Consider this scenario: an agent navigates a latent graph by performing
...
We propose schemas as a model for abstractions that can be used for rapi...
A central challenge in 3D scene perception via inverse graphics is robus...
Noisy-OR Bayesian Networks (BNs) are a family of probabilistic graphical...
While recent advances in artificial intelligence have achieved human-lev...
PGMax is an open-source Python package for easy specification of discret...
Visual servoing enables robotic systems to perform accurate closed-loop
...
Discrete undirected graphical models, also known as Markov Random Fields...
Perturb-and-MAP offers an elegant approach to approximately sample from ...
We consider the problem of learning the underlying graph of a sparse Isi...
Probabilistic graphical models (PGMs) provide a compact representation o...
For an intelligent agent to flexibly and efficiently operate in complex
...
We introduce a novel formulation for incorporating visual feedback in
co...
The ability of humans to quickly identify general concepts from a handfu...
Typical amortized inference in variational autoencoders is specialized f...
This paper is the preprint of an invited commentary on Lake et al's
Beha...
Variable order sequence modeling is an important problem in artificial a...
Humans can infer concepts from image pairs and apply those in the physic...
Understanding the information processing roles of cortical circuits is a...
The recent adaptation of deep neural network-based methods to reinforcem...
Convolutional neural networks (CNNs) have shown great success in compute...
We demonstrate that a generative model for object shapes can achieve sta...
Neural networks have shown to be a practical way of building a very comp...
We introduce the hierarchical compositional network (HCN), a directed
ge...