London Lowmanstone

Harvard University Press, University of Minnesota, Harvard University

Papers

Total Citations

H-Index

About

London Lowmanstone is a leading researcher at the intersection of human-computer interaction, programming languages, and robotics, with a focus on making complex systems more accessible and intelligent. Their most impactful work, "Interactive Program Synthesis by Augmented Examples" (2020, 54 citations), tackles a core challenge in programming-by-example (PBE): resolving ambiguity in user-provided examples. By introducing a novel interaction model, Lowmanstone enables more precise and user-friendly code generation, directly advancing tools for end-user programming and human-robot collaboration. In robotics, Lowmanstone has made foundational contributions to swarm intelligence. Their paper "Demystifying Emergent Intelligence and Its Effect on Performance In Large Robot Swarms" (2020, 8 citations) introduces STOCH-N1, a stochastic allocation model that quantifies emergent intelligence from self-organized task allocation, offering a rigorous framework for understanding how simple agents produce complex collective behaviors. Additionally, their work on "Communication-Restricted Exploration for Search Teams" (2018, 20 citations) addresses critical constraints in multi-agent systems. Through these contributions, Lowmanstone has shaped how researchers design interactive, intelligent systems that bridge human intent and machine execution, with lasting impact on both theory and practical tool-building.