I’m Kenichi Maeda, a Master of Science student in Computer Science at Brown University. My interests span machine learning, computer vision, visualization, medical imaging, and robotics.
My current research focuses on robot manipulation, including dexterous manipulation. I’m interested in imitation learning, reinforcement learning, and multimodal vision-language-action (VLA) models, particularly how to train policies efficiently and transfer them from simulation to robust operation on physical robots.
Previously, I earned my Bachelor of Science in Computer Science from the University of Massachusetts Boston, where I worked on multimodal large language models and geometric mesh processing.
Education
Brown University
2025–Master of Science in Computer Science
Research focus: Dexterous hand manipulation; reinforcement learning and imitation learning.
University of Massachusetts Boston
2021–2025Bachelor of Science in Computer Science
Research focus: Multimodal large language models and geometric mesh processing.
Work Experience
Amazon
June 2026 - August 2026Robotics Software Development Engineer Intern
Bellevue, WA
Amazon Fulfillment Technology & Robotics
University of Rostock
June 2024 - August 2024Research Intern
Rostock, Germany
Selected as a 2024 DAAD RISE Germany Scholar.
Contributed to simulation software for deep brain stimulation.
NASA Marshall Space Flight Center
June 2023 - August 2023Software Engineer Intern
Huntsville, AL
Contributed to the development of a quadcopter control system for autonomous flight.
News
| Jul 11, 2026 | I presented our poster at the ICML FM4LS Workshop in Seoul, South Korea. |
|---|---|
| May 27, 2026 | Our paper, PaCX-MAE: Physiology-Augmented Chest X-Ray Masked Autoencoder, was accepted to the ICML 3rd Workshop on Multi-modal Foundation Models and Large Language Models for Life Sciences. |
| Apr 24, 2025 | I gave an oral presentation at IEEE PacificVis 2025 in Taiwan. |
| Feb 08, 2025 | Our paper, “Evaluating Graphical Perception with Multimodal LLMs,” was accepted to IEEE PacificVis 2025. |