Xilun Zhang
Papers
2
Total Citations
7
H-Index
2
About
Xilun Zhang is a rising researcher at the forefront of bridging simulation and reality in robotics, with a focus on closing the sim-to-real gap and enabling creative machine intelligence. His work tackles fundamental challenges in robot learning, particularly the dynamical disparities that prevent simulated policies from transferring effectively to physical systems. In his highly cited 2023 paper, "What Went Wrong? Closing the Sim-to-Real Gap via Differentiable Causal Discovery" (4 citations), Zhang introduces a novel framework that uses causal reasoning to identify and correct model inaccuracies, offering a principled approach to robust policy transfer. Complementing this, his work "Creative Robot Tool Use with Large Language Models" (3 citations) explores how large language models can empower robots to creatively employ tools in tasks requiring implicit physical reasoning and long-term planning—a hallmark of advanced intelligence. Though early in his career, Zhang’s contributions are already shaping how researchers think about sim-to-real transfer and the integration of language models into robotic cognition. His work stands out for its blend of theoretical rigor and practical ambition, promising to accelerate the deployment of intelligent, adaptable robots in the real world.
Research Focus
Key Achievements
Top Papers
- 1
- 2Creative Robot Tool Use with Large Language Models3 citations · 2023