Yuvan Sharma

About

Yuvan Sharma is at the forefront of embodied AI and robot learning, with a particular focus on harnessing the in-context learning (ICL) capabilities of Large Language Models (LLMs) for direct robot action prediction. His pioneering work, most notably the RoboPrompt framework introduced in his highly cited 2025 paper, addresses a critical gap in robotics: enabling LLMs to translate language understanding into physical action without task-specific fine-tuning. By demonstrating that ICL can be effectively leveraged to predict robot trajectories and manipulation sequences, Sharma has opened a new paradigm for few-shot robot control, reducing the need for extensive real-world data collection. His research, which has already garnered significant attention with over 3 citations in its first year, bridges the gap between natural language processing and robotics, offering a scalable path toward more adaptable and intelligent autonomous systems. Sharma’s contributions are particularly notable for their practical implications, promising to accelerate the deployment of robots in unstructured environments by allowing them to learn from just a handful of demonstrations.

Research Focus

Key Achievements

Top Papers

1. 1
   In-Context Learning Enables Robot Action Prediction in LLMs

   3 citations · 2025

Key Collaborators

Contact & Links