Evaluating Visual Dialogue, the task of answering a sequence of question...
Miscalibration – a mismatch between a model's confidence and its correct...
Standard adversarial training involves two agents, namely a generator an...
This paper describes an intuitive generalization to the Generative
Adver...
Communicating and sharing intelligence among agents is an important face...
Understanding, predicting, and generating object motions and transformat...