Kinam Kim
Ph.D. Student · KAIST AI
I am a Ph.D. student at KAIST AI, advised by Prof. Jaegul Choo. I am currently a research intern at NVIDIA, previously at Microsoft Research Asia.
My research is on robot foundation models: training Vision-Language-Action (VLA) policies that act reliably on real hardware, and scaling the data and training recipes behind them. I work on latent reasoning inside VLA policies, reinforcement learning with zero-shot sim-to-real transfer, and demonstration generation that needs no human teleoperation. My work on video generative models as world models is a second route to robot data: egocentric human video and the simulators that produce it.
If you have any questions or suggestions, please feel free to contact me via email (kinamplify@kaist.ac.kr)!
