| license: apache-2.0 | |
| tags: [] | |
| tasks: | |
| - robotics | |
| ### Paper | |
| [Hugging Face Papers: 2610.02054](https://huggingface.co/papers/2610.02054) | |
| UniWAM is an 8B-parameter model that brings semantic understanding, visual prediction, and action generation into one MoT architecture. Its three experts exchange information through joint multimodal attention. During pretraining, physical-language supervision and complementary signals from robot, human egocentric, and VQA data build embodied knowledge. During post-training, future visual noise augmentation reduces reliance on precise future predictions, while encoded action history initializes action generation through flow matching. | |