| CARVIEW |
Select Language
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Thu, 18 Dec 2025 23:51:05 GMT
access-control-allow-origin: *
etag: W/"69449369-7058"
expires: Mon, 29 Dec 2025 00:01:40 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: C3FE:2D8B9D:812C8E:9118A0:6951C28C
accept-ranges: bytes
age: 0
date: Sun, 28 Dec 2025 23:51:40 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210023-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1766965900.366698,VS0,VE233
vary: Accept-Encoding
x-fastly-request-id: ed7fab4f0c60a27278eebbd105d5ab279ec9a74f
content-length: 5974
Xiao Ma's Homepage
Xiao Ma
I am a staff research scientist at ByteDance Seed, leading the robotic foundation model team. Prior to that, I pursued my PhD at National University of Singapore, advised by Prof. David Hsu. I have worked as research scientist at Dyson Robot Learning Lab, led by Dr. Stephen James and at Sea AI Lab, hosted by Prof. Shuicheng Yan and Dr. Min Lin. My research spans across reinforcement learning, robotics, and multi-modal models.
We're seeking research scientist (interns) in robotics. Please drop me an email if you're interested.
photo credits to Rachel Li Rui ♥
News
[Dec. 2025] I gave talks at NUS and THU about robot foundation models.
[Dec. 2025] We have released Seed
GR-RL, our VLA-RL model that for the first time learns to lace up your shoes.
[Oct. 2025] RoboVLMs has been accepted to Nature Machine Intelligence (NMI).
[Sept. 2025] We have released ByteWrist, our wrist design for dexterous manipulation in compact spaces used in GR-3.
[Sept. 2025] 4 papers accepted to NeurIPS 2025.
Show more
[Sept. 2025] I'm serving as an area chair of ICLR 2026.
[Aug. 2025] 1 paper accepted to EMNLP 2025.
[July 2025] We have released Seed
GR-3, our latest Vision-Language-Action model for generalizable, dexterous, and robust robotic
manipulation.
[Jan. 2025] 1 paper accepted to ICRA 2025.
[Sept. 2024] 1 paper accepted to CoRL 2024.
[Jun. 2024] 1 paper accepted to RA-L 2024.
[Feb. 2024] 1 paper accepted to CVPR 2024.
[Sept. 2023] 3 papers accepted to NeurIPS 2023.
[Feb. 2023] 1 paper accepted to CVPR 2023.
[Jan. 2023] 3 papers accepted to ICLR 2023 (1 oral 2 posters)!
Selected Publications (Full publication list)
GR-RL: Going Dexterous and Precise for Long-Horizon Robotic Manipulation
Technical Report, 2025
Seed GR Team
ByteWrist: A Parallel Robotic Wrist Enabling Flexible and Anthropomorphic Motion for Confined Spaces
Technical Report, 2025
Jiawen Tian,
Liqun Huang,
Zhongren Cui,
Jingchao Qiao,
Jiafeng Xu,
Xiao Ma,
Zeyu Ren
Towards Generalist Robot Policies: What Matters in Building Vision-Language-Action
Models
Xinghang Li,
Peiyan Li,
Minghuan Liu,
Dong Wang,
Jirong Liu,
Bingyi Kang,
Xiao Ma,
Tao Kong,
Hanbo Zhang,
Huaping Liu
Nature Machine Intelligence, 2025
BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmark
Nikita Cherniadev*,
Nicholas Backshall*,
Xiao Ma*,
Yunfan Lu,
Younggyo Seo,
Stephen James (*equal contributions)
Conference on Robot Learning (CoRL), 2024
Redundancy-aware Action Spaces for Robot Learning
IEEE Robotics and Automation Letters (RA-L), 2024
Hierarchical Diffusion Policy for Multi-Task Robotic Manipulation
Proceedings of the IEEE Conference on Computer Vision and Pattern
Recognition (CVPR), 2024
InsActor: Instruction-driven Physics-based Characters
Conference on Neural Information Processing Systems (NeurIPS), 2023
Efficient Diffusion Policies for Offline Reinforcement Learning
Conference on Neural Information Processing Systems (NeurIPS), 2023
Mutual Information Regularized Offline Reinforcement Learning
Conference on Neural Information Processing Systems (NeurIPS), 2023
Imitation Learning via Differentiable Physics
Siwei Chen,
Xiao Ma,
Zhongwen Xu
Computer Vision and Pattern Recognition (CVPR), 2023
DaxBench: Benchmarking Deformable Object Manipulation with Differentiable Physics
Siwei Chen*,
Cunjun Yu*,
Yiqing Xu*,
Linfeng Li,
Xiao Ma,
Zhongwen Xu,
David Hsu
(*equal contributions)
International Conference on Learning Representations (ICLR), 2023
(oral)
DiffMimic: Efficient Motion Mimicking with Differentiable Physics
International Conference on Learning Representations (ICLR), 2023
Learning Latent Graph Dynamics for Deformable Object Manipulation
Xiao Ma,
David Hsu,
Wee Sun Lee
International Conference on Robotics and Automation (ICRA), 2022
Ab Initio Particle-based Object Manipulation
Robotics: Science and Systems (RSS), 2021
Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction
European Conference on Computer Vision (ECCV), 2020
Differentiable Algorithm Networks for Composable Robot Learning
Robotics: Science and Systems (RSS), 2019 (best system paper finalist & best student paper finalist)