Shuang Ma
I am a senior researcher in the Autonomous Systems Research team at Microsoft. I work in computer vision, machine learning and robotics. Most recently, my research is focused on building foundation models for perception and control. I am particularly interested in unifying perception and control from unlabeled ego-view videos and spatio-temporal multimodal data.
I obtained my Ph.D. degree in Computer Science from SUNY Buffalo, where I was a member of Ubiquitous Multimedia Lab (UBMM). I was lucky to have my advisor Prof. Chang Wen Chen and my mentors Daniel Mcduff, Yale Song, Mary Czerwinski, Jianlong Fu and Tao Mei .
Research Interests
-
Multimodal Learning
-
Computer Vision
-
Robotics and Reinforcement Learning
News
-
Our paper 'SMART: Self-supervised Multi-task pretrAining with contRol Transformers' is accepted by ICLR 2023 as notable top 25% (Spotlight).
-
Our paper 'LaTTe: Language Trajectory TransformEr' is accepted by ICRA 2023.
-
Our team EgoMotion-COMPASS got the 2nd place on two tasks of Ego4D challenge (ECCV 2022).
-
Our paper 'Compass: Contrastive multimodal pretraining for autonomous systems' is accepted by IROS 2022.
-
Our paper 'Reshaping robot trajectories using natural language commands: A study of multi-modal data alignment using transformers' is accepted by IROS 2022
-
Our paper 'CausalCity: Complex Simulations with Agency for Causal Discovery and Reasoning' is accepted by CLeaR 2022.
Interns
-
Jianchen Lei, Zhejiang University 2023
-
Yao Wei, Zhejiang University 2023
-
Ruijie Zheng, University of Maryland 2023
-
Yanchao Sun, University of Maryland 2022
-
Arthur Fender Coelho Bucker, Technical University of Munich (TUM) 2022
-
Weijian Xu, UC San Diego 2021
-
Cherie Ho, Carnegie Mellon University 2021
-
Zhaoyang Zeng, Sun Yat-sen University 2020
-
Mingzhi Yu, University of Pittsburgh 2020