A major driver of AI products today is the fact that new skills emerge i...
Developing deep learning models that effectively learn object-centric
re...
The aim of object-centric vision is to construct an explicit representat...
Accurately inferring Gene Regulatory Networks (GRNs) is a critical and
c...
Uncovering data generative factors is the ultimate goal of disentangleme...
Self-Supervised Learning (SSL) methods operate on unlabeled data to lear...
Several self-supervised representation learning methods have been propos...
Goal-conditioned reinforcement learning (RL) is a promising direction fo...
Bayesian Inference offers principled tools to tackle many critical probl...
In cooperative multi-agent reinforcement learning, a team of agents work...
Deep neural networks perform well on prediction and classification tasks...
Learning models that offer robust out-of-distribution generalization and...
Recurrent neural networks have a strong inductive bias towards learning
...
In Multi-Agent Reinforcement Learning (MARL), specialized channels are o...
The fundamental challenge in causal induction is to infer the underlying...
We consider the problem of segmenting scenes into constituent entities, ...
Most deep reinforcement learning (RL) algorithms distill experience into...
Discovering causal structures from data is a challenging inference probl...
Deep learning has advanced from fully connected architectures to structu...
Inducing causal relationships from observations is a classic problem in
...
Learning the causal structure that underlies data is a crucial step towa...
A fundamental challenge in artificial intelligence is learning useful
re...
Decomposing knowledge into interchangeable pieces promises a generalizat...
Visual environments are structured, consisting of distinct objects or
en...
Deep learning has seen a movement away from representing examples with a...
An important development in deep learning from the earliest MLPs has bee...
The two fields of machine learning and graphical causality arose and
dev...
A fascinating hypothesis is that human and animal intelligence could be
...
Despite recent successes of reinforcement learning (RL), it remains a
ch...
Capturing the structure of a data-generating process by means of appropr...
Robust perception relies on both bottom-up and top-down signals. Bottom-...
Deep Neural Networks have shown great promise on a variety of downstream...
Modeling a structured, dynamic environment like a video game requires ke...
Attention and self-attention mechanisms, inspired by cognitive processes...
Despite impressive progress in the last decade, it still remains an open...
In many applications, it is desirable to extract only the relevant
infor...
Although deep learning models have achieved state-of-the-art performance...
We introduce a simple (one line of code) modification to the Generative
...
Recent work by Brock et al. (2018) suggests that Generative Adversarial
...
Meta-learning over a set of distributions can be interpreted as learning...
Learning modular structures which reflect the dynamics of the environmen...
We humans seem to have an innate understanding of the asymmetric progres...
Reinforcement learning agents that operate in diverse and complex
enviro...
Model-based Reinforcement Learning approaches have the promise of being
...
Machine learning promises methods that generalize well from finite label...
In model-based reinforcement learning, the agent interleaves between mod...
A common technique to improve speed and robustness of learning in deep
r...
We propose to meta-learn causal structures based on how fast a learner a...
A central challenge in reinforcement learning is discovering effective
p...
Unsupervised learning is about capturing dependencies between variables ...