4 papers
Differentiate the Evaluator, Not the Program: An Efficient Runtime Representation for Neuro-Symbolic Learning
Lucas Sheneman
AI systems increasingly propose executable scientific models whose value depends on both their symbolic structure and their fitted continuous parameters. This makes parameter calib…
Compile Once, Differentiate Everywhere: A Differentiable Meta-Circular Interpreter
Lucas Sheneman
The boundary between program execution and gradient-based optimization has long limited the use of code itself as a learnable scientific model. We present a compiler that translate…
The Neural Compiler: Program-to-Network Translation for Hybrid Scientific Machine Learning
Lucas Sheneman
Scientific machine learning often requires combining known physics with unknown parameters or correction terms learned from data. Existing approaches either ignore known structure,…
TaMPERing with Large Language Models: A Field Guide for using Generative AI in Public Administration Research
Michael Overton, Barrie Robison, Lucas Sheneman
The integration of Large Language Models (LLMs) into social science research presents transformative opportunities for advancing scientific inquiry, particularly in public administ…