Yash Sharma
Papers
1
Total Citations
3
H-Index
1
About
Yash Sharma is a rising researcher at the intersection of robotics, artificial intelligence, and human-robot interaction, with a focus on enabling non-expert users to intuitively teach robots new skills. His most notable contribution is the groundbreaking work "Demo2Code: From Summarizing Demonstrations to Synthesizing Code via Extended Chain-of-Thought," which bridges the gap between human demonstration and robotic programming. This work addresses a fundamental challenge in robotics: while large language models (LLMs) excel at translating language instructions into code, translating physical demonstrations—a more natural teaching method—remains difficult. Sharma’s approach leverages extended chain-of-thought reasoning to first summarize demonstrations and then synthesize executable code, effectively allowing robots to learn from human actions without requiring programming expertise. Though early in his career, his work has already garnered attention (3 citations for a 2023 paper), signaling its potential impact. By making robot programming more accessible, Sharma is contributing to a future where robots can be personalized by everyday users, not just experts. His research sits at the exciting frontier where LLMs meet embodied AI, promising to reshape how we teach and interact with robotic systems.
Research Focus
Key Achievements
Top Papers
- 1