Computer Science · University of Rochester

Weikai Lin 林惟凱

Hardware–Software Co-design for AR/VR, AI, and Imaging Systems

Weikai Lin holding a circuit board

I am a Computer Science Ph.D. student at University of Rochester, advised by Yuhao Zhu. Previously, I earned B.E. in Electronic Engineering from Tsinghua University and M.Sc. in Intelligent Science from Peking University.

Research. I am interested in end-to-end hardware-software co-design. My publications span AR/VR, AI, and imaging systems. More details are available on my research page.

I am also an AI maximalist interested in Autoresearch/AI4S, aiming to accelerate scientific discovery by orders of magnitude and unlock research that was previously impossible.

Latest news

All news
Aug 17, 2026 ControlGS is accepted to SIGGRAPH Asia 2026.
Jul 13, 2026 LowPowAR is accepted to TVCG 2026 (ISMAR Journal Track).
Jul 10, 2026 UniMod is accepted to ACM MM 2026.
Jun 18, 2026 ControlHair is accepted to ECCV 2026.
May 18, 2026 I have joined Meta as a Research Scientist Intern.

Publications

Search publications

* Indicates equal contributions, some papers are highlighted. See Google Scholar for full list.

2026

  1. SIGGRAPH Asia
    controlgs.png
    ControlGS: Conditioning Neural Gaussians for Downstream-Processing–Aware XR Rendering
    Weikai Lin, Junjie Zhao, Carl Marshall, and 2 more authors
    In SIGGRAPH Asia Conference Papers, 2026
  2. TVCG
    lowpowar.png
    LowPowAR: Power-Constrained Tone Mapping for Augmented Reality
    Weikai Lin, Sheng Zhao, Ian Ross, Carl Marshall, Sushant Kondguli, and Yuhao Zhu
    In IEEE Transactions on Visualization and Computer Graphics (ISMAR Journal Track), 2026
    PDF Webpage Code
  3. ECCV
    controlhair.png
    ControlHair: Synergizing Physics Simulator and Video Diffusion for Controllable Dynamic Hair Rendering
    Weikai Lin, Haoxiang Li, and Yuhao Zhu
    In 19th European Conference on Computer Vision, 2026
    PDF Webpage Code
  4. ArXiv
    metasapiens_v2.png
  5. ACM MM
    unimod.png
    UniMod: Enhancing Multi-Modal Medical Diagnosis through Cross-Modality and Within-Modality Alignment
    Zijian Gu, Weikai Lin, Shuang Zhou, Zihan Chen, and Song Wang
    In 34th ACM International Conference on Multimedia, 2026
  6. DAC
    dac26.webp
    HoloCode: Hybrid Optical-Electronic Edge Encoding for Privacy-Preserving Cloud Training
    Ruofan Xing, Arman Akbari, Weikai Lin, and 6 more authors
    In 63rd ACM/IEEE Design Automation Conference, 2026
    Webpage
  7. DAC
    dac_invited_2026.webp
    Invited Paper: A Quantitative Approach to Exploring Novel Image Sensor Architecture Towards Autonomous Edge Machine Vision
    Han Yan*, Yifei Zou*, Weikai Lin, and 2 more authors
    In 63rd ACM/IEEE Design Automation Conference, 2026
    Webpage
  8. CVPR
    cvpr25.png
    SeeLe: A Unified Acceleration Framework for Real-Time Gaussian Splatting on Mobile Devices
    🌟 CVPR Highlight
    He Zhu*, Xiaotong Huang*, Zihan Liu, and 6 more authors
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026
    🌟 CVPR Highlight PDF

