Sam Wang
Papers
1
Total Citations
7
H-Index
1
About
Sam Wang is a rising star in robotics and artificial intelligence, whose work is reshaping how robots learn and adapt. His primary research focuses on the critical challenge of sim-to-real transfer—the process of taking skills learned in a virtual environment and deploying them effectively in the physical world. Wang’s most notable contribution, the "DrEureka" framework (2024), introduces a novel approach where large language models guide the automatic design of reward functions and simulation parameters, dramatically reducing the need for painstaking human engineering. This work, already garnering 7 citations in its first year, represents a significant leap toward scalable robot learning. By automating the bridge between simulation and reality, Wang is tackling one of robotics’ most persistent bottlenecks. His research promises to accelerate the development of robots that can learn complex tasks at scale, moving beyond the manual, case-by-case tuning that has long limited the field. For students and researchers, Wang’s work exemplifies how AI can be used to bootstrap the very process of robot learning itself.
Research Focus
Key Achievements
Top Papers
- 1DrEureka: Language Model Guided Sim-To-Real Transfer7 citations · 2024