Xingyu Liu

Incoming Assistant Professor of Electrical and Computer Engineering
National University of Singapore

Research Scientist
Skild AI

  • xyl@cs.stanford.edu



I will be joining the ECE Department of National University of Singapore (NUS) as an Assistant Professor in 2025. I will be recruiting Ph.D. students, master's students, postdocs and interns to join my group starting 2025. If interested, please kindly read this page.

Welcome to my home page! I am a research scientist at Skild AI, an AI and robotics unicorn founded by Professor Abhinav Gupta and Professor Deepak Pathak. I previouly did postdoc at Carnegie Mellon University (CMU) where I worked with Professor Ding Zhao in Safe AI Lab, Professor Yoichi Sato and Professor Kris Kitani in Robotics Institute, and also collaborated with Professor Deepak Pathak, Professor Nancy Pollard and Professor Jean Oh. My research interest is in the broad disciplines related to artificial intelligence, particularly in robotics, reinforcement learning and computer vision.

I received my Ph.D. from Stanford University where I was advised by Professor Jeannette Bohg in Interactive Perception and Robot Learning Lab (IPRL) and Stanford AI Lab (SAIL). Prior to Stanford, I received my Bachelor's degree from Tsinghua University. I was an undergraduate exchange student at the ECE Department of University of Toronto. I previously interned at Google Brain Robotics, Adobe Research, Amazon A9, NVIDIA and Microsoft Research Asia.

Publications

LocoMan: Advancing Versatile Quadrupedal Dexterity with Lightweight Loco-Manipulators

Changyi Lin, Xingyu Liu, Yuxiang Yang, Yaru Niu, Wenhao Yu, Tingnan Zhang, Jie Tan, Byron Boots, Ding Zhao
IROS 2024
[PDF][Code][Project][Bibtex]

Design and Control Co-Optimization for Automated Design Iteration of Dexterous Anthropomorphic Soft Robotic Hands

Pragna Mannam*, Xingyu Liu*, Ding Zhao, Jean Oh, Nancy Pollard
RoboSoft 2024 (Best Demo Finalist)
[PDF][Bibtex]

Meta-Evolve: Continuous Robot Evolution for One-to-many Policy Transfer

Xingyu Liu, Deepak Pathak, Ding Zhao
ICLR 2024
[PDF][Code][Project][Bibtex]

COMPOSER: Scalable and Robust Modular Policies for Snake Robots

Yuyou Zhang, Yaru Niu, Xingyu Liu, Ding Zhao
ICRA 2024
CoRL 2023 L4SR Workshop (Spotlight)
[PDF][Project][Bibtex]

Deformer: Dynamic Fusion Transformer for Robust Hand Pose Estimation

Qichen Fu, Xingyu Liu, Ran Xu, Juan Carlos Niebles, Kris M. Kitani
ICCV 2023
[PDF][Code][Project][Bibtex]

HERD: Continuous Human-to-Robot Evolution for Learning from Human Demonstration

Xingyu Liu, Deepak Pathak, Kris M. Kitani
CoRL 2022
[PDF][Code][Project][Bibtex]

REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer

Xingyu Liu, Deepak Pathak, Kris M. Kitani
ICML 2022 (Long Oral, Top 2.1%)
[PDF][Code][Oral][Project][Bibtex]

Ego4D: Around the World in 3,000 Hours of Egocentric Video

Kristen Grauman, Andrew Westbury, Eugene Byrne*, Zachary Chavis*, Antonino Furnari*, Rohit Girdhar*, Jackson Hamburger*, Hao Jiang*, Miao Liu*, Xingyu Liu*, Miguel Martin*, Tushar Nagarajan*, Ilija Radosavovic*, Santhosh Kumar Ramakrishnan*, Fiona Ryan*, Jayant Sharma*, Michael Wray*, Mengmeng Xu*, Eric Zhongcong Xu*, Chen Zhao*, Siddhant Bansal, Dhruv Batra, Vincent Cartillier, Sean Crane, Tien Do, Morrie Doulaty, Akshay Erapalli, Christoph Feichtenhofer, Adriano Fragomeni, Qichen Fu, Christian Fuegen, Abrham Gebreselasie, Cristina Gonzalez, James Hillis, Xuhua Huang, Yifei Huang, Wenqi Jia, Weslie Khoo, Jachym Kolar, Satwik Kottur, Anurag Kumar, Federico Landini, Chao Li, Yanghao Li, Zhenqiang Li, Karttikeya Mangalam, Raghava Modhugu, Jonathan Munro, Tullie Murrell, Takumi Nishiyasu, Will Price, Paola Ruiz Puentes, Merey Ramazanova, Leda Sari, Kiran Somasundaram, Audrey Southerland, Yusuke Sugano, Ruijie Tao, Minh Vo, Yuchen Wang, Xindi Wu, Takuma Yagi, Yunyi Zhu, Pablo Arbelaez, David Crandall, Dima Damen, Giovanni Maria Farinella, Bernard Ghanem, Vamsi Krishna Ithapu, C. V. Jawahar, Hanbyul Joo, Kris Kitani, Haizhou Li, Richard Newcombe, Aude Oliva, Hyun Soo Park, James M. Rehg, Yoichi Sato, Jianbo Shi, Mike Zheng Shou, Antonio Torralba, Lorenzo Torresani, Mingfei Yan, Jitendra Malik
TPAMI
[PDF][Code][Video][Project][Bibtex]


