About me

I am currently a Postdoctoral Researcher at Microsoft Research, NYC. Previously, I obtained the Ph.D. degree in electrical and systems engineering from the University of Pennsylvania (UPenn). I was advised by Prof. Victor M. Preciado. At UPenn, I am also closely working with Prof. Manfred Morari, Prof. George J. Pappas, and Prof. Nikolai Matni. Before coming to UPenn, I received a B.E. degree in Automation from Zhejiang University, China, in 2017.

You can find my CV here and contact me at shaoruchen at microsoft dot com. If you are interested in my research or want to collaborate, please feel free to reach me!

About my research

I am interested in making AI systems work reliably and safely. My research spans machine learning, control, and optimization. Currently, I am mainly working on evaluation of the reasoning power of large language models (LLMs) and using language model feedback for reinforcement learning. Previously, I have worked on:

  1. Neural Network Verification: Developing specialized and scalable optimization tools to verify properties of NNs and NN-controlled systems.

  2. Representation Learning for Planning: Learning latent space models that captures environmental geometry for motion planning from observation data.

  3. Verification-Aided Learning of Neural Certificates: Investigating how to best couple verification and learning to find a formal neural network certificate for learning-enabled systems.

  4. Robust Model Predictive Control: Boosting the tightness of robust MPC by jointly searching for robust feedback policies and system uncertainty over-approximations through convex programming.