Education

  • M.S. Computer Science - Harvard University
  • B.S. Computer Science - Drexel University

Selected Publications

“Page Stream Segmentation with LLMs: Challenges and Applications in Insurance Document Automation”
Hunter Heidenreich, Ratish Dalvi, Nikhil Verma, Yosheb Getachew
31st International Conference on Computational Linguistics: Industry Track (COLING ‘25)
📄 Paper

“The earth is flat and the sun is not a star: The susceptibility of GPT-2 to universal adversarial triggers”
Hunter Scott Heidenreich, Jake Ryland Williams
Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society (AIES ‘21)
📄 Paper

“Latent semantic network induction in the context of linked example senses”
Hunter Heidenreich, Jake Williams
5th Workshop on Noisy User-generated Text (W-NUT 2019)
📄 Paper

These publications span document processing, AI safety, and knowledge graph construction. My research explores making AI systems more robust and practically useful across different domains.

For a complete list, see my Research page.

Experience

I’ve worked in machine learning for 5+ years, spanning academic research and practical applications. My focus areas include:

  • Natural Language Processing (4+ years) - Semi-supervised learning, large language models, text processing
  • Scientific Computing (2+ years) - Time-series forecasting, molecular dynamics, materials science applications
  • Graph Neural Networks (1+ year) - Chemistry and materials applications

Technical Background

  • Languages: Python, SQL, C/C++
  • Frameworks: PyTorch, TensorFlow, Hugging Face
  • Domains: NLP, Generative Modeling, Time-Series Forecasting, Scientific Computing

What I Write About

I share thoughts on:

  • Deep learning architectures and techniques
  • Natural language processing advances
  • Generative AI applications
  • Time-series forecasting methods
  • Scientific computing with machine learning
  • ML engineering practices

Connect

I’m interested in discussing ML research, collaboration opportunities, or developments in AI. Feel free to reach out whether you’re a researcher, practitioner, or just curious about machine learning.