Yifei Yu

prof_pic.jpg

I am a final-year PhD student in the Department of Electrical and Computer Engineering, The University of Hong Kong, supervised by Prof. Zhongrui Wang and Prof. Xiaojuan Qi.

Prior to joining HKU, I received my B.Eng. degree from School of Information Science and Technology, Fudan University.

My long-term goal is to build brain-inspired physical AI. My work focuses on both the development of novel machine learning algorithms and the design of unconventional computational hardware, with applications in perception, reasoning, and action.

My current research interests include:

  • World Model, Embodied AI, 3D Vision, Spatial Intelligence
  • Compute-In-Memory, Software-Hardware Co-design
  • Neuromorphic Computing, Brain-Inspired AI

I’m open to academic collaborations. If you are interested, feel free to reach out!

news

Jun 10, 2026 Our paper on neural field reconstruction with resistive memory published in Nature
Sep 01, 2025 EAG3R accepted to NeurIPS 2025 (Spotlight, top 3%)
Jan 01, 2025 Paper on “Random memristor-based dynamic graph CNN” highlighted by Nature Nobel Prize in Physics 2024 Collection! :sparkles:

selected publications

  1. Efficient and accurate neural-field reconstruction using resistive memory
    Yifei Yu, Xinyuan Zhang, Shaocong Wang, and 23 more authors
    Nature, 2026
    DOI
  2. VideoSSM: Autoregressive Long Video Generation with Hybrid State-Space Memory
    Yifei Yu, Xiaoshan Wu, Xinting Hu, and 8 more authors
    In , 2025

    In submission

    arXiv
  3. EAG3R: Event-Augmented 3D Geometry Estimation for Dynamic and Extreme-Lighting Scenes
    Xiaoshan Wu*, Yifei Yu*, Xiaoyang Lyu, and 5 more authors
    In Advances in Neural Information Processing Systems (NeurIPS), 2025

    Spotlight (top 3%)

    arXiv
  4. Random memristor-based dynamic graph CNN for efficient point cloud learning at the edge
    Yifei Yu, Shaocong Wang, Meng Xu, and 13 more authors
    npj Unconventional Computing, 2024

    Featured in Nature Nobel Prize in Physics 2024 Collection

    DOI

talks

Jun 2026 I gave a talk at College of Future Information Technology, Fudan University on Efficient Neural Field Reconstruction with Resistive Memory.
Feb 2026 I gave a talk at School of Electronic and Computer Engineering, Peking University on Brain-Inspired AI with Software-Hardware Co-design.
Dec 2025 I gave a talk at ACCESS (AI Chip Center for Emerging Smart Systems) on Event Camera-based 3D Geometry Estimation.
Dec 2025 I gave a talk at ByteDance PICO on Efficient Neural Rendering.
Nov 2025 I gave a talk at Department of Electrical and Computer Engineering, The University of Hong Kong on Event Camera-based 3D Geometry Estimation.