• Home
• Publications
• CV (last updated: May 2021)
• Quotes

PhD Candidate Department of Electrical and Computer Engineering The University of Texas at Austin Email: vasic AT utexas.edu LinkedIn Github Google Scholar

About Me

I am a PhD candidate in Electrical and Computer Engineering department advised by Professor Sarfraz Khurshid, while my unofficial co-adviser is Professor David Soloveichik.

Research interests:

• Molecular programming: Designing natural programming methods and languages for synthetic biology, nanotechnology, and bioengineering which efficiently compile to chemistry.
• AI for code: Applying AI techniques to improve software development process, e.g., developing tools for automated bug detection and program repair.

Publications

• Marko Vasic, Cameron Chalk, Austin Luchsinger, Sarfraz Khurshid, David Soloveichik
  Programming and Training Rate-Independent Chemical Reaction Networks
  Proceedings of the National Academy of Sciences
  (PNAS), 2022.
  [publisher] [video] [github]
• Marko Vasic, Andrija Petrovic, Kaiyuan Wang, Mladen Nikolic, Rishabh Singh, Sarfraz Khurshid
  MoËT: Mixture of Expert Trees and its Application to Verifiable Reinforcement Learning
  Neural Networks
  (), 2022.
  [pdf] [github]
• Marko Vasic, David Soloveichik, Sarfraz Khurshid
  CRNs Exposed: Systematic Exploration of Chemical Reaction Networks
  International Conference on DNA Computing and Molecular Programming
  (DNA), 2020.
  [Best Student Paper Award] [arxiv] [publisher]
• Marko Vasic, Cameron Chalk, Sarfraz Khurshid, David Soloveichik
  Deep Molecular Programming: A Natural Implementation of Binary-Weight ReLU Neural Networks
  International Conference on Machine Learning
  (ICML), 2020.
  [arxiv] [video] [github]
• Muhammad Usman, Wenxi Wang, Marko Vasic, Kaiyuan Wang, Haris Vikalo, Sarfraz Khurshid
  A Study of the Learnability of Relational Properties: Model Counting Meets Machine Learning (MCML)
  Conference on Programming Language Design and Implementation
  (PLDI), 2020.
  [arxiv]
• Shikhar Singh, Marko Vasic, Sarfraz Khurshid
  Designing Neural Networks Using Logical Specs
  International Symposium on Software Reliability Engineering
  (ISSRE), 2020.
  [publisher]
• Marko Vasic, David Soloveichik, Sarfraz Khurshid
  CRN++: Molecular Programming Language
  Journal of Natural Computing
  (), 2020.
  [arxiv] [github]
• Marko Vasic, Aditya Kanade, Petros Maniatis, David Bieber, Rishabh Singh
  Neural Program Repair by Jointly Learning to Localize and Repair
  International Conference on Learning Representations
  (ICLR), 2019.
  [arxiv]
• Marko Vasic, David Soloveichik, Sarfraz Khurshid
  CRN++: Molecular Programming Language
  International Conference on DNA Computing and Molecular Programming
  (DNA), 2018.
  [arxiv] [github]
• Ahmet Celik, Marko Vasic, Aleksandar Milicevic, Milos Gligoric
  Regression Test Selection Across JVM Boundaries
  Symposium on the Foundations of Software Engineering
  (FSE), 2017.
  [arxiv]
• Marko Vasic, Zuhair Parvez, Aleksandar Milicevic, Milos Gligoric
  File-Level vs. Module-Level Regression Test Selection for .NET
  Symposium on the Foundations of Software Engineering
  (FSE), 2017.
  [arxiv] [github]