COMPAS: Compose Actions and Slots in Object-Centric World Models
In this paper, we propose a novel approach, <b>COMPAS</b> (<b>COMP</b>ose <b>A</b>ctions and <b>S</b>lots), which leverages the strengths of state-of-the-art object-centric approaches for modeling the dynamics of an environment. Our method encodes the environment’s state into symbol-like, object-cen...
Сохранить в:
| Главные авторы: | , , , , |
|---|---|
| Формат: | Artigo |
| Язык: | Inglês |
| Опубликовано: |
MDPI AG
2026-04-01
|
| Серии: | Machine Learning and Knowledge Extraction |
| Предметы: | |
| Online-ссылка: | https://www.mdpi.com/2504-4990/8/5/117 |
| Метки: |
Нет меток, Требуется 1-ая метка записи!
|