Understanding relations between objects is crucial for understanding the...
Deep reinforcement learning agents need to be trained over millions of
e...
State-of-the-art visual grounding models can achieve high detection accu...
While VideoQA Transformer models demonstrate competitive performance on
...
This paper presents a framework for training an agent to actively reques...
Federated Reinforcement Learning (FedRL) encourages distributed agents t...
Abductive reasoning aims to make the most likely inference for a given s...
Humans with an average level of social cognition can infer the beliefs o...
In reality, it is often more efficient to ask for help than to search th...
Children's cognitive abilities are sometimes cited as AI benchmarks. How...
Research in cognitive science has provided extensive evidence on human
c...
Attention modules for Convolutional Neural Networks (CNNs) are an effect...
Recent work in computer vision and cognitive reasoning has given rise to...
The growing literature of Federated Learning (FL) has recently inspired
...
Recent work in cognitive reasoning and computer vision has engendered an...
To align advanced artificial intelligence (AI) with human values and pro...
Recent advancements in deep learning, computer vision, and embodied AI h...
Navigation to multiple cued reward locations has been increasingly used ...
One-shot learning can be achieved by algorithms and animals, but how the...
There has been an emerging paradigm shift from the era of "internet AI" ...
The problem of task planning for artificial agents remains largely unsol...
6D object pose estimation is widely applied in robotic tasks such as gra...
Socially-intelligent agents are of growing interest in artificial
intell...
In i-theory a typical layer of a hierarchical architecture consists of H...
Faces are a class of visual stimuli with unique significance, for a vari...