Papers
7
Total Citations
79
H-Index
4
About
Kevin Lin’s research spans the frontiers of robotics, embodied AI, and neuro-inspired systems, with a particular focus on enabling robots to understand natural language, plan complex manipulation tasks, and learn from human demonstrations. His most impactful work includes Text2Motion, a framework that translates natural language instructions into feasible task-and-motion plans for long-horizon robotic reasoning, and DexMimicGen, which automates data generation for bimanual dexterous manipulation via imitation learning—directly addressing the data bottleneck in skill acquisition. Lin also contributed to GR00T N1, an open foundation model for generalist humanoid robots, and the DROID dataset, a large-scale in-the-wild robot manipulation dataset that supports robust policy learning. Earlier in his career, he explored neurobiological reward–place coding in hippocampal cells and developed a millimeter-scale fuel cell with onboard fuel control, demonstrating interdisciplinary breadth. With papers accumulating over 80 citations, Lin’s work is shaping the next generation of autonomous, language-guided robots that can operate in human environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2Millimeter-Scale Fuel Cell With Onboard Fuel and Passive Control System24 citations · 2008
- 3Text2Motion: From Natural Language Instructions to Feasible Plans10 citations · 2023
- 4
- 5GR00T N1: An Open Foundation Model for Generalist Humanoid Robots4 citations · 2025
- 6DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset3 citations · 2024
- 7