Mirabel Reid

About

I am Mirabel Reid, and I have just graduated with my PhD in computer science from Georgia Tech, advised by Santosh Vempala.

My research lies at the intersection of theoretical computer science, neuroscience, and human-AI understanding.

Research Interests

• Mathematically tractable models for neural computation.
• Random Graphs and the probabilistic analysis of recurrent processes.
• Cognitive abilities of Large Language Models.
• Interplay between machine and human learning and computation.

Publications

• The alpha-Cap Process: A Continuous Model for Random Geometric Networks of Binary Neurons
  Mirabel Reid and Daniel Zhang. View it here.

• Does GPT Really Get It? A Hierarchical Scale to Quantify Human vs AI’s Understanding of Algorithms.
  Mirabel Reid and Santosh S. Vempala. Proceedings of AAAI 2025 (Oral).View it here.

  Check out the survey questions at this GitHub Repository, or take the survey yourself here.

• The k-Cap Process on Geometric Random Graphs.
  Mirabel Reid and Santosh S. Vempala. Published at COLT 2023. View it here.
• Online Decision Deferral under Budget Constraints.
  Mirabel Reid, Tom Sühr, Claire Vernade, Samira Samadi. View it here.
• Improving Radiography Machine Learning Workflows via Metadata Management for Training Data Selection.
  Mirabel Reid, Christine Sweeney, and Oleg Korobkin. View it here.

Presentations

• On k-Winners-Take-All as a Model of Neuron Communication
  CMU Theory Lunch Seminar, Mar 2025 (Oral)
• Does GPT Really Get It? A Hierarchical Scale to Quantify Human vs AI’s Understanding of Algorithms
  Workshop on Behavioral ML, NeurIPS, Dec 2024 (Poster)
• The Effects of Locality on Neural Firing Dynamics
  Computational and Systems Neuroscience, Mar 2023 (Poster). View poster here.
• The k-Cap Process on Geometric Random Graphs
  Mathematical and Scientific Foundations of Deep Learning Annual Meeting, Sep 2022 (Poster). View poster here.