Tag
The paper identifies persistent high-norm spatial outliers in World Action Model representations and introduces RegisterWAM, which adds learnable non-spatial registers paired with observation flow-matching loss supervision to reorganize action-relevant information, achieving 81.64% success on LIBERO-Plus and 93.0% on RoboTwin 2.0 without extra embodied pretraining data.
This paper explores the use of register tokens in pixel-space Diffusion Transformers (DiTs), finding they improve feature map quality despite DiTs lacking patch-token outliers. The authors propose Register Guidance, a technique to amplify register contributions for better visual structure.
A detailed reverse-engineering analysis of the Intel 386 processor's register circuitry, revealing six different custom circuits and interleaved bit storage.