Scholar

Seungjae (Jay) Lee

Google Scholar ID: hpR9h74AAAAJ

University of Maryland

Reinforcement LearningRobotics

Citations & Impact

All-time

Citations

224

H-index

i10-index

Publications

Co-authors

list available

Contact

Publications

11 items

Browse publications on Google Scholar (top-right) ↗

Resume (English only)

Academic Achievements

- Published Papers: Multiple papers such as 'Sequential-EQA: A Memory-Centric Benchmark for Embodied VQA' covering areas like reinforcement learning, control policies, etc.
- Awards: ICML 2024 Workshop MFM-EAI, 'Outstanding Paper Award - Winner'
- Project Involvement: Involved in multiple research projects, such as 'Imagine, Verify, Execute: Memory-guided Agentic Exploration with Vision-Language Models'.

Research Experience

- During his time at NYU's Generalizable Robotics and AI Lab, he worked on enhancing the data efficiency of Reinforcement Learning (RL) and Imitation Learning (IL) systems and applied them to various decision-making scenarios, including real-world robots.

Education

- Ph.D. in Computer Science, University of Maryland, Aug 2024 - Present, Advisors: Furong Huang and Jia-Bin Huang
- Visiting Research, New York University, Jul 2023 - Jun 2024, Advisor: Lerrel Pinto
- M.S. in Aerospace Engineering, Seoul National University, Mar 2021 - Feb 2024, Advisor: H. Jin Kim
- B.S. in Mechanical & Aerospace Engineering, Seoul National University, Mar 2015 - Feb 2021

Background

- Research Interests: Understanding the interaction between agents and environments, devising data-efficient decision-making (or robot learning) algorithms, especially in the field of reinforcement learning (RL).
- Professional Fields: Computer Science, Aerospace Engineering
- Brief Introduction: Currently a Ph.D. student in the Department of Computer Science at UMD, previously obtained a Master's degree in Aerospace Engineering from SNU, and conducted research at NYU's Generalizable Robotics and AI Lab.

Miscellany