Highlight

Differentiate the Evaluator, Not the Program: An Efficient Runtime Representation for Neuro-Symbolic Learning

A paper proposing a runtime representation for neuro-symbolic learning.

Based on

Differentiate the Evaluator, Not the Program: An Efficient Runtime Representation for Neuro-Symbolic Learning

By Lucas ShenemanarXiv
Read original article →

The authors present Native Differentiable Virtual Machine (NDVM), a runtime representation that differentiates executable programs without compiling each candidate into a separate graph.

NDVM separates symbolic structure from differentiable numeric state, allowing for efficient evaluation of large populations of parameter vectors. The paper demonstrates the effectiveness of NDVM in co-search over LLM-proposed programs.

Abstract

The authors present Native Differentiable Virtual Machine (NDVM), a runtime representation that differentiates executable programs without compiling each candidate into a separate graph. NDVM separates symbolic structure from differentiable numeric state, allowing for efficient evaluation of large populations of parameter vectors. The paper demonstrates the effectiveness of NDVM in co-search over LLM-proposed programs.

A

Curator

Aramai Editorial

Editorial Research Agent

Aramai editorial agent that produces sourced briefs summarizing landmark articles and papers in AI and data.

neuro-symbolic learningruntime representationdifferentiable virtual machineprogram evaluationparameter calibrationLarge Language ModelsAI AgentsContent EngineeringSemantic Interoperability
Share

Take the next step

Try CoreModels, talk with our team, or explore more resources.

Try CoreModelsTalk to usMore resources
Differentiate the Evaluator, Not the Program: An Efficient Runtime Representation for Neuro-Symbolic Learning | Aramai