Kelvin Lin
Papers
3
Total Citations
6
H-Index
2
About
Kelvin Lin is a rising researcher at the forefront of embodied AI and robotic manipulation, with a focus on bridging language, perception, and physical interaction. His work centers on three key areas: language-guided manipulation, tactile reasoning, and robot caregiving. In his notable paper "DISCO," Lin pioneered the integration of diffusion policies with constrained inpainting to enable robots to follow open-vocabulary language instructions, a significant step toward generalizable manipulation in unstructured environments. His contributions to tactile intelligence are exemplified in "Octopi," where he introduced large tactile-language models capable of reasoning about object properties—such as texture and hardness—beyond what vision alone can perceive. Lin also made a substantial impact in assistive robotics with "OpenRoboCare," the first multimodal, multi-task expert demonstration dataset for robot caregiving, capturing occupational therapist demonstrations of Activities of Daily Living. Though early in his career, each of his papers has garnered 2 citations, signaling growing recognition. Lin’s work is distinguished by its practical orientation toward real-world human-robot interaction, particularly in healthcare and home settings, where safe, context-aware physical contact is critical.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Octopi: Object Property Reasoning with Large Tactile-Language Models2 citations · 2024