research
∙
07/29/2023
A Theory for Emergence of Complex Skills in Language Models
A major driver of AI products today is the fact that new skills emerge i...
share
research
∙
06/03/2023
Cycle Consistency Driven Object Discovery
Developing deep learning models that effectively learn object-centric re...
research
∙
05/31/2023
Spotlight Attention: Robust Object-Centric Learning With a Spatial Locality Prior
The aim of object-centric vision is to construct an explicit representat...
research
∙
04/12/2023
DiscoGen: Learning to Discover Gene Regulatory Networks
Accurately inferring Gene Regulatory Networks (GRNs) is a critical and c...
research
∙
04/08/2023
TC-VAE: Uncovering Out-of-Distribution Data Generative Factors
Uncovering data generative factors is the ultimate goal of disentangleme...
research
∙
01/27/2023
Leveraging the Third Dimension in Contrastive Learning
Self-Supervised Learning (SSL) methods operate on unlabeled data to lear...
research
∙
12/28/2022
Representation Learning in Deep RL via Discrete Information Bottleneck
Several self-supervised representation learning methods have been propos...
research
∙
11/01/2022
Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning
Goal-conditioned reinforcement learning (RL) is a promising direction fo...
research
∙
10/24/2022
GFlowOut: Dropout with Generative Flow Networks
Bayesian Inference offers principled tools to tackle many critical probl...
research
∙
10/04/2022
Stateful active facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning
In cooperative multi-agent reinforcement learning, a team of agents work...
research
∙
07/22/2022
Discrete Key-Value Bottleneck
Deep neural networks perform well on prediction and classification tasks...
research
∙
06/09/2022
On the Generalization and Adaption Performance of Causal Models
Learning models that offer robust out-of-distribution generalization and...
research
∙
05/30/2022
Temporal Latent Bottleneck: Synthesis of Fast and Slow Processing Mechanisms in Sequence Learning
Recurrent neural networks have a strong inductive bias towards learning ...
research
∙
05/21/2022
Coordinating Policies Among Multiple Agents via an Intelligent Communication Channel
In Multi-Agent Reinforcement Learning (MARL), specialized channels are o...
research
∙
04/11/2022
Learning to Induce Causal Structure
The fundamental challenge in causal induction is to infer the underlying...
research
∙
03/21/2022
Generating Fast and Slow: Scene Decomposition via Reconstruction
We consider the problem of segmenting scenes into constituent entities, ...
research
∙
02/17/2022
Retrieval-Augmented Reinforcement Learning
Most deep reinforcement learning (RL) algorithms distill experience into...
research
∙
09/06/2021
Learning Neural Causal Models with Active Interventions
Discovering causal structures from data is a challenging inference probl...
research
∙
07/06/2021
Discrete-Valued Neural Communication
Deep learning has advanced from fully connected architectures to structu...
research
∙
07/02/2021
Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning
Inducing causal relationships from observations is a classic problem in ...
research
∙
06/14/2021
Variational Causal Networks: Approximate Bayesian Inference over Causal Structures
Learning the causal structure that underlies data is a crucial step towa...
research
∙
06/11/2021
Robust Representation Learning via Perceptual Similarity Metrics
A fundamental challenge in artificial intelligence is learning useful re...
research
∙
05/18/2021
Fast and Slow Learning of Recurrent Independent Mechanisms
Decomposing knowledge into interchangeable pieces promises a generalizat...
research
∙
03/02/2021
Neural Production Systems
Visual environments are structured, consisting of distinct objects or en...
research
∙
03/01/2021
Coordination Among Neural Modules Through a Shared Global Workspace
Deep learning has seen a movement away from representing examples with a...
research
∙
02/27/2021
Transformers with Competitive Ensembles of Independent Mechanisms
An important development in deep learning from the earliest MLPs has bee...
research
∙
02/22/2021
Towards Causal Representation Learning
The two fields of machine learning and graphical causality arose and dev...
research
∙
11/30/2020
Inductive Biases for Deep Learning of Higher-Level Cognition
A fascinating hypothesis is that human and animal intelligence could be ...
research
∙
10/08/2020
CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning
Despite recent successes of reinforcement learning (RL), it remains a ch...
research
∙
07/13/2020
S2RMs: Spatially Structured Recurrent Modules
Capturing the structure of a data-generating process by means of appropr...
research
∙
06/30/2020
Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules
Robust perception relies on both bottom-up and top-down signals. Bottom-...
research
∙
06/30/2020
Maximum Entropy Models for Fast Adaptation
Deep Neural Networks have shown great promise on a variety of downstream...
research
∙
06/29/2020
Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems
Modeling a structured, dynamic environment like a video game requires ke...
research
∙
06/16/2020
Untangling tradeoffs between recurrence and self-attention in neural networks
Attention and self-attention mechanisms, inspired by cognitive processes...
research
∙
06/14/2020
Is Independence all you need? On the Generalization of Representations Learned from Correlated Data
Despite impressive progress in the last decade, it still remains an open...
research
∙
04/24/2020
The Variational Bandwidth Bottleneck: Stochastic Evaluation on an Information Budget
In many applications, it is desirable to extract only the relevant infor...
research
∙
03/10/2020
DIBS: Diversity inducing Information Bottleneck in Model Ensembles
Although deep learning models have achieved state-of-the-art performance...
research
∙
02/14/2020
Top-K Training of GANs: Improving Generators by Making Critics Less Critical
We introduce a simple (one line of code) modification to the Generative ...
research
∙
10/29/2019
Small-GAN: Speeding Up GAN Training Using Core-sets
Recent work by Brock et al. (2018) suggests that Generative Adversarial ...
research
∙
10/02/2019
Learning Neural Causal Models from Unknown Interventions
Meta-learning over a set of distributions can be interpreted as learning...
research
∙
09/24/2019
Recurrent Independent Mechanisms
Learning modular structures which reflect the dynamics of the environmen...
research
∙
07/02/2019
Learning the Arrow of Time
We humans seem to have an innate understanding of the asymmetric progres...
research
∙
06/25/2019
Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives
Reinforcement learning agents that operate in diverse and complex enviro...
research
∙
06/11/2019
Learning Powerful Policies by Using Consistent Dynamics Model
Model-based Reinforcement Learning approaches have the promise of being ...
research
∙
05/26/2019
State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations
Machine learning promises methods that generalize well from finite label...
research
∙
03/05/2019
Learning Dynamics Model in Reinforcement Learning by Incorporating the Long Term Future
In model-based reinforcement learning, the agent interleaves between mod...
research
∙
02/16/2019
Communication Topologies Between Learning Agents in Deep Reinforcement Learning
A common technique to improve speed and robustness of learning in deep r...
research
∙
01/30/2019
A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
We propose to meta-learn causal structures based on how fast a learner a...
research
∙
01/30/2019
InfoBot: Transfer and Exploration via the Information Bottleneck
A central challenge in reinforcement learning is discovering effective p...
research
∙
01/24/2019