Neuro-Symbolic Execution of Generic Source Code
Can a Python program be executed statement-by-statement by neural networks composed according to the source code? We formulate the Neuro-Symbolic Execution Problem and introduce Neural Interpretation (NI), the first neural model for the execution of generic source code that allows missing definitions. NI preserves source code structure, where every variable has a vector encoding, and every function executes a neural network. NI is a novel neural model of computers with a compiler architecture that can assemble neural layers "programmed" by source code. NI is the first neural model capable of executing Py150 dataset programs, including library functions without concrete inputs, and it can be trained with flexible code understanding objectives. We demonstrate white-box execution without concrete inputs for variable misuse localization and repair.
Code (0)
등록된 구현이 없습니다.
Tasks
Variable misuseMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
NEUROSYMLAND: Neuro-Symbolic Landing-Site Assessment for Robust and Edge-Deployable UAV Autonomy
Safe landing-site assessment in unstructured environments remains a key challenge for autonomous UAV deployment, as vision-only learning approaches often degrade under terrain variability and provide limited transparency…
Safe Neurosymbolic Learning with Differentiable Symbolic Execution
We study the problem of learning worst-case-safe parameters for programs that use neural networks as well as symbolic, human-written code. Such neurosymbolic programs arise in many safety-critical domains. However, becau…
Neuro-Symbolic Decoding of Neural Activity
We propose NEURONA, a neuro-symbolic framework for fMRI decoding and concept grounding in neural activity. Leveraging image- and video-based fMRI question-answering datasets, NEURONA learns to decode interacting concepts…
NEUROSPF: A tool for the Symbolic Analysis of Neural Networks
This paper presents NEUROSPF, a tool for the symbolic analysis of neural networks. Given a trained neural network model, the tool extracts the architecture and model parameters and translates them into a Java representat…
PathfinderBioProAgent: Neuro-Symbolic Grounding for Constrained Scientific Planning
Large language models (LLMs) have demonstrated significant reasoning capabilities in scientific discovery but struggle to bridge the gap to physical execution in wet-labs. In these irreversible environments, probabilisti…