2025

  1. SIGGRAPH Asia
    powergs.png
    PowerGS: Display–Rendering Power Co-Optimization for Neural Rendering in Power-Constrained XR Systems
    Weikai Lin, Sushant Kondguli, Carll Marshall, and 1 more author
    In SIGGRAPH Asia Conference Papers, 2025
    arXiv Webpage Code XR Viewer
  2. DAC
    snappix.png
    SnapPix: Efficient-Coding–Inspired In-Sensor Compression for Edge Vision
    Weikai Lin*, Tianrui Ma*, Adith Boloor, and 4 more authors
    In 62nd ACM/IEEE Design Automation Conference, 2025
    arXiv Code
  3. ASPLOS
    asplos25_vr.png
    MetaSapiens: Real-Time Neural Rendering with Efficiency-Aware Pruning and Accelerated Foveated Rendering
    🏆 Best Paper Award
    Weikai Lin*, Yu Feng*, and Yuhao Zhu
    In 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, 2025
    🏆 Best Paper Award PDF Webpage Code
    ASPLOS 2025 Best Paper Award certificate for MetaSapiens
  4. ASPLOS
    asplos25_pc.png
    StreamGrid: Streaming Point Cloud Analytics via Compulsory Splitting and Deterministic Termination
    Yu Feng*, Zheng Liu*, Weikai Lin*, and 6 more authors
    In 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, 2025
    arXiv Webpage
  5. ISCA
    isca25.png
    Lumina: Real-Time Mobile Neural Rendering by Exploiting Computational Redundancy
    Yu Feng, Weikai Lin, Yuge Cheng, and 6 more authors
    In 52nd IEEE/ACM International Symposium on Computer Architecture, 2025
    arXiv Webpage
  6. WACV
    wacv25.png
    Private-Eye: In-Sensor Privacy Preservation Through Optical Feature Separation
    Adith Boloor, Weikai Lin, Tianrui Ma, and 3 more authors
    In IEEE/CVF Winter Conference on Applications of Computer Vision, 2025
    PDF
  7. HotMobile
    hotmobile25.png
    Advancing Immersive Content Delivery with Dynamic 3D Gaussian Splatting
    Nan Wu*, Weikai Lin*, Ruizhi Cheng*, and 4 more authors
    In 26th International Workshop on Mobile Computing Systems and Applications, 2025
    Webpage

2024

  1. TACO
    taco24.png
    Potamoi: Accelerating Neural Rendering via a Unified Streaming Architecture
    Yu Feng*, Weikai Lin*, Zihao Liu, and 6 more authors
    In ACM Transactions on Architecture and Code Optimization, 2024
    PDF
  2. IROS
    iros24.png
    OW3Det: Toward Open-World 3D Object Detection for Autonomous Driving
    Wenfei Hu, Weikai Lin, Hongyu Fang, and 2 more authors
    In IEEE/RSJ International Conference on Intelligent Robots and Systems, 2024
    PDF
  3. ArXiv
    rtgs.png
    RTGS: Enabling Real-Time Gaussian Splatting on Mobile Devices Using Efficiency-Guided Pruning and Foveated Rendering
    Weikai Lin, Yu Feng, and Yuhao Zhu
    (Preprint and Shortened Version of MetaSapiens), arXiv preprint arXiv:2407.00435, 2024
    arXiv Code
  4. Project
    hvs_proj.png
    Exploiting Human Color Discrimination for Memory and Energy-Efficient Image Encoding in Virtual Reality: An FPGA Demo
    Open-source AR/VR hardware project, 2024
    Code

2023

  1. ROMAN
    Learning Clear Class Separation for Open-set 3D Detector in Autonomous Vehicle via Selective Forgetting
    Wenfei Hu, Weikai Lin, Hongyu Fang, and 2 more authors
    In 32nd IEEE International Conference on Robot and Human Interactive Communication, 2023
  2. PKU ASN
    A Review of Robot Learning
    Weiming Qu, Tianlin Liu, Weikai Lin, and 1 more author
    In Acta Scientiarum Naturalium Universitatis Pekinensis, 2023

2021

  1. ICDL
    Approaching Sound Object with Sensorimotor Coordination when Sensors Partially Damaged
    Shuai Fang, Yaoyao Wei, Weikai Lin, and 3 more authors
    In IEEE International Conference on Development and Learning, 2021
  2. ICDL
    Acquiring robot navigation skill with knowledge learned from demonstration
    Yaoyao Wei, Shuai Fang, Weikai Lin, and 2 more authors
    In IEEE International Conference on Development and Learning, 2021