Ying Wen
Papers
3
Total Citations
17
H-Index
3
About
Ying Wen is a researcher working at the intersection of robotics, reinforcement learning, and intelligent decision-making systems. Their work spans two exciting frontiers: adaptive control for physical robotic systems and the application of large language models (LLMs) to autonomous agents capable of complex real-world reasoning. Among their most notable contributions is research on fault-tolerant quadruped robots, where they developed adaptive control strategies that enable robots to continue operating under actuator degradation — a critical advancement for practical robotics deployment in extreme environments. This work has garnered 7 citations, reflecting its relevance to the field. Wen has also made meaningful strides in LLM-based agent design, with the TRAD framework introducing step-wise thought retrieval and aligned decision-making to improve agent generalization across tasks like web navigation and online shopping (5 citations). Additionally, their perspective paper on Foundation Decision Models addresses the grand challenge of building intelligent systems that adapt continuously in uncertain, dynamic real-world settings — a vision that unifies much of their research agenda. With a portfolio bridging physical robotics and AI-driven decision-making, Ying Wen is emerging as a versatile contributor to the next generation of autonomous, resilient intelligent systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3