Scholar
Shaofei Cai (蔡少斐)
Google Scholar ID: MZXDSSUAAAAJ
Peking University
Citations & Impact
Citations
1,040
H-index
11
i10-index
11
Publications
20
Co-authors
6
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- 1st Place at ATEC 2025 Robotics and AI Challenge, Software Track
- Gold Medal (Top 3.3%) at the 43rd ICPC International Collegiate Programming Contest Asia Regional, 2018
- 3rd Academic Star Award (Top 5 Students) at Peking University, 2025
- Outstanding Student Award at Xi’an Jiaotong University for undergraduate students, 2019
- Publications: ROCKET-3 (2025), ROCKET-2 (2025), GROOT-2 (2025), OmniJARVIS (2024), GROOT (2024), etc.
Background
- Research Interests: Machine Learning, Computer Vision, Reinforcement Learning, Embodied Intelligence, LLM Agents. Doctoral research focused on multi-task agents in open-world settings, particularly developing a task representation method with high expressiveness, low ambiguity, and scalability. Led the development of the GROOT and ROCKET series in 3D video games, enabling AI agents to perform complex tasks in Minecraft based on human instructions. Also explored using reinforcement learning to enhance visual reasoning abilities.
Miscellany
- Dream is to witness the emergence of AGI and contribute efforts. Believes that scalable generation and validation of tasks within digital worlds is currently the most viable route to achieving AGI.
