Fei Ni   倪飞

Research Associate

I am a PostDoc at Imperial College London, working with Jiankang Deng and Stefanos Zafeiriou. Previously, I was a Ph.D. student at the TJURLLab in Tianjin University, supervised by Jianye Hao. My research interests include Meta Reinforcement Learning, Diffusion Models, Multimodal Robotics.

Email: f.ni@imperial.ac.uk

Fei-Ni

News

  • 2025.06, one paper is accepted to ICCV'25.
  • 2025.05, one paper is accepted to ICML'25.
  • 2025.05, one paper is accepted to ACL'25.
  • 2025.01, one paper is accepted to WWW'25.
  • 2024.11, one paper is accepted to AAAI'25.
  • 2024.09, three papers is accepted to NeurIPS'24.
  • 2024.05, one paper is accepted to ICML'24.
  • 2024.02, one paper is accepted to CVPR'24.
  • 2024.01, one paper is accepted to ICLR'24.
  • 2023.04, two papers are accepted to ICML'23.
  • 2023.01, one paper is accepted to ICLR'23.
  • 2022.11, one paper is accepted to AAAI'23.
  • 2022.09, one paper is accepted to NeurIPS'22.
  • 2021.05, one paper is accepted to KDD'21.

    • Publications (Google Scholar)

    Conference Papers

    RoboAnnotatorX: A Comprehensive and Universal Annotation Framework for Accurate Understanding of Long-horizon Robot Demonstration.

    Longxin Kou*, Fei Ni*, Jianye HAO, Peilong Han, Jinyi Liu, Haiqin Cui, Rui Liu, Yan Zheng.

    The Twentieth IEEE/CVF International Conference on Computer Vision (ICCV), 2025. (CCF-A)

    Peria: Perceive, reason, imagine, act via holistic language and vision planning for manipulation.

    Fei Ni, Jianye Hao, Shiguang Wu, Longxin Kou, Yifu Yuan, Zibin Dong, Jinyi Liu, MingZhi Li, Yuzheng Zhuang, Yan Zheng.

    The Thirty-Eighth Annual Conference on Neural Information Processing Systems ( NeurIPS ), 2024. (CCF-A)

    KISA: A Unified Keyframe Identifier and Skill Annotator for Long-Horizon Robotics Demonstrations.

    Longxin Kou*, Fei Ni*, Yan Zheng, Jinyi Liu, Yifu Yuan, Zibin Dong, Jianye Hao.

    The Forty-first International Conference on Machine Learning ( ICML ), 2024. (CCF-A)

    Generate Subgoal Images before Act: Unlocking the Chain-of-Thought Reasoning in Diffusion Model for Robot Manipulation with Multimodal Prompts.

    Fei Ni, Jianye Hao, Shiguang Wu, Longxin Kou, Jiashun Liu, Yan Zheng, Bin Wang, Yuzheng Zhuang.

    The IEEE/CVF Conference on Computer Vision and Pattern Recognition ( CVPR ), 2024. (CCF-A)

    AlignDiff: Aligning Diverse Human Preferences Via Behavior-customisable Diffusion Model.

    Zibin Dong , Yifu Yuan, Jianye Hao, Fei Ni, Yao Mu, Yan Zheng, Yujing Hu, Tangjie Lv, Changjie Fan, Zhipeng Hu.

    The 12th International Conference on Learning Representations ( ICLR ), 2024.

    AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners. [arXiv] [webpage]

    Zhixuan Liang, Yao Mu, Mingyu Ding, Fei Ni, Masayoshi Tomizuka, Ping Luo.

    The Fortieth International Conference on Machine Learning ( ICML ), Oral, 2023. (CCF-A)

    MetaDiffuser: Diffusion Model as Conditional Planner for Offline Meta-RL. [webpage]

    Fei Ni, Jianye Hao, Yao Mu, Yifu Yuan, Yan Zheng, Bin Wang, Zhixuan Liang.

    The Fortieth International Conference on Machine Learning ( ICML ), 2023. (CCF-A)

    EUCLID: Towards Efficient Unsupervised Reinforcement Learning with Multi-choice Dynamics Model. [arXiv] [webpage]

    Yifu Yuan, Jianye Hao, Fei Ni, Yao Mu, Yan Zheng, Yujing Hu, Jinyi Liu, Yingfeng Chen, Changjie Fan.

    The 11th International Conference on Learning Representations ( ICLR ), 2023.

    SplitNet: A Reinforcement Learning based Sequence Splitting Method for the MinMax Multiple Travelling Salesman Problem. [talk]

    Hebin Liang, Yi Ma, Zilin Cao, Tianyang Liu, Fei Ni, Zhigang Li, Jianye Hao.

    Thirty-Sixth AAAI Conference on Artificial Intelligence ( AAAI ), 2022. (CCF-A)

    DOMINO: Decomposed Mutual Information Optimization for Generalized Context in Meta-Reinforcement Learning. [arXiv] [webpage]

    Yao Mu, Yuzheng Zhuang, Fei Ni, Bin Wang, Jianyu Chen, Jianye Hao, Ping Luo.

    Advances in Neural Information Processing Systems( NeurIPS ), 2022, 35: 27563-27575 . (CCF-A)

    A Multi-Graph Attributed Reinforcement Learning based Optimization Algorithm for Large-scale Hybrid Flow Shop Scheduling Problem. [arXiv]

    Fei Ni, Jianye Hao, Jiawen Lu, Xialiang Tong, Mingxuan Yuan, Jiahui Duan, Yi Ma, Kun He

    Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining ( KDD ), 2021: 3441-3451. (CCF-A)

    Journal Papers

    Adaptive simulated annealing with greedy search for the circle bin packing problem. [Paper]

    Kun He, Kevin Tole, Fei Ni, Yong Yuan, Linyun Liao.

    Computers & Operations Research ( COR ), in press, 2021. (SCI Q1, IF=5.159)
    Adaptive simulated annealing with greedy search for the circle bin packing problem. [arXiv]

    Yong Yuan, Kevin Tole, Fei Ni, Kun He, Zhengda Xiong, Jinfa Liu.

    Computers & Operations Research ( COR ), in press, 2022. (SCI Q1, IF=5.159)

    Awards

    Industrial Experience

    Academic Experience:Reviewer

    Reviewers: ICML, NeurIPS, ICLR, CVPR, ICCV, AAAI, WACV, AMAAS, ACL, TNNLS, T-CYB.

    Invited Talks