Kai Mo

Tsinghua–Berkeley Shenzhen Institute

Papers

2

Total Citations

39

H-Index

2

About

Kai Mo is a rising researcher in robot manipulation, with a focus on deformable objects and sequential task planning. His work addresses some of the most challenging problems in robotics: enabling robots to perceive, plan, and execute complex manipulations of non-rigid materials like cloth. In his highly cited 2022 paper, "Foldsformer: Learning Sequential Multi-Step Cloth Manipulation With Space-Time Attention" (25 citations), Mo introduced a novel space-time attention mechanism that allows robots to learn chained actions for folding tasks, moving beyond simple goal-conditioned approaches. He further advanced the field with his 2024 work, "Learning Language-Conditioned Deformable Object Manipulation with Graph Dynamics" (14 citations), which leverages natural language instructions and graph-based dynamics models to enable multi-task learning and generalization to new tasks without requiring goal images. Mo's contributions are particularly notable for their practical impact on robotic laundry, garment handling, and other real-world applications. His innovative integration of attention mechanisms and language conditioning marks him as a key figure in the next generation of robotic manipulation research.

Research Focus

Key Achievements

2
H-Index
2
Papers
39
Total Citations
20
Avg Citations/Paper
🏆 Most Cited Paper
Foldsformer: Learning Sequential Multi-Step Cloth Manipulation With Space-Time Attention
25 citations · 2022
📈 Most Prolific Year: 2022 (1 Papers)
🤝 Key Collaborators: 6
🏛 Institutions: Tsinghua–Berkeley Shenzhen Institute

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago