ARTFEED — Contemporary Art Intelligence

DriftXpress: Faster Drifting Models via Projected RKHS Fields

ai-technology · 2026-07-27

DriftXpress is a new formulation of drifting models for one-step generative modeling, introduced in a paper on arXiv. It accelerates training by approximating the drifting kernel in a low-rank feature space using projected RKHS fields, preserving the attraction-repulsion structure while reducing field evaluation cost. The method achieves comparable FID scores to standard drifting on image-generation benchmarks while cutting wall-clock training time. This pushes the training-inference trade-off further, making drifting models more efficient without iterative inference.

Key facts

  • DriftXpress is an accelerated formulation of drifting models.
  • It uses projected RKHS fields to approximate the drifting kernel.
  • The method reduces the cost of field evaluation.
  • It preserves the attraction-repulsion structure of the original drifting field.
  • DriftXpress achieves comparable FID to standard drifting.
  • It reduces wall-clock training cost on image-generation benchmarks.
  • The paper is available on arXiv with ID 2605.12183.
  • Drifting models replace iterative denoising with a single generator evaluation.

Entities

Institutions

  • arXiv

Sources