SOURCE-LINKED INTELLIGENCE

ParetoTransport: Generative Optimization by Mass Transport Toward The Pareto Front

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Offline multi-objective optimization requires not only moving the objective vectors of candidate designs toward the Pareto front, but also distributing them effectively along it. Generative methods have recently emerged as a natural approach because they learn a distribution over feasible designs while allowing generation to be steered toward promising designs. Existing methods, however, largely retain classical sample-wise guidance strategies, leaving the distribution-level modeling capability of generative methods underused. We propose ParetoTransport, a training-free guidance method for pre

Read original source ↗ Open in workspace

recordType

paper

region

Global