English

Improved Constrained Generation by Bridging Pretrained Generative Models

Machine Learning 2026-03-10 v1 Artificial Intelligence Robotics

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.

Keywords

Cite

@article{arxiv.2603.06742,
  title  = {Improved Constrained Generation by Bridging Pretrained Generative Models},
  author = {Xiaoxuan Liang and Saeid Naderiparizi and Yunpeng Liu and Berend Zwartsenberg and Frank Wood},
  journal= {arXiv preprint arXiv:2603.06742},
  year   = {2026}
}
R2 v1 2026-07-01T11:07:46.627Z