Cyril Zhang
Papers
1
Total Citations
5
H-Index
1
About
Cyril Zhang is a researcher at the forefront of differentiable programming and control theory, with a focus on bridging the gap between simulation and real-world robotics. His most notable contribution is the development of **Deluca**, a groundbreaking differentiable control library introduced in 2021. This open-source framework provides natively differentiable physics and robotics environments, enabling auto-differentiation through simulation dynamics for the first time. By allowing gradient-based methods to train control policies directly, Zhang's work has accelerated the optimization of complex robotic systems, reducing reliance on model-free reinforcement learning. Though his seminal paper has garnered over 5 citations, its impact is amplified by the broader adoption of differentiable programming in robotics. Zhang's achievements include pioneering a benchmark suite that standardizes evaluation for gradient-based control, making his work a cornerstone for researchers exploring end-to-end learning in physical systems. His contributions are particularly influential for students and engineers seeking efficient, data-driven approaches to robot manipulation and autonomous navigation.
Research Focus
Key Achievements
Top Papers
- 1