David Kanter
David is the Founder and Head of MLPerf at MLCommons, where he leads efforts to standardize machine learning benchmarks and create tools for data-centric AI. Previously, as Executive Director of MLCommons, he collaborated with industry leaders to drive innovation in ML benchmarking and datasets. With over two decades as President of Real World Insights, David has advised top tech companies like Intel, Nvidia, and Microsoft on IP strategies and performance analysis. A University of Chicago graduate with honors in Mathematics and Economics, he specializes in AI benchmarking, semiconductor economics, and scalable tech solutions
Speaker Sessions
[Panel] Choosing the Right Approach: When to Use Long Context Windows, Fine-Tuning, or Retrieval-Augmented Generation
In this panel, industry experts discuss how developers can choose the right AI technique by comparing long context windows, fine tuning, and retrieval augmented generation based on their project needs. Speakers will cover real world factors such as cost, speed, and accuracy, while highlighting best practices for integrating each approach into existing workflows. Attendees will gain a practical understanding of when to rely on a larger context window, how to tailor models with fine tuning, and ways to incorporate external knowledge through retrieval. The goal is to provide actionable guidance for maximizing AI’s impact without compromising quality or performance.
