I am a PhD from HKUST and also a member affiliated with GEAR at NVIDIA Research, working with Yuke Zhu and Jim Fan. I am currently scaling foundation models for robots. Previously, I was fortunate to work at OpenDriveLab.

I was born in the last year of the 20th century (May 17th, 2000). I hope to live until the 22nd century so that my life would span three centuries. The Chinese meanings of each word in my name (高深远) are "High", "Deep", "Far", respectively.

• Video World Models for General-Purpose Robots
• Self-Improvement by Scaling Data and Compute

• DreamDojo [Project] [VentureBeat]

  A Robot World Model pretrained on 44k hours of human egocentric data, showing unprecedented generalization to diverse objects and environments.

• DreamZero [Project]

  A World Action Model (WAM) that enables zero-shot generalization to unseen tasks and enables few-shot embodiment learning.

• Ph.D. in Electronic and Computer Engineering, 2022-2026
  • HKUST, under the tutelage of Prof. Jun Zhang (IEEE Fellow)
• B.Eng. in Electronic Information Engineering, 2018-2022
  • HUST, Advanced Class (GPA 3.9/4.0, ranked 1st)

Please find my up-to-date [Resume] to check my current status.

• XingQi Intern (the highest honor for research interns at Shanghai AI Laboratory)
• NeurIPS Top Reviewer
• RedBird PhD Scholarship
• Full Postgraduate Scholarship
• Outstanding Graduate
• Outstanding Graduation Thesis
• Outstanding Undergraduate in Terms of Academic Performance (Top 1%)
• National Scholarship (Top 2%)

• Workshop Organizer
  • CVPR 2025 Workshop on Scalable Robot Learning Systems
  • NeurIPS 2025 Workshop on Embodied World Models for Decision Making
• Conference Reviewer
  • ICLR, ICML, NeurIPS, RSS, SIGGRAPH, CVPR, ICCV, ECCV, WACV, AAAI, AISTATS, BMVC, ICPR
• Journal Reviewer
  • CSUR, TMLR, RAL, TPAMI, TMM, TCSVT, TASE, IMAVIS, PR, ASOC
• Teaching
  • COMP 5214: Advanced Deep Learning Architectures (graduate/undergraduate)
  • ELEC 3100: Signal Processing and Communications (undergraduate)