让生成模型在复杂约束区域中保持真实感地生成样本。
Improved Constrained Generation by Bridging Pretrained Generative Models
- 微调预训练生成模型，直接在约束区域内采样
- 在满足约束的同时保持生成质量，优于现有方法
- 适合机器人控制、自动驾驶等需安全约束的场景
受限生成建模在机器人控制和自动驾驶等应用中至关重要，要求模型遵守物理规律与安全约束。现实中，这些约束往往不是简单的线性不等式，而是类似道路地图的复杂可行区域。本文提出一种受限生成框架，使生成样本直接位于此类可行区域内，同时保持生成的真实性。通过微调预训练生成模型，在不破坏生成保真度的前提下强制执行约束。实验表明，该方法在约束满足度与采样质量之间展现出与现有微调及无训练基线不同的特性，揭示了一种新的权衡关系。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。