Robotics affordances, providing information about what actions can be ta...
Identifying the causal variables of an environment and how to intervene ...
Problems involving geometric data arise in a variety of fields, includin...
Embodied agents operate in a structured world, often solving tasks with
...
The expressive power of Graph Neural Networks (GNNs) has been studied
ex...
Standard imitation learning can fail when the expert demonstrators have
...
Equivariant networks capture the inductive bias about the symmetry of th...
There exist well-developed frameworks for causal modelling, but these re...
Causal representation learning is the task of identifying the underlying...
Equivariance to symmetries has proven to be a powerful inductive bias in...
Learning high-level causal representations together with a causal model ...
Understanding the latent causal factors of a dynamical system from visua...
We propose a method to compress full-resolution video sequences with imp...
Learning the structure of a causal graphical model using both observatio...
The last decade has witnessed an experimental revolution in data science...
Rate-Distortion Optimized Quantization (RDOQ) has played an important ro...
Conventional neural message passing algorithms are invariant under
permu...
In this paper, we present a novel adversarial lossy video compression mo...
A common approach to define convolutions on meshes is to interpret them ...
Group equivariant convolutional neural networks (G-CNNs) have recently
e...
We present a convolutional network that is equivariant to rigid body mot...
We propose a new model for digital pathology segmentation, based on the
...
We propose Teacher-Student Curriculum Learning (TSCL), a framework for
a...