Sequential Voting with Relational Box Fields for Active Object Detection

Qichen Fu, Xingyu Liu, Kris M. Kitani
CVPR 2022
[PDF][Code][Video][Project][Bibtex]

V-MAO: Generative Modeling for Multi-Arm Manipulation of Articulated Objects

Xingyu Liu, Kris M. Kitani
CoRL 2021
[PDF][Video][Poster][Project][Bibtex]

StereOBJ-1M: Large-scale Stereo Image Dataset for 6D Object Pose Estimation

Xingyu Liu, Shun Iwase, Kris M. Kitani
ICCV 2021
[PDF][Code][Data][Video][Project][Leaderboard][Bibtex]

RePOSE: Fast 6D Object Pose Refinement via Deep Texture Rendering

Shun Iwase, Xingyu Liu, Rawal Khirodkar, Rio Yokota, Kris M. Kitani
ICCV 2021
[PDF][Code][Project][Bibtex]

KDFNet: Learning Keypoint Distance Field for 6D Object Pose Estimation

Xingyu Liu, Shun Iwase, Kris M. Kitani
IROS 2021
[PDF][Project][Bibtex]

KeyPose: Multi-View 3D Labeling and Keypoint Estimation for Transparent Objects

Xingyu Liu, Rico Jonschkowski, Anelia Angelova, Kurt Konolige
CVPR 2020
[PDF][Code][Data][Video][Blog][Project][Bibtex]

MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences

Xingyu Liu, Mengyuan Yan, Jeannette Bohg
ICCV 2019 (Oral, Top 4.3%)
[PDF][Code][Oral][Project][Bibtex]

Learning Video Representations from Correspondence Proposals

Xingyu Liu, Joon-Young Lee, Hailin Jin
CVPR 2019 (Oral, Top 5.6%)
[PDF][Code][Oral][Bibtex]

FlowNet3D: Learning Scene Flow in 3D Point Clouds

Xingyu Liu*, Charles R. Qi*, Leonidas J. Guibas
CVPR 2019
[PDF][Code][Bibtex]

Efficient Sparse-Winograd Convolutional Neural Networks

Xingyu Liu, Jeff Pool, Song Han, William J. Dally
[PDF][Code][Bibtex]

EIE: Efficient Inference Engine on Compressed Deep Neural Network

Song Han, Xingyu Liu, Huizi Mao, Jing Pu, Ardavan Pedram, Mark A. Horowitz, William J. Dally
Hotchips 2016
[PDF][Slides][Retrospective Paper][Bibtex]

RadixBoost: A Hardware Acceleration Structure for Scalable Radix Sort on Graphic Processors

Xingyu Liu, Shikai Li, Kuan Fang, Yufei Ni, Zonghui Li, Yangdong Deng
ISCAS 2015
[PDF][Bibtex]

FastTree: A Hardware KD-tree Construction Acceleration Engine for Real-time Ray Tracing

Xingyu Liu, Yangdong Deng, Yufei Ni, Zonghui Li
DATE 2015
[PDF][Bibtex]

Education

Ph.D. in Electrical Engineering, 2015 - 2019
M.S. in Computer Science, 2016 - 2019
B.Eng. in Microelectronics with Honors, 2011 - 2015
Exchange Student, in Electrical and Computer Engineering, 2013

Industry Experience

Research Scientist, May 2024 - Present
Research Intern, Jun 2019 - Dec 2019
Research Intern, Jun 2018 - Sep 2018
Research Intern, Jun 2017 - Sep 2017

NVIDIA

Compute Architecture Team, Santa Clara, CA
Research Intern, Jun 2016 - Sep 2016

Teaching

16-720B: Computer Vision
Guest Lecturer, Fall 2021
16-720: Computer Vision
Guest Lecturer, Spring 2021
16-887: Special Topics in Geometry-based Methods in Vision
Guest Lecturer, Fall 2020
16-720B: Computer Vision
Guest Lecturer, Fall 2020

Teaching Assistant, Fall 2019
Teaching Assistant, Spring 2018
Teaching Assistant, Winter 2018
Teaching Assistant, Fall 2017
Teaching Assistant, Spring 2017

Service

Workshop Organizer: Workshop on Pretraining for Robotics (PT4R) @ ICRA 2023
Conference Reviewer: RSS, CoRL, ICRA, IROS, ICML, NeurIPS, ICLR, CVPR, ICCV, ECCV, AAAI, AISTATS, WACV, ACCV
Journal Reviewer: T-RO, RA-L, TPAMI, IJCV, TIP, PR, TCSVT, TVLSI