Improved Constrained Generation by Bridging Pretrained Generative Models

2026-03-06

AI Summary

This work addresses the challenge of enforcing complex nonlinear constraints—such as road-legal regions in robotic control and autonomous driving—within generative models, where existing approaches often fail to simultaneously ensure constraint satisfaction and high-fidelity generation. The authors propose a constrained fine-tuning framework that leverages pre-trained generative models to produce outputs strictly confined within structured feasible regions, without compromising sample realism. By overcoming the limitations of conventional fine-tuning or training-free strategies, the method achieves superior performance across diverse and intricate constraint scenarios, consistently outperforming current baselines in both generation quality and adherence to constraints.

Technology Category

• Natural Language Processing: Generation
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Constrained generative modeling is fundamental to applications such as robotic control and autonomous driving, where models must respect physical laws and safety-critical constraints. In real-world settings, these constraints rarely take the form of simple linear inequalities, but instead complex feasible regions that resemble road maps or other structured spatial domains. We propose a constrained generation framework that generates samples directly within such feasible regions while preserving realism. Our method fine-tunes a pretrained generative model to enforce constraints while maintaining generative fidelity. Experimentally, our method exhibits characteristics distinct from existing fine-tuning and training-free constrained baselines, revealing a new compromise between constraint satisfaction and sampling quality.

Problem

• constrained generation
• pretrained generative models
• feasible regions
• safety-critical constraints
• structured spatial domains

Innovation

• constrained generation
• pretrained generative models
• feasible regions
• fine-tuning
• generative fidelity