ResWAM:为世界-动作模型学习什么在变化,而非什么保持不变

Media reports Hugging Face Papers Source language: Chinese

论文摘要(作者报告,未经本站复测):世界-动作模型(WAM)通过未来预测来增强视觉-语言-动作策略(VLA),使策略能够预判其动作将如何影响物理世界。

Full text

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.

Sources

← Back to Daily AI Report