Xiao Ma (马骁)

I am a research scientist at SEA AI Lab. I pursued my PhD at National University of Singapore, advised by Prof. David Hsu. I also worked closely with Prof. Wee Sun Lee on my projects. I received my B.Sc. in Computer Science from Shanghai Jiao Tong University in 2017, where I was advised by Prof. Fan Wu and Prof. Xiaofeng Gao.

My research focuses on uncertainty modelling, reinforcement learning, graph neural networks, and their applications to robotics.

I'm looking for research interns to work on topics including multi-agent RL / offline RL. Please reach out if you are interested :)

Email  /  CV  /  Google Scholar  /  Semantic Scholar  /  Twitter  /  Github

- [Apr. 2022] HILMO for reinforcement learning under mixed observability has been accepted to WAFR 2022!

- [Feb. 2022] G-DOOM for deformable object manipulation has been accepted to ICRA 2022!

- [Nov. 2021] I've successfully defensed my PhD thesis!

- [Oct. 2021] SABRA for object relationship detection under imbalanced distributions has been accepted to BMVC 2021.

- [Jul. 2021] I'm joining SEA AI Lab as a research scientist working on reinforcement learning.

- [May 2021] PROMPT for ab-initio object manipulation has been accepted by RSS 2021.

- [Oct. 2020] CVRL for model-based RL under complex observations has been accepted by CoRL 2020.

- [Sept. 2020] BALMS for long-tailed visual recognition has been accepted by NeurIPS 2020.

- [Jul. 2020] STAR for pedestrian trajectory prediction has been accepted by ECCV 2020.

- [Dec. 2019] DPFRL for reinforcement learning under complex and partial observations has been accepted by ICLR 2020.

- [Nov. 2019] PF-RNNs for sequence modeling under uncertainty has been accepted to AAAI 2020.

- [Jun. 2019] DAN was nominated for the best system paper and best student paper of RSS 2019!

We present G-DOOM for deformable object manipulation. G-DOOM abstract an deformable object as a keypoint-based graph and models the spatio-temporal keypoint interactions with Recurrent Graph Dynamics. G-DOOM achieves SOTA performance on a set of deformable object manipulation tasks.

This paper introduces PROMPT, a framework for particle-based object manipulation. PROMPT performs high-quality online point cloud reconstruction from multi-view images captured by an eye-in-hand camera. It achieves high performance in object grasping, pushing, and placing.

We introduce CVRL, contrastive model-based reinforcement learning for complex observations. Different from standard generative models, CVRL learns a contrastive latent world model and significantly improves the robustness against complex observations.

Our key observation is that softmax is biased under the long-tailed distribution. BALMS provides a mathematically unbiased gradient estimate for long-tailed distributions and applies meta-learning to further improve the data sampling process.

We introduce STAR, the first transformer-based pedestrian trajectory predictor. STAR generalizes the Transformers into spatio-temporal graphs and significantly improves the trajectory prediction accuracy (2x).

We introduce DPFRL for reinforcement learning for complex partial observations. DPFRL encodes a discriminative particle algorithm as a differentiable computational graph in neural networks which improves the belief tracking.

We introduce PF-RNNs for general sequence prediction under uncertainty. PF-RNNs encodes a differentiable particle filter algorithm with standard RNNs and improves the general sequence prediction performance.

A DAN is composed of neural network modules, each encoding a differentiable algorithm and an associated model; and it is trained end-to-end from data. The algorithms and models act as structural priors to reduce the data requirements for learning; end-to-end learning allows the modules to adapt to one another and compensate for imperfect models and algorithms.

Stolen from Jon Barron