About me

Hello! My name is Alaia, and I am a fourth-year Ph.D. student at the University of Pennsylvania where I am fortunate to be advised by Rajeev Alur. My current research interests include:

• Policy enforcement for agents
• Constrained decoding of LLMs for code generation
• Clinical forecasting

Currently, I am a student researcher at Google DeepMind, working on policy enforcement for agents. In the past, I have interned in the Agentic AI/Automated Reasoning Group at AWS where I worked on automated inference of API preconditions to improve the correctness of LLM-generated code. My research has previously been supported by a gift from AWS.

Publications

Preprints

• Efficient and Sound Probabilistic Verification for AI Agents
  Alaia Solko-Breslin, Pramod Kaushik Mudrakarta, Mihai Christodorescu, Somesh Jha, and Krishnamurthy Dj Dvijotham
  June 2026

• CAMEL: An ECG Language Model for Forecasting Cardiac Events
  Neelay Velingker*, Alaia Solko-Breslin*, Mayank Keoliya*, Seewon Choi*, Jiayi Xin, Anika Marathe, Alireza Oraii, Rajat Deo, Sameed Khatana, Rajeev Alur, Mayur Naik, and Eric Wong
  February 2026

Conference Publications

• CTSketch: Compositional Tensor Sketching for Scalable Neurosymbolic Learning
  Seewon Choi*, Alaia Solko-Breslin*, Rajeev Alur, and Eric Wong
  NeurIPS 2025

• Understanding the Effectiveness of LLMs in Detecting Security Vulnerabilities
  Avishree Khare*, Saikat Dutta*, Ziyang Li, Alaia Solko-Breslin, Rajeev Alur, and Mayur Naik
  ICST 2025

• Data-Efficient Learning with Neural Programs
  Alaia Solko-Breslin, Seewon Choi, Ziyang Li, Neelay Velingker, Rajeev Alur, Mayur Naik, and Eric Wong
  NeurIPS 2024

• Automata Learning with an Incomplete Teacher
  Mark Moeller, Thomas Wiener, Alaia Solko-Breslin, Caleb Koch, Nate Foster, and Alexandra Silva
  ECOOP 2023

• Petr4: Formal Foundations for P4 Data Planes
  Ryan Doenges, Mina Tahmasbi Arashloo, Santiago Bautista, Alexander Chang, Newton Ni, Samwise Parkinson, Rudy Peterson, Alaia Solko-Breslin, Amanda Xu, and Nate Foster
  POPL 2021

Other Writing

• Development and Validation of a New Large Language Model for Detecting Atrial Fibrillation
  Seewon Choi, Mayank Keoliya, Alaia Solko-Breslin, Neelay Velingker, Alireza Oraii, Rajeev Alur, Rajat Deo, Sameed Ahmed Khatana, Mayur Naik, and Eric Wong
  Heart Rhythm Society 2026

• Learning Neural Programs
  Alaia Solko-Breslin
  UPenn WPE-II Research Qualifier 2024

* equal contribution

Teaching

University of Pennsylvania

• Spring 2024 TA for CIS 7000: Special Topics: Trustworthy Machine Learning
• Fall 2023 TA for CIS 5000: Software Foundations

Cornell University

• Spring 2022 TA for CS 4160/5160: Formal Verification
• Fall 2021 TA for CS 3110: Data Structures and Functional Programming
• Spring 2021 TA for CS 4820: Introduction to Analysis of Algorithms
• Fall 2020 TA for CS 4820: Introduction to Analysis of Algorithms
• Spring 2020 TA for CS 3110: Data Structures and Functional Programming
• Fall 2019 TA for CS 3110: Data Structures and Functional Programming

Service

• Reviewer: NeurIPS 2025, ICML 2026

Other

Outside of academic things, I like to run and read. I am also passionate about animal rights and veganism 🌱. In a past life, I was an avid Tetris player.