About Me

My name is Kia Rahmani, and I am a computer scientist passionate about designing generalizable, interpretable, and reliable machine learning algorithms using the theory of programming languages.

I currently serve as a postdoctoral fellow at the Computer Science Department of the University of Texas at Austin, under the supervision of Prof. Işil Dillig and Prof. Joydeep Biswas.

The current focus of my research is on neuro-symbolic algorithms for sequential decision making. My ultimate scientific goal is to train intelligent agents that can provide formal explanation and guarantees about their behaviors.

Prior to joining UT, I obtained my PhD from Purdue University under the supervision of Prof. S. Jagannathan and Prof. B. Delaware. I also did an internship with Microsoft where I developed a new program synthesis algorithm using large language models, under the supervision of Dr. S. Gulwani and Dr. M. Raza.

Publications & Patents

  • Multi-modal Program Inference (US20230176829A1)
    (Kia Rahmani, Mohammad Raza, Sumit Gulwani, Vu Le, Daniel Morris, Arjun Radhakrishna, Gustavo Soares, Ashish Tiwari)
    [United States Patent Application]

Service