. When Large Multimodal Models Confront Evolving Knowledge: Challenges and Pathways
    Kailin Jiang*, Yuntao Du*, Yukai Ding, Yuchen Ren, Ning Jiang, Zhi Gao, Zilong Zheng, Lei Liu , Bin Li, Qing Li
    PDF

  3. Chain-of-Focus: Adaptive Visual Search and Zooming for Multimodal Reasoning via RL
    Xintong Zhang*, Zhi Gao*, Bofei Zhang, Pengxiang Li, Xiaowen Zhang, Yang Liu, Tao Yuan, Yuwei Wu1, Yunde Jia, Song-Chun Zhu, Qing Li (*Co-first author)
    PDF Code Project Page

  4. ICLR 2025
    MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge
    Yuntao Du*, Kailin Jiang*, Zhi Gao, Chenrui Shi, Zilong Zheng, Siyuan Qi, Qing Li
    International Conference on Learning Representations (ICLR), 2025
    PDF Code Project Page

  5. NeurIPS 2024
    FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models
    Pengxiang Li*, Zhi Gao*, Bofei Zhang*, Tao Yuan, Yuwei Wu, Mehrtash Harandi, Yunde Jia, Song-Chun Zhu, Qing Li (*Co-first author)
    Advances in Neural Information Processing Systems (NeurIPS), D&B Track, 2024
    PDF Code Project Page

Open-Environment Learning

  1. Adaptive Model Ensemble for Continual Learning
    Yuchuan Mao, Zhi Gao, Xiaomeng Fan, Yuwei Wub, Yunde Jia, Chenchen Jing
    PDF

  2. NeurIPS 2025
    Beyond the Seen: Bounded Distribution Estimation for Open-Vocabulary Learning
    Xiaomeng Fan*, Yuchuan Mao*, Zhi Gao, Yuwei Wu, Jin Chen, Yunde Jia
    Advances in Neural Information Processing Systems (NeurIPS), 2025
    PDF Code

  3. VUDG: A Dataset for Video Understanding Domain Generalization
    Ziyi Wang, Zhi Gao, Boxuan Yu, Zirui Dai, Yuxiang Son, Qingyuan Lu, Jin Chen, Xinxiao Wu
    PDF Project Page

  4. T-MM 2025
    Simulate, Refocus and Ensemble: An Attention-Refocusing Scheme for Domain Generalization
    Ziyi Wang, Zhi Gao, Jin Chen, Qingjie Zhao, Xinxiao Wu, Jiebo Luo
    IEEE Transactions on Multimedia (T-MM), 2025
    PDF

  5. CVPR 2023
    Meta-causal Learning for Single Domain Generalization
    Jin Chen*, Zhi Gao*, Xinxiao Wu, Jiebo Luo (*Co-first author)
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023
    PDF Code

Riemannian Geometry

  1. MODALITY ALIGNMENT ACROSS TREES ON HETEROGENEOUS HYPERBOLIC MANIFOLDS
    Wei Wu*, Xiaomeng Fan*, Yuwei Wu, Zhi Gao, Pengxiang Li, Yunde Jia, Mehrtash Harandi
    PDF

  2. T-NNLS 2025
    Riemannian Implicit Differentiation via a Fixed-Point Equation for Riemannian Bi-Level Optimization
    Xiaomeng Fan, Yuwei Wu, Zhi Gao, Zhipeng Lu, Feng Li, Mehrtash Harandi, Yunde Jia
    IEEE Transactions on Neural Networks and Learning Systems (T-NNLS), 2025
    PDF

  3. IJCV 2025
    Curvature Learning for the Generalization of Hyperbolic Neural Networks
    Xiaomeng Fan, Yuwei Wu, Zhi Gao, Mehrtash Harandi, Yunde Jia
    International Journal of Computer Vision(IJCV), 2025
    PDF

  4. A Set-to-Set Distance Measure in Hyperbolic Space
    Pengxiang Li*, Wei Wu*, Zhi Gao, Xiaomeng Fan, Peilin Yu, Yuwei Wu, Zhipeng Lu, Yunde Jia, Mehrtash Harandi
    PDF

  5. Geometry-aware Distance Measure for Diverse Hierarchical Structures in Hyperbolic Spaces
    Pengxiang Li, Yuwei Wu, Zhi Gao, Xiaomeng Fan, Wei Wu, Zhipeng Lu, Yunde Jia, Mehrtash Harandi
    PDF

