Zhou Xian
Hi there! I am Zhou Xian, a final-year PhD student in the Robotics Institute at Carnegie Mellon University, advised by Katerina Fragkiadaki. I am broadly interested in robotics, computer vision and world model learning. Prior to CMU, I completed my Bachelor's degree at Nanyang Technological University in Singapore, working with Pham Quang Cuong and I-Ming Chen. I have also spent wonderful summers as a research intern at Meta AI with Akshara Rai, and at MIT-IBM AI Lab with Chuang Gan.
My current research focuses on building unified neural policies and data engine for robotics research and beyond.
I am also an independent landscape photographer, with a special interest in aerial and celestial photography. I was affiliated with the Visual China Group (视觉中国) and was one of the top 10 contributors on Unsplash.com. My images have received tens of millions of views and near a million downloads across platforms like Unsplash, Notion, Trello, Medium, etc. Here are some of my personal favorite photos of all time.
I get emotional watching the Milky Way dance, every single time.
[Contact] If you are interested in chatting about robots, AI, research, photography, dreams, stand-up comedy, Honor of Kings, wine tasting, kittens🐱, the best superpower, the illusion of free will and consciousness, or anything else that makes absolutely no sense apart from being fun or romantic :P, feel free to shoot me an email at zhouxian@cmu.edu / zhouxian.sq@gmail.com.
[2024-9] [New] Architect is accepted to NeurIPS 2024.
[2024-9] [New] UBSoft is accepted to CoRL 2024.
[2024-5] [New] RoboGen and RL-VLM-F are accepted to ICML 2024.
[2024-1] [New] Gen2Sim is accepted to ICRA 2024.
[2024-1] [New] ThinShellLab and DiffTactile are accepted to ICLR 2024.
[2023-11] Introducing RoboGen, a generative robotic agent for automated and diverse skill acquisition.
[2023-9] We are organizing a workshop on the topic of "Towards Generalist Robots" at CoRL 2023.
[2023-8] We released a white paper envisioning a promising path towards Generalist Robots!
[2023-8] Act3D and ChainedDiffuser are accepted to CoRL 2023.
[2023-6] RoboNinja and EBMPlanner are accepted to RSS 2023.
Recent
Publications
(* indicates equal contribution)
RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation
Yufei Wang*, Zhou Xian*, Feng Chen*, Tsun-Hsuan Wang, Yian Wang, Katerina Fragkiadaki, Zackory Erickson, David Held, Chuang Gan
ICML 2024
[Project Page] | [Paper] | [Code]
RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback
Yufei Wang, Zhanyi Sun, Jesse Zhang, Zhou Xian, Erdem Bıyık, David Held, Zackory Erickson
ICML 2024
[Project Page] | [Paper] | [Code]
Gen2Sim: Scaling up Robot Learning in Simulation with Generative Models
Pushkal Katara*, Zhou Xian*, Katerina Fragkiadaki
ICRA 2024
[Project Page] | [Paper] | [Code]
Thin-Shell Object Manipulations With Differentiable Physics Simulations
Yian Wang*, Juntian Zheng*, Zhehuan Chen, Zhou Xian, Gu Zhang, Chao Liu, Chuang Gan
ICLR 2024 (Spotlight)
[Project Page] | [Paper] | [Code]
DiffTactile: A Physics-based Differentiable Tactile Simulator for Contact-rich Robotic Manipulation
Zilin Si*, Gu Zhang*, Qingwei Ben*, Branden Romero, Zhou Xian, Chao Liu, Chuang Gan
ICLR 2024
[Project Page] | [Paper] | [Code]
ChainedDiffuser: A Unified Neural Architecture for Multimodal Multi-task Robotic Manipulation
Zhou Xian*, Nikolaos Gkanatsios*, Theophile Gervet*, Katerina Fragkiadaki
CoRL 2023
[Project Page] | [Paper] | [Code]
Act3D: Infinite Resolution Action Detection Transformer for Robotic Manipulation
Theophile Gervet*, Zhou Xian*, Nikolaos Gkanatsios, Katerina Fragkiadaki
CoRL 2023
[Project Page] | [Paper] | [Code]
Energy-based Models are Zero-Shot Planners for Compositional Scene Rearrangement
Nikolaos Gkanatsios*, Ayush Jain*, Zhou Xian, Yunchu Zhang, Christopher Atkeson, Katerina Fragkiadaki
RSS 2023
[Project Page] | [Paper] | [Code]
RoboNinja: Learning an Adaptive Cutting Policy for Multi-Material Objects
Zhenjia Xu, Zhou Xian, Xingyu Lin, Cheng Chi, Zhiao Huang, Chuang Gan, Shuran Song
RSS 2023
[Project Page] | [Paper] | [Code]
FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulation
Zhou Xian, Bo Zhu, Zhenjia Xu, Hsiao-Yu Tung, Antonio Torralba, Katerina Fragkiadaki, Chuang Gan
ICLR 2023 (Spotlight)
[Project Page] | [Paper] | [Code]
SoftZoo: A Soft Robot Co-design Benchmark For Locomotion In Diverse Environments
Tsun-Hsuan Wang, Pingchuan Ma, Andrew Spielberg, Zhou Xian, Hao Zhang, Joshua Tenenbaum, Daniela Rus, Chuang Gan
ICLR 2023
[Project Page] | [Paper] | [Code]
HyperDynamics: Meta-Learning Object and Agent Dynamics with Hypernetworks
Zhou Xian, Shamit Lal, Hsiao-Yu Tung, Emmanouil Antonios Platanios, Katerina Fragkiadaki
ICLR 2021
[Project Page] | [Paper] | [Code]
3D-OES: Viewpoint-Invariant Object-Factorized Environment Simulators
Hsiao-Yu Fish Tung*, Zhou Xian*, Mihir Prabhudesai, Shamit Lal, Katerina Fragkiadaki
CoRL 2020
[Project Page] | [Paper]
Learning from Unlabelled Videos Using Contrastive Predictive Neural 3D Mapping
Adam W. Harley, Fangyu Li, Shrinidhi K. Lakshmikanth, Zhou Xian, Hsiao-Yu Fish Tung, Katerina Fragkiadaki
ICLR 2020
[Project Page] | [Paper] | [Code]
Graph-Structed Visual Imitation
Maximilian Sieb*, Zhou Xian*, Audrey Huang, Oliver Kroemer, Katerina Fragkiadaki
CoRL 2019
[Project Page] | [Paper] | [Code]
Domain Randomization for Macromolecule Structure Classification and Segmentation in Electron Cyro-tomograms
Chengqian Che*, Zhou Xian*, Xiangrui Zeng, Xin Gao, Min Xu
BIBM 2019
[Paper]