Xiao Ma

I am a staff research scientist at ByteDance Seed. 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.

CV Google Scholar Twitter Github
profile photo

photo credits to Rachel Li Rui ♥

News

[Aug. 2025] I'll be 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)

GR3
GR-3 Technical Report
Technical Report, 2025
project page pdf
RoboVLMs
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
Technical Report, 2024
project page pdf code checkpoints datasets
BiGym
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
project page pdf code
Redundancy-aware Action Spaces
Redundancy-aware Action Spaces for Robot Learning
Pietro Mazzaglia*, Nicholas Backshall*, Xiao Ma, Stephen James (*equal contributions)
IEEE Robotics and Automation Letters (RA-L), 2024
project page pdf code
HDP
Hierarchical Diffusion Policy for Multi-Task Robotic Manipulation
Xiao Ma, Sumit Patidar, Iain Haughton, Stephen James
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
project page pdf code
InsActor
InsActor: Instruction-driven Physics-based Characters
Jiawei Ren*, Mingyuan Zhang, Cunjun Yu*, Xiao Ma, Liang Pan, Ziwei Liu
Conference on Neural Information Processing Systems (NeurIPS), 2023
project page pdf code
Efficient Diffusion Policies
Efficient Diffusion Policies for Offline Reinforcement Learning
Bingyi Kang*, Xiao Ma*, Chao Du, Tianyu Pang, Shuicheng Yan (*equal contributions)
Conference on Neural Information Processing Systems (NeurIPS), 2023
pdf code
Mutual Information Regularized Offline Reinforcement Learning
Mutual Information Regularized Offline Reinforcement Learning
Xiao Ma*, Bingyi Kang*, Zhongwen Xu, Min Lin, Zhongwen Xu, Shuicheng Yan (*equal contributions)
Conference on Neural Information Processing Systems (NeurIPS), 2023
pdf code
Imitation Learning via Differentiable Physics
Imitation Learning via Differentiable Physics
Siwei Chen, Xiao Ma, Zhongwen Xu
Computer Vision and Pattern Recognition (CVPR), 2023
pdf code bibtex
DaxBench
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)
pdf bibtex
DiffMimic
DiffMimic: Efficient Motion Mimicking with Differentiable Physics
Jiawei Ren*, Cunjun Yu*, Siwei Chen, Xiao Ma, Liang Pan, Ziwei Liu, (*equal contributions)
International Conference on Learning Representations (ICLR), 2023
project page pdf code live demo bibtex
gdoom
Learning Latent Graph Dynamics for Deformable Object Manipulation
Xiao Ma, David Hsu, Wee Sun Lee
International Conference on Robotics and Automation (ICRA), 2022
project page pdf bibtex
gdoom
Ab Initio Particle-based Object Manipulation
Siwei Chen, Xiao Ma, Yunfan Lu, David Hsu
Robotics: Science and Systems (RSS), 2021
project page pdf code bibtex
star
Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction
Cunjun Yu*, Xiao Ma*, Jiawei Ren, Haiyu Zhao, Shuai Yi (* equal contributions)
European Conference on Computer Vision (ECCV), 2020
project page pdf code talk bibtex
dan
Differentiable Algorithm Networks for Composable Robot Learning
Peter Karkus, Xiao Ma, David Hsu, Leslie Kaelbling, Wee Sun Lee Tomas Lozano-Perez
Robotics: Science and Systems (RSS), 2019 (best system paper finalist & best student paper finalist)
pdf bibtex