  6. Hyperbolic Dual Feature Augmentation for Open-Environment
    Peilin Yu, Yuwei Wu, Zhi Gao, Xiaomeng Fan, Shuo Yang, Yunde Jia
    PDF

  7. CVIU 2025
    Large-Scale Riemannian Meta-Optimization via Subspace Adaptation
    Peilin Yu, Yuwei Wu, Zhi Gao, Xiaomeng Fan, Yunde Jia
    Computer Vision and Image Understanding(CVIU), 2025
    PDF Code

  8. 计算机学报 2024
    混合曲率空间中的几何自适应元学习方法
    高志, 武玉伟, 贾云得
    计算机学报, 2024.
    PDF

  9. CVPR 2023
    Exploring Data Geometry for Continual Learning
    Zhi Gao, Chen Xu, Feng Li, Yunde Jia, Mehrtash Harandi, Yuwei Wu
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023
    PDF Code

  10. T-PAMI 2023
    Learning to Optimize on Riemannian Manifolds
    Zhi Gao, Yuwei Wu, Xiaomeng Fan, Mehrtash Harandi, Yunde Jia
    IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2023
    PDF Code

  11. T-PAMI 2023
    Curvature-Adaptive Meta-Learning for Fast Adaptation to Manifold Data
    Zhi Gao, Yuwei Wu, Mehrtash Harandi, Yunde Jia
    IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2023
    PDF Code

  12. NeurIPS 2022
    Hyperbolic Feature Augmentation via Distribution Estimation and Infinite Sampling on Manifolds
    Zhi Gao, Yuwei Wu, Mehrtash Harandi, Yunde Jia
    Advances in Neural Information Processing Systems (NeurIPS), 2022
    PDF Code

  13. AAAI 2022
    Efficient Riemannian Meta-Optimization by Implicit Differentiation
    Xiaomeng Fan, Yuwei Wu, Zhi Gao, Yunde Jia, Mehrtash Harandi
    AAAI Conference on Artificial Intelligence (AAAI), 2022
    PDF Code

  14. ICCV 2021
    Curvature Generation in Hyperbolic Spaces for Few-Shot Learning
    Zhi Gao, Yuwei Wu, Yunde Jia, Mehrtash Harandi
    IEEE InternationalConference on Computer Vision (ICCV), 2021
    PDF Code

  15. AAAI 2021
    Learning a Gradient-free Riemannian Optimizer on Tangent Spaces
    Xiaomeng Fan*, Zhi Gao*, Yuwei Wu, Yunde Jia, Mehrtash Harandi (*Co-first author)
    AAAI Conference on Artificial Intelligence (AAAI), 2021
    PDF Code

  16. CVPR 2021
    A Hyperbolic-to-Hyperbolic Graph Convolutional Network
    Jindou Dai, Yuwei Wu, Zhi Gao, Yunde Jia
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021
    PDF Code

  17. PR 2021
    Infinite-dimensional Feature Aggregation via a Factorized Bilinear Model
    Jindou Dai, Yuwei Wu, Zhi Gao, Yunde Jia
    Pattern Recognition (PR), 2021
    PDF

  18. CVPR 2020
    Learning to Optimize on SPD Manifolds
    Zhi Gao, Yuwei Wu, Yunde Jia, Mehrtash Harandi
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
    PDF Code

  19. AAAI 2020
    Revisiting Bilinear Pooling: A Coding Perspective
    Zhi Gao, Yuwei Wu, Xiaoxun Zhang, Jindou Dai, Yunde Jia, Mehrtash Harandi
    AAAI Conference on Artificial Intelligence (AAAI), 2020
    PDF Code

  20. T-NNLS 2020
    A Robust Distance Measure for Similarity-Based Classification on the SPD Manifold
    Zhi Gao, Yuwei Wu, Mehrtash Harandi, Yunde Jia
    IEEE Transactions on Neural Networks and Learning Systems (T-NNLS), 2020
    PDF Code

  21. PR 2019
    Learning a robust representation via a deep network on symmetric positive definite manifolds
    Zhi Gao, Yuwei Wu, Xingyuan Bu, Tan Yu, Junsong Yuan, Yunde Jia
    Pattern Recognition (PR), 2019
    PDF Code

  22. PR 2019
    Deep convolutional network with locality and sparsity constraints for texture classification
    Xingyuan Bu, Yuwei Wu, Zhi Gao, Yunde Jia
    Pattern Recognition (PR), 2019
    PDF

Others

Visitor Badge


Powered by Jekyll and Minimal Light theme.