Yen‐Jen Wang
Papers
7
Total Citations
70
H-Index
6
About
Yen-Jen Wang is a rising star at the intersection of large language models (LLMs) and robotics, pioneering methods to imbue machines with both high-level reasoning and low-level motor control. His core research focuses on grounding foundation models—LLMs and vision-language models (VLMs)—for real-world robotic locomotion and manipulation. Wang’s major contributions include developing frameworks that enable robots to interpret natural language prompts for walking (cited 21 times) and to detect and recover from plan-execution misalignment in physical tasks (cited 17 times). He also advanced vision-language-action (VLA) models by improving them through online reinforcement learning, a novel approach that moves beyond supervised fine-tuning. Notably, Wang created Humanoid-Gym, a reinforcement learning framework for humanoid robots that achieves zero-shot sim-to-real transfer, demonstrating his commitment to bridging simulation and reality. His work on decentralized motor skill learning further showcases his ability to tackle complex, multi-agent robotic systems. With a rapidly growing citation record and publications in top venues, Wang is shaping the future of intelligent, language-guided robotics.
Research Focus
Key Achievements
Top Papers
- 1Prompt a Robot to Walk with Large Language Models21 citations · 2024
- 2
- 3
- 4Prompt a Robot to Walk with Large Language Models7 citations · 2023
- 5Decentralized Motor Skill Learning for Complex Robotic Systems6 citations · 2023
- 6
- 7