**Modality-Autoregressive World-Action Models**

> 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. However, how best to combine these modalities within WAMs remains an open question. We introduce ModAR, the first WAM to autoregressively denois...

**来源信息**
- **来源**：HuggingFace Daily Papers（社区热门论文）
- **分类**：ai-models
- **发布时间**：2026-09-16 08:00（北京时间）
- **原文**：[打开原文](https://huggingface.co/papers/2609.17524)