About Me

My name is Kia Rahmani, and I am an AI scientist at Durable. I am passionate about designing interpretable and reliable artificial intelligence through the theory of programming languages. At Durable, we aim to bridge the gap between natural language and code through trustworthy program synthesis methods.

Before joining Durable, I served as a post-doctoral researcher at the University of Texas at Austin under the supervision of Prof. I. Dillig and 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.

Publications & Patents

• Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning
  (Arko Banerjee, Kia Rahmani, Joydeep Biswas, Isil Dillig)
  [Neurips'24: The Thirty-eighth Annual Conference on Neural Information Processing Systems] [Arxiv]

• Programmatic Imitation Learning from Unlabeled and Noisy Demonstrations
  (Jimmy Xin*, Linus Zheng*, Kia Rahmani, Jiayi Wei, Jarrett Holtz, Isil Dillig, Joydeep Biswas)
  [IEEE Robotics and Automation Letters] [Video] [Project Website] [Arxiv]

• Programming-by-Demonstration for Long-Horizon Robot Tasks
  (Noah Patton, Kia Rahmani, Meghana Missula, Joydeep Biswas, Isil Dillig)
  [POPL'24: 51st ACM SIGPLAN Symposium on Principles of Programming Languages] [Arxiv]

• 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]

• Symbolic Analysis of Weak Concurrency Semantics in Modern Database Programs
  (Kia Rahmani)
  [PhD Thesis, Purdue University, August 2022] [Slides]

• Multi-modal Program Inference: a Marriage of Large Language Models and Component-based Synthesis
  (Kia Rahmani, Mohammad Raza, Sumit Gulwani, Vu Le, Daniel Morris, Arjun Radhakrishna, Gustavo Soares, Ashish Tiwari)
  [OOPSLA'21: ACM Conference on Object-Oriented Programming, Languages, Systems, and Applications]
  [pre-print] [Pdf] [15min-talk] [Slides]

• Repairing Serializability Bugs in Distributed Database Programs via Automated Schema Refactoring
  (Kia Rahmani, Kartik Nagar, Benjamin Delaware and Suresh Jagannathan)
  [PLDI'21: ACM SIGPLAN Conference on Programming Language Design and Implementation]
  [pdf]

• CLOTHO: Directed Test Generation for Weakly Consistent Database Systems
  (Kia Rahmani, Kartik Nagar, Benjamin Delaware and Suresh Jagannathan)
  [OOPSLA'19: ACM Conference on Object-Oriented Programming, Languages, Systems, and Applications]
  [Tech Report] [Talk @OOPSLA] [Talk @Midwest PL Summit] [Slides]

• Fine-grained Distributed Consistency Guarantees with Effect Orchestration
  (Kia Rahmani, Gowtham Kaki and Suresh Jagannathan)
  [PaPoC'18: Workshop on the Principles and Practice of Consistency for Distributed Data]
  [Tech Report] [Slides]

Academic Service

• 2026
  • Program Committee
  • ACM Conference on Object-Oriented Programming, Languages, Systems, and Applications (OOPSLA)
• 2025
  • Program Committee
  • International Conference on Learning Representations (ICLR)
  • International Conference on Machine Learning (ICML)
• 2024
  • Program Committee
  • Conference on Neural Information Processing Systems (NeurIPS)
  • DoE SBIR and STTR Programs
  • IEEE Robotics and Automation Letters (RA-L)
• 2023
  • Program Committee
  • International Symposium on Technological Advances in Human-Robot Interaction (TAHRI)
  • Reviewer
  • IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
• 2021
  • Program Committee
  • Advances in Programming Languages and Neurosymbolic Systems Workshop (@Neurips 2021)