ResWAM: Learning What Changes, Not What Stays, for World-Action Models

媒体报道 Hugging Face Papers 原文语言:中文

论文摘要(作者报告,未经本站复测):World-action models (WAMs) augment vision-language-action policies (VLAs) with future prediction so that the policy can anticipate how its actions will affect the physical world.

全文

ResWAM combines visual residual learning in frozen DINOv3 features with a lightweight dual-branch DiT trained via conditional flow matching to improve vision-language-action policy success while lowering training and inference compute.

正文以来源语言显示。

参考来源

← 返回每日AI报告