SOURCE-LINKED INTELLIGENCE

Beyond Future Prediction: Denoising as Generative Adaptation for Robot Control

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

Pretrained generative Diffusion Transformers (DiTs) capture rich pixel-level visual and language-conditioned structure through large-scale image and video generation training. A growing line of robot policies builds on this generative prior, but how it should be transferred to control remains unclear, and existing approaches commonly instantiate this transfer through future visual prediction. We ask a more basic question: what a pretrained generative DiT actually contributes to action learning, and how this prior should be adapted for control. We introduce NowWAM, a future-target-free co-train

Read original source ↗ Open in workspace

recordType

paper

region

Global