Zhiao Huang (黄志翱)

Ph.D. Student, CSE, UCSD

z2huang [at] eng (dot) ucsd (dot) edu

Research Topics

  • Differentiable Physics

  • Structured Policy Learning

Short Bio

I am currently a fourth-year Ph.D. student advised by Prof. Hao Su at the Computer Science & Engineering (CSE), University of California, San Diego. My general research interests cover Computer Vision and Machine Learning.

I have got my bachelor's degree at Tsinghua University, where I worked at the Machine Intelligence Group, advised by Prof. Chongjie Zhang. I spent most of my time being an intern at Megvii Inc. (Face++). During the spring of 2017, I was a visiting student at the University of Michigan, advised by Prof. Jia Deng.

Education

  • Ph.D. in Computer Science, University of California, San Diego, 2018 - present

  • B.E. in Computer Science, Tsinghua University, 2014 - 2018

Publication

  • Learning Multi-Object Dynamics with Compositional Neural Radiance Fields

Danny Driess, Zhiao Huang, Yunzhu Li, Russ Tedrake, Marc Toussaint

[arxiv]

  • RoboCraft: Learning to See, Simulate, and Shape Elasto-Plastic Objects with Graph Networks

Haochen Shi*, Huazhe Xu*, Zhiao Huang, Yunzhu Li, Jiajun Wu

Robotics: Science and Systems (RSS), 2022.

[code] [project page]

  • DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Tools

Xingyu Lin, Zhiao Huang, Yunzhu Li, Joshua B Tenenbaum, David Held, Chuang Gan

International Conference on Learning Representations (ICLR), 2022.

[paper]

  • Contact Points Discovery for Soft-Body Manipulations with Differentiable Physics

Sizhe Li*, Zhiao Huang*, Tao Du, Hao Su, Joshua B Tenenbaum, Chuang Gan

International Conference on Learning Representations (ICLR), 2022 (Spotlight).

[paper]

  • Efficient Hierarchical Navigation and Manipulation by Constraint-induced Option-Reward Design

Zhiao Huang, Xiaochen Li and Hao Su

RSS 2021 Workshop on Declarative and Neurosymbolic Representations in Robot Learning and Control

[paper]

  • ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations

Tongzhou Mu, Zhan Ling, Fanbo Xiang, Derek Yang, Xuanlin Li, Stone Tao, Zhiao Huang, Zhiwei Jia, Hao Su

[paper]

  • PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics

Zhiao Huang, Yuanming Hu, Tao Du, Siyuan Zhou, Hao Su, Joshua B. Tenenbaum, Chuang Gan

International Conference on Learning Representations (ICLR), 2021 (Spotlight) .

[paper] [project page]

  • Towards Scale-Invariant Graph-related Problem Solving by Iterative Homogeneous Graph Neural Networks

Hao Tang, Zhiao Huang, Jiayuan Gu, Bao-Liang Lu, Hao Su

Neural Information Processing Systems (NeurIPS), 2020.

[paper]

  • Learning to Group: A Bottom-Up Framework for 3D Part Discovery in Unseen Categories

Tiange Luo, Kaichun Mo, Zhiao Huang, Jiarui Xu, Siyu Hu, Liwei Wang, Hao Su

International Conference on Learning Representations (ICLR), 2020.

[paper]

  • Mapping State Space using Landmarks for Universal Goal Reaching

Zhiao Huang*, Fangchen* Liu, Hao Su

Neural Information Processing Systems (NeurIPS), 2019.

[paper]

  • Object-oriented dynamics predictor

Guangxiang Zhu, Zhiao Huang, Chongjie Zhang

Neural Information Processing Systems (NeurIPS), 2018.

[paper]

  • Associative Embedding: End-to-End Learning for Joint Detection and Grouping

Alejandro Newell, Zhiao Huang, Jia Deng

Neural Information Processing Systems (NIPS), 2017.

[paper]

I know nothing, so I borrow wisdom from the past and the future.