Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
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…
cs.LG2026
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,…