SOURCE-LINKED INTELLIGENCE

One-Step Generative Surrogate Models via Block-Triangular Joint Drifting

arXiv · AI, language, vision and robotics · article · Sep 22, 2026 · UTC

Drifting provides a direct route to one-step generative models, but applying it directly to stochastic transition modeling requires multiple samples of the next state conditioned on the same current state. Standard trajectory data, however, typically provide only one realized next state for each observed current state and therefore do not provide an empirical approximation of the corresponding conditional distribution over possible next states. We introduce block-triangular joint drifting, which instead applies a projected drift field to the empirically accessible joint distribution of consecu

Read original source ↗ Open in workspace

recordType

paper

region

Global