avatar

Chenhongyi Yang

杨陈弘毅

Research Scientist
Meta

About Me

I am a research scientist at Reality Labs Research (RL-R) at Meta (Zurich office). I am now working on robotics and world action models. Before moving to robotics, I worked in Meta Superintelligence Labs (MSL) on building efficient video generation models and creating large scale data curation pipeline for image / video generation models. Before that, I worked at the XR-Tech department of Meta Reality Labs on human body modelling, where I drove the design and on-device shipment of the latest generation of human motion estimation model for Meta's VR / AR devices.

I got my PhD from the University of Edinburgh, under the supervison of Dr Elliot J. Crowley. My PhD research was in computer vision, with a focus on developing effective neural networks for 2D and 3D visual perception and designing efficient training algorithms for visual recognition models. I hold an MSc in computer science from Boston University and BEng in computer science from the University of Science and Technology of China.

Selected Publications

  1. EgoPoseFormer v2: Accurate Egocentric Human Motion Estimation for AR/VR
    CVPR 2026
    Zhenyu Li, Sai Kumar Dwivedi, Filip Maric, Carlos Chacon, Nadine Bertsch, Filippo Arcadu, Tomas Hodan, Michael Ramamonjisoa, Peter Wonka, Amy Zhao, Robin Kips, Cem Keskin, Anastasia Tkach, Chenhongyi Yang
    arXiv Highlight

  2. PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition
    BMVC 2024
    Chenhongyi Yang*, Zehui Chen*, Miguel Espinosa*, Linus Ericsson, Zhenyu Wang, Jiaming Liu, Elliot J. Crowley
    arXiv Code

  3. EgoPoseFormer: A Simple Baseline for Stereo Egocentric 3D Human Pose Estimation
    ECCV 2024
    Chenhongyi Yang, Anastasia Tkach, Shreyas Hampali, Linguang Zhang, Elliot J. Crowley, Cem Keskin
    arXiv Code

  4. WidthFormer: Toward Efficient Transformer-based BEV View Transformation
    IROS 2024
    Chenhongyi Yang, Tianwei Lin, Lichao Huang, Elliot J. Crowley
    arXiv Code Oral Presentation

  5. Plug and Play Active Learning for Object Detection
    CVPR 2024
    Chenhongyi Yang, Lichao Huang, Elliot J. Crowley
    arXiv Code

  6. GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation
    ICLR 2023
    Chenhongyi Yang*, Jiarui Xu*, Shalini De Mello, Elliot J. Crowley, Xiaolong Wang
    arXiv Code Spotlight Presentation

  7. Prediction-Guided Distillation for Dense Object Detection
    ECCV 2022
    Chenhongyi Yang, Mateusz Ochal, Amos Storkey, Elliot J. Crowley
    arXiv Code

  8. QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection
    CVPR 2022
    Chenhongyi Yang, Zehao Huang, Naiyan Wang
    arXiv Code Oral Presentation

  9. Disentangle Your Dense Object Detector
    ACM Multimedia 2021
    Zehui Chen*, Chenhongyi Yang*, Qiaofei Li, Feng Zhao, Zheng-Jun Zha, Feng Wu
    arXiv Code Oral Presentation

  10. Learning to Separate: Detecting Heavily-Occluded Objects in Urban Scenes
    ECCV 2020
    Chenhongyi Yang, Vitaly Ablavsky, Kaihong Wang, Qi Feng, Margrit Betke
    arXiv Code


Powered by Jekyll and Minimal Light theme.