About me
I am an Assistant Professor of Computer Science at the School of Computing and Information Systems at Singapore Management University. I joined SMU in January 2024.
Prior to joining SMU, I obtained my PhD in computer science in 2023 at the Institute of Science and Technology Austria (ISTA), where I was fortunate to be supervised by Krishnendu Chatterjee and Petr Novotný. For my work on developing a framework for learning and verifying neural controllers in stochastic dynamical systems, I received the 2023 Outstanding Scientific Achievement award at ISTA together with my colleague Mathias Lechner. Before that, I obtained bachelor’s and master’s degrees in mathematics at the University of Cambridge. You can find my CV here.
Research Interests
My research is concerned with the development of formal verification, synthesis and certified learning techniques towards making software and intelligent systems more safe, robust and trustworthy. To do so, I combine ideas and tackle a range of problems from Formal Methods, Artificial Intelligence, Machine Learning and Programming Languages research.
The central theme of my work are formal verification, synthesis and certified learning techniques for software and intelligent systems in the presence of uncertainty. Uncertainty may arise due to a plethora of reasons, including interaction with unknown environments, inference from data, randomization, interleaving of processes or multi-agent systems. My goal is to design methods that take uncertainty into account and allow us to build safe, robust and trustworthy software and intelligent systems even in the presence of uncertainty. My current research interests include:
- Learning-based control and safe reinforcement learning (NeurIPS23, ATVA23, TACAS23, AAAI23, AAAI22)
- Program analysis of probabilistic (CAV22, FM21, POPL17) and non-deterministic (PLDI22, PLDI21) programs
- Formal verification and control of Markov models (CAV23, FSTTCS22)
- Formal verification and certified learning of neural networks (AAAI23, NeurIPS21, AAAI21)
- Bidding games on graphs (ECAI23, AAAI23, SODA21, MFCS19)
Openings
I have multiple openings for motivated PhD students to work with me on topics related to formal methods, trustworthy AI or program analysis. I also have openings for undergraduate students at SMU, as well as visiting undergraduate, master and PhD students from other institutions. Please drop me an email with your CV if you are interested. Applicants with a degree in computer science, mathematics or related fields are all welcome.
Singapore is a vibrant and cosmopolitan place with a thriving academic landscape. It is also a perfect place for fellow food lovers. SMU is a premier university and provides an excellent research environment with strong groups in formal methods, AI and software engineering. Doctoral positions at SMU are fully funded. See this page for details.
News
March 2024. Our work Equivalence and Similarity Refutation for Probabilistic Programs has been accepted at PLDI 2024. Thanks and congrats to my coauthors!
February 2024. Our work Quantitative Bounds on Resource Usage of Probabilistic Programs has been accepted at OOPSLA 2024. Thanks and congrats to my coauthors!
December 2023. Honoured to receive the Outstanding Scientific Achievement award at the Institute of Science and Technology Austria, together with Mathias Lechner, for our work on developing a framework for learning and verifying neural controllers in stochastic dynamical systems!
October 2023. I will attend ATVA 2023 in Singapore for the whole duration of the conference, and will present our work Learning Provably Stabilizing Neural Controllers for Discrete-Time Stochastic Systems.
September 2023. Our work Compositional Policy Learning in Stochastic Control Systems with Formal Guarantees has been accepted at NeurIPS 2023. Thanks and congrats to my coauthors!
July 2023. Visited École Normale Supérieure in Paris and talked about A Learner-verifier Framework for Learning and Certifying Neural Controllers in Stochastic Systems.
July 2023. I will attend CAV 2023 in Paris for the whole duration of the conference, and will present the following:
- Our work MDPs as Distribution Transformers: Affine Invariant Synthesis for Safety Objectives at CAV.
- Keynote talk From Probabilistic Program Analysis to Learning-based Stochastic Control with Martingales at the VeriProP workshop.
I will also be at Highlights 2023. Reach out if you will be around and would like to connect!