Papers
1
Total Citations
6
H-Index
1
About
Kaiyi Ji is a rising leader in the intersection of machine learning and robotics, with a focus on self-supervised learning, neuro-symbolic frameworks, and robot autonomy. Their most notable contribution is the development of "Imperative Learning," a self-supervised neuro-symbolic learning framework that addresses a critical bottleneck in robotics: the inability of data-driven methods like reinforcement learning to generalize to dynamic environments. By reducing reliance on expensive data labeling, Ji’s work offers a scalable path toward adaptable, autonomous systems. This flagship paper, published in 2025, has already garnered 6 citations, signaling its early impact on the field. Ji’s research is particularly significant for its potential to bridge symbolic reasoning with continuous learning, enabling robots to operate robustly in unstructured settings. As a researcher pushing the boundaries of how machines learn from sparse feedback, Kaiyi Ji is shaping the next generation of intelligent, self-improving robotic systems—work that promises to make autonomous agents more practical and resilient in real-world applications.
Research Focus
Key Achievements
Top Papers
- 1