跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 28 天前AI 評分42

OSWAM:以單步動作生成實現高效世界動作模型

OSWAM: An Effective World Action Model with One-Step Action Generation

AI 導讀

OSWAM 是一種面向自動駕駛及具身控制的世界動作模型,只需一次擴散步驟即可生成高質素動作。實驗顯示,其表現媲美或優於需要數十步的 direct-policy WAM 和 Joint-WAM,速度約提升 3 倍。模型在 NVIDIA RTX 5090 GPU 上的推理延遲低至 40ms。

正文

Published on Oct 26

·

Submitted by

Guowen

on Nov 2

Authors:

,

,

,

,

,

Abstract

OSWAM enables real-time, high-quality action generation in autonomous driving and embodied control by initializing diffusion with structured imagination tokens and distilling future-conditioned privileged information into a single denoising step.

Direct-policy World Action Models (WAM) have demonstrated the benefits of decoupling action generation from explicit future visual prediction for efficient inference in autonomous driving and embodied control. However, they still require tens of denoising steps to achieve competitive action quality, incurring substantial latency and hindering real-time deployment. Simply reducing the number of denoising steps will collapse the nonlinear multi-step denoising trajectory into coarse updates, substantially degrading action quality. To reduce the denoising steps while enabling real-time action generation, we present an effective world action model with one-step action generation, namely OSWAM, for autonomous driving and embodied control. We argue that it is the absence of structured action priors in random noise initialization that forces direct-policy WAMs to recover coherent action sequences through iterative denoising. Hence, we construct imagination tokens to initialize the diffusion process, providing physical priors and action-conditioned representations. We further introduce privileged information distillation with future conditioning to enhance future-aware action generation. As a result, OSWAM can efficiently and effectively generate high quality actions in just one diffusion step. Our experiments demonstrate that OSWAM achieves comparable or even better results in both autonomous driving and embodied control than direct-policy WAM and Joint-WAM that require tens of steps. It obtains approximately 3times speedup over direct-policy WAM baselines and supports real-time compiled inference with latency as low as 40ms on an NVIDIA RTX 5090 GPU. The project page is available at https://gwenzhang.github.io/OSWAM/

View arXiv page View PDF Project page GitHub 20 Add to collection

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.35850 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.35850 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.35850 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co