Stephan Mandt

Papers

Total Citations

H-Index

About

Stephan Mandt is a leading researcher at the intersection of machine learning, probabilistic modeling, and robotics. His work advances scalable Bayesian inference and deep generative models, with a particular focus on making complex statistical methods practical for real-world systems. Mandt is widely recognized for his foundational contributions to stochastic gradient-based inference and variational autoencoders, which have enabled more efficient learning from large-scale, high-dimensional data. His research has been cited over 10,000 times, reflecting its profound impact on both theory and application. Notably, Mandt has explored the frontier of autonomous systems, including pioneering work in mobile robotic painting—extending robotic capabilities from controlled factory settings to dynamic, unstructured environments. This work, such as his 2019 paper on robotic texture painting, demonstrates his commitment to bridging algorithmic innovation with tangible, real-world deployment. A recipient of multiple best paper awards and an NSF CAREER Award, Mandt continues to shape the future of machine learning and robotics, inspiring students and researchers to push the boundaries of what intelligent systems can achieve.