Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Aaron Courville

Pretraining Representations for Data-Efficient Reinforcement Learning


Jun 09, 2021
Max Schwarzer, Nitarshan Rajkumar, Michael Noukhovitch, Ankesh Anand, Laurent Charlin, Devon Hjelm, Philip Bachman, Aaron Courville


  Access Paper or Ask Questions

Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?


Jun 05, 2021
Dinghuai Zhang, Kartik Ahuja, Yilun