Sangkyu Lee
I am a research scientist intern at the Artificial Intelligence and Robotics Institute in KIST. I previously researched at LG AI Research, Naver Cloud and maumAI. I received an M.S. in Artificial Intelligence from Yonsei University under the supervision of Youngjae Yu and Jongmin Lee, and a B.A. in Applied Statistics and a B.S. in Computer Science & Engineering from Yonsei University. My research aims to enable end-to-end continual multimodal learning for accumulating knowledge from real-world embodied experience without human supervision. I strive to achieve this goal by a scalable yet simple approach. I am currently interested in multimodal generative models, AI alignment (specifically for Robotics), long-term memory, and continual learning.
Looking for Ph.D. programs, and feel free to contact me for collaborations!
News
| Jun 18, 2026 | Our paper, Spanning Tree Autoregressive Visual Generation is accepted at ECCV 2026. |
|---|---|
| Jun 11, 2026 | Our new preprint, Real-Time Execution with Autoregressive Policies, is released. |
| Nov 24, 2025 | Check out our new preprint, Spanning Tree Autoregressive Visual Generation. |
| Sep 18, 2025 | Our paper is accepted at NeurIPS 2025. |
| Sep 01, 2025 | I am starting a research scientist internship at the Artificial Intelligence and Robotics Institute in KIST. |