Publications

2025

1. DynaGuard: A Dynamic Guardian Model With User-Defined Policies

   Monte Hoover, Vatsal Baherwani, Neel Jain, and 7 more authors

   arXiv preprint arXiv:2509.02563, 2025
2. Exploiting Sparsity for Long Context Inference: Million Token Contexts on Commodity GPUs

   Ryan Synk, Monte Hoover, John Kirchenbauer, and 6 more authors

   In the 42nd International Conference on Machine Learning Workshops on Vector Databases (ICML VecDB), 2025
3. Towards Making Linear Attention Usable

   Armin Gerami, Monte Hoover, and Ramani Duraiswami

   arXiv preprint, 2025

2024

1. FAST: Factorizable Attention for Speeding up Transformers

   Armin Gerami, Monte Hoover, Pranav S. Dulepet, and 1 more author

   arXiv preprint arXiv:2402.07901, 2024

2023

1. Computing Acoustic Onsets Via an Eikonal Solver

   Samuel F. Potter, Monte Hoover, Dmitry Zotkin, and 1 more author

   In 2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2023

2019

1. Machine Learning at Microsoft with ML.NET

   Zeeshan Ahmed, Saeed Amizadeh, Mikhail Bilenko, and 27 more authors

   In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019

   Abs

   Machine Learning is transitioning from an art and science into a technology available to every developer. In the near future, every application on every platform will incorporate trained models to encode data-based decisions that would be impossible for developers to author. This presents a significant engineering challenge, since currently data science and modeling are largely decoupled from standard software development processes. This separation makes incorporating machine learning capabilities inside applications unnecessarily costly and difficult, and furthermore discourage developers from embracing ML in first place. In this paper we present ML.NET, a framework developed at Microsoft over the last decade in response to the challenge of making it easy to ship machine learning models in large software applications. We present its architecture, and illuminate the application demands that shaped it. Specifically, we introduce DataView, the core data abstraction of ML.NET which allows it to capture full predictive pipelines efficiently and consistently across training and inference lifecycles. We close the paper with a surprisingly favorable performance study of ML.NET compared to more recent entrants, and a discussion of some lessons learned.