Neuro-Symbolic Generative Diffusion Models for Physically Grounded, Robust, and Safe Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Christopher, Jacob K., Cardei, Michael, Liang, Jinhao, Fioretto, Ferdinando
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910979969777664
author Christopher, Jacob K.
Cardei, Michael
Liang, Jinhao
Fioretto, Ferdinando
author_facet Christopher, Jacob K.
Cardei, Michael
Liang, Jinhao
Fioretto, Ferdinando
contents Despite the remarkable generative capabilities of diffusion models, their integration into safety-critical or scientifically rigorous applications remains hindered by the need to ensure compliance with stringent physical, structural, and operational constraints. To address this challenge, this paper introduces Neuro-Symbolic Diffusion (NSD), a novel framework that interleaves diffusion steps with symbolic optimization, enabling the generation of certifiably consistent samples under user-defined functional and logic constraints. This key feature is provided for both standard and discrete diffusion models, enabling, for the first time, the generation of both continuous (e.g., images and trajectories) and discrete (e.g., molecular structures and natural language) outputs that comply with constraints. This ability is demonstrated on tasks spanning three key challenges: (1) Safety, in the context of non-toxic molecular generation and collision-free trajectory optimization; (2) Data scarcity, in domains such as drug discovery and materials engineering; and (3) Out-of-domain generalization, where enforcing symbolic constraints allows adaptation beyond the training distribution.
format Preprint
id arxiv_https___arxiv_org_abs_2506_01121
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neuro-Symbolic Generative Diffusion Models for Physically Grounded, Robust, and Safe Generation
Christopher, Jacob K.
Cardei, Michael
Liang, Jinhao
Fioretto, Ferdinando
Machine Learning
Artificial Intelligence
Despite the remarkable generative capabilities of diffusion models, their integration into safety-critical or scientifically rigorous applications remains hindered by the need to ensure compliance with stringent physical, structural, and operational constraints. To address this challenge, this paper introduces Neuro-Symbolic Diffusion (NSD), a novel framework that interleaves diffusion steps with symbolic optimization, enabling the generation of certifiably consistent samples under user-defined functional and logic constraints. This key feature is provided for both standard and discrete diffusion models, enabling, for the first time, the generation of both continuous (e.g., images and trajectories) and discrete (e.g., molecular structures and natural language) outputs that comply with constraints. This ability is demonstrated on tasks spanning three key challenges: (1) Safety, in the context of non-toxic molecular generation and collision-free trajectory optimization; (2) Data scarcity, in domains such as drug discovery and materials engineering; and (3) Out-of-domain generalization, where enforcing symbolic constraints allows adaptation beyond the training distribution.
title Neuro-Symbolic Generative Diffusion Models for Physically Grounded, Robust, and Safe Generation
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2506.01121