avatar

Chenyang (Danny) Ma

PhD Candidate
University of Oxford
chenyang.ma [at] cs.ox.ac.uk


About Me

I am a second-year Ph.D. candidate in Computer Science at the University of Oxford, co-supervised by Prof. Andrew Markham and Prof. Niki Trigoni. My study is generously funded by the EPSRC DTP International Doctoral Scholarship. I had the privilege of collaborating closely with Xavier Puig and Ruta Desai at FAIR, Meta (2024) and spent wonderful times interning at Roku (2024) and Flower Labs (2023).

Prior to my Ph.D., I worked as a research assistant in Cambridge Machine Learning Systems Lab, supervised by Prof. Nicholas Lane. I obtained my B.S.E. degree from University of Michigan, completing multiple projects under the guidances of Prof. Andrew Owens, Prof. Wenzhen Yuan, and Prof. Paul Green.

I am actively looking for a research internship for Summer 2025. Feel free to contact me for any research opportunities!

Research Interests

My main research interest focuses on developing human-centered embodied and AI agents in open-world settings. My Ph.D. work mainly builds on three closely-related questions:

  1. Most agents today use VLMs/VLAs as their core reasoning component. How can we enhance their reasoning and planning capabilities in dynamic 3D environments, and bridge the gap from visual perception and task descriptions to low-level actions?
  2. How can we represent humans within robot simulation platforms, considering factors such as motion feasibility, human-object interactions, and extending to human preferences, traits, and habits?
  3. How can we design systems and frameworks that allow us to study open-ended human-robot collaboration, accommodating human preferences, needs, and spontaneous intentions?

On the side, I also enjoy working with vision applications that utilize various modalities (Vision, Tactile) and AI methods that are less centralized and more collaborative (Federated Learning).

News

Selected Publications (Full list on Google Scholar)

  1. Preprint
    COOPERA: Continual Open-Ended Human-Robot Assistance
    Chenyang Ma, Kai Lu, Ruta Desai*, Xavier Puig*, Andrew Markham*, Niki Trigoni (*=Equal Advising)
    Under Submission, 2024.
    Project Page Paper Code

    NeurIPS
    SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors
    Chenyang Ma, Kai Lu, Ta-Ying Cheng, Niki Trigoni, Andrew Markham
    Neural Information Processing Systems (NeurIPS), 2024.
    Project Page Paper Code

    EuroMLSys
    Gradient-less Federated Gradient Boosting Tree with Learnable Learning Rates
    Chenyang Ma, Xinchi Qiu, Daniel Beutel, Nicholas Lane
    Workshop on Machine Learning and Systems (EuroMLSys), 2023.
    Project Page Paper Code

    NeurIPS
    Touch and Go: Learning from Human-Collected Vision and Touch
    Fengyu Yang*, Chenyang Ma*, Jiacheng Zhang, Jing Zhu, Wenzhen Yuan, Andrew Owens (*=Equal Contribution)
    NeurIPS Datasets and Benchmarks, 2022.
    Project Page Paper Dataset Code

    CVPR
    Sparse and Complete Latent Organization for Geospatial Semantic Segmentation
    Fengyu Yang*, Chenyang Ma* (*=Equal Contribution)
    Computer Vision and Patter Recognition (CVPR), 2022.
    Paper

Industry Experience

  1. Research Consultant
    MERL — Apr 2025 to Present
    Advised by Chiori Hori, Diego Romeres

    Research Collaborator
    FAIR, Meta — June 2024 to Apr 2025
    Advised by Xavier Puig, Ruta Desai

    Applied Scientist Intern
    Roku — July 2024 to Oct 2024
    Advised by Michael Sanders

    Research Scientist Intern
    Flower Labs — Oct 2022 to July 2023
    Advised by Nicholas Lane, Daniel Beutel

Services

Conference Reviewer

Teaching Assistant


Powered by Jekyll and Minimal Light theme.