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

• URL: http://arxiv.org/abs/2506.01121v1
• Date: Sun, 01 Jun 2025 18:58:59 GMT
• Title: Neuro-Symbolic Generative Diffusion Models for Physically Grounded, Robust, and Safe Generation
• Authors: Jacob K. Christopher, Michael Cardei, Jinhao Liang, Ferdinando Fioretto,
• Abstract summary: Neuro-Symbolic Diffusion (NSD) is a novel framework that interleaves diffusion steps with symbolic optimization.<n>This paper introduces NSD, enabling the generation of certifiably consistent samples under user-defined functional and logic constraints.<n>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.
• Score: 44.80048928651511
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Neural Proposals, Symbolic Guarantees: Neuro-Symbolic Graph Generation with Hard Constraints [11.61618152472216]
  We introduce Neuro-Symbolic Graph Generative Modeling (NSGGM), a neurosymbolic framework that reapproaches molecule generation as a scaffold and interaction learning task with symbolic assembly.<n>An autoregressive neural model proposes scaffolds and refines interaction signals, and a CPU-efficient SMT solver constructs full graphs while enforcing chemical validity, structural rules, and user-specific constraints.<n>NSGGM delivers strong performance on both unconstrained generation and constrained generation tasks, demonstrating that neuro-symbolic modeling can match state-of-the-art generative performance while offering explicit controllability and guarantees.
  arXiv  Detail & Related papers  (2026-02-18T23:37:15Z)
• Strictly Constrained Generative Modeling via Split Augmented Langevin Sampling [0.1052166918701117]
  We develop a principled framework for sampling from a target distribution while rigorously satisfying physical constraints.<n>We propose Split Augmented Langevin (SAL), a novel primal-dual sampling algorithm that enforces constraints progressively through variable splitting, with convergence guarantees.<n>We apply our method to diffusion-based data assimilation on a complex physical system, where enforcing physical constraints substantially improves both forecast accuracy and the preservation of critical conserved quantities.
  arXiv  Detail & Related papers  (2025-05-23T15:21:10Z)
• Constrained Discrete Diffusion [61.81569616239755]
  This paper introduces Constrained Discrete Diffusion (CDD), a novel integration of differentiable constraint optimization within the diffusion process.<n>CDD directly imposes constraints into the discrete diffusion sampling process, resulting in a training-free and effective approach.
  arXiv  Detail & Related papers  (2025-03-12T19:48:12Z)
• UniGenX: Unified Generation of Sequence and Structure with Autoregressive Diffusion [61.690978792873196]
  Existing approaches rely on either autoregressive sequence models or diffusion models.<n>We propose UniGenX, a unified framework that combines autoregressive next-token prediction with conditional diffusion models.<n>We validate the effectiveness of UniGenX on material and small molecule generation tasks.
  arXiv  Detail & Related papers  (2025-03-09T16:43:07Z)
• Training-Free Constrained Generation With Stable Diffusion Models [45.138721047543214]
  We propose a novel approach to integrate stable diffusion models with constrained optimization frameworks.<n>We demonstrate the effectiveness of this approach through material science experiments requiring adherence to precise morphometric properties.
  arXiv  Detail & Related papers  (2025-02-08T16:11:17Z)
• Derivative-Free Diffusion Manifold-Constrained Gradient for Unified XAI [59.96044730204345]
  We introduce Derivative-Free Diffusion Manifold-Constrainted Gradients (FreeMCG)<n>FreeMCG serves as an improved basis for explainability of a given neural network.<n>We show that our method yields state-of-the-art results while preserving the essential properties expected of XAI tools.
  arXiv  Detail & Related papers  (2024-11-22T11:15:14Z)
• Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design [56.957070405026194]
  We propose an algorithm that enables direct backpropagation of rewards through entire trajectories generated by diffusion models.<n>DRAKES can generate sequences that are both natural-like and yield high rewards.
  arXiv  Detail & Related papers  (2024-10-17T15:10:13Z)
• Chemistry-Inspired Diffusion with Non-Differentiable Guidance [10.573577157257564]
  Recent advances in diffusion models have shown remarkable potential in the conditional generation of novel molecules.<n>We propose a novel approach that leverage domain knowledge from quantum chemistry as a non-differentiable oracle to guide an unconditional diffusion model.<n>Instead of relying on neural networks, the oracle provides accurate guidance in the form of estimated gradients, allowing the diffusion process to sample from a conditional distribution specified by quantum chemistry.
  arXiv  Detail & Related papers  (2024-10-09T03:10:21Z)
• Constrained Synthesis with Projected Diffusion Models [47.56192362295252]
  This paper introduces an approach to generative diffusion processes the ability to satisfy and certify compliance with constraints and physical principles. The proposed method recast the traditional process of generative diffusion as a constrained distribution problem to ensure adherence to constraints.
  arXiv  Detail & Related papers  (2024-02-05T22:18:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.