研究人员开发了新的世界动作模型（WAMs），它们在视觉分布变化下提高了泛化能力。第一个模型CSWAM集成了基于V-JEPA 2.1构建的因果语义专家，以更好地表示语义状态变化和运动，显著提高了真实机器人实验的成功率。第二个模型ModAR自回归地去除了RGB之外的多种未来模态的噪声，例如深度图和点轨迹，展示了在训练FLOPs显著减少且无需预训练的情况下性能更优。 AI
影响 世界动作模型的这些进步可能带来更强大、更高效的AI系统，使其能够在多样化和不可预测的环境中运行。
排序理由 两篇研究论文介绍了具有改进泛化能力的新型世界动作模型。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2609.19441v1 Announce Type: cross Abstract: World action models (WAMs) rely on video-generation backbones, requiring substantial memory and compute for deployment. Post-training quantization reduces memory and can accelerate inference, but bit width, grouping, and quantizer…
arXiv:2609.18462v1 Announce Type: cross Abstract: FastWAM-style world action models enable efficient action-only inference, but generalize poorly under visual distribution shifts. Their reconstruction-oriented representations emphasize appearance-specific details, limiting genera…
World-action models (WAMs) jointly model future observations and actions, typically predicting the future as RGB images. Other visual modalities such as depth, pretrained visual features, and point tracks can more efficiently capture geometric, semantic, and motion features. Howe…