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:
- 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?
- 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?
- 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
- [Apr. 2025] Started my research consultant role at Mitsubishi Electric Research Laboratories! (Mentors: Chiori Hori, Diego Romeres)
- [Jan. 2025] Defended my Transfer of Status viva (Examiners: Prof. Alessandro Abate, Prof. Ioannis Havoutis).
- [Sep. 2024] Our paper SpatialPIN got accepted into NeurIPS 2024!
- [Jul. 2024] Started my internship at Roku Advanced Development! (Mentor: Michael Sanders)
- [Jun. 2024] Started my research collaboration with Meta FAIR! (Mentors: Xavier Puig, Ruta Desai)
- [Oct. 2023] Started my Ph.D. journey at the University of Oxford.
Selected Publications (Full list on Google Scholar)
-
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.
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.
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.
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.
CVPR
Sparse and Complete Latent Organization for Geospatial Semantic Segmentation
Fengyu Yang*, Chenyang Ma* (*=Equal Contribution)
Computer Vision and Patter Recognition (CVPR), 2022.
Industry Experience
-
Research Consultant
MERL — Apr 2025 to Present
Advised by Chiori Hori, Diego Romeres
Research Collaborator
Advised by Xavier Puig, Ruta Desai
Applied Scientist Intern
Roku — July 2024 to Oct 2024
Advised by Michael Sanders
Research Scientist Intern
Advised by Nicholas Lane, Daniel Beutel
Services
Conference Reviewer
Teaching Assistant
Powered by Jekyll and Minimal Light theme.