World models are a fundamental component in model-based reinforcement
le...
Transformations based on domain expertise (expert transformations), such...
Despite remarkable recent advances, making object-centric learning work ...
Existing learning-based multi-view stereo (MVS) methods rely on the dept...
The panorama image can simultaneously demonstrate complete information o...
Top-performing Model-Based Reinforcement Learning (MBRL) agents, such as...
A crucial ability of human intelligence is to build up models of individ...
The ability to decompose complex multi-object scenes into meaningful
abs...
Indoor robotics localization, navigation and interaction heavily rely on...
Compositional structures between parts and objects are inherent in natur...
We present a set of fault injection experiments performed on the ACES
(L...
There has been a gap between artificial intelligence and human intellige...