I’m Siyuan Zhou, a third-year PhD student at Hong Kong University of Science and Technology (HKUST), supervised by Prof. Dit-Yan Yeung. I’m fortunately supervised by Prof. Chuang Gan and closely collaborate with Prof. Yilun Du.

Currently, I’m focusing on:

  1. Generation Models and World Models
  2. Generalization in Robot Learning

Publications

ICML 2024

Robodreamer: Learning Compositional World Models for Robot Imagination

Siyuan Zhou, Yilun Du, Jiaben Chen, Yandong Li, Dit-Yan Yeung, Chuang Gan

ICML 2024 [arXiv] [Project] [Code]

Neurips 2023
sym

Adaptive Online Replanning with Diffusion Models

Siyuan Zhou, Yilun Du, Shun Zhang, Mengdi Xu, Yikang Shen, Wei Xiao, Dit-Yan Yeung, Chuang Gan

Neurips 2023 [arXiv] [Code]

AAMAS 2024
sym

Multi-Agent Alternate Q-Learning

Kefan Su, Siyuan Zhou, Jiechuan Jiang, Chuang Gan, Xiangjun Wang, Zongqing Lu

AAMAS 2024 [arXiv]

ICRA 2022
sym

The threedworld transport challenge: A visually guided task-and-motion planning benchmark for physically realistic embodied ai

Chuang Gan, Siyuan Zhou, Jeremy Schwartz, Seth Alter, Abhishek Bhandwaldar, Dan Gutfreund, Daniel LK Yamins, James J DiCarlo, Josh McDermott, Antonio Torralba, Joshua B Tenenbaum

ICRA 2022 [arXiv]

Honors and Awards

  • 2022.09, HKUST RedBird PhD Award
  • 2016, NOI Siliver Medal

Education

  • 2022.08 - Now, Ph.D. student in Computer Science and Engineering, The Hong Kong University of Science and Technology.
  • 2017.09 - 2022.06, BSc in Computer Science, Peking University.

Internships

  • 2024.08 - Now, Research Intern, Tencent Robotics X Lab
  • 2023.06 - 2023.09, Visiting Student, MIT-IBM Watson AI Lab
  • 2021.09 - 2021.12, Research Intern, Tencent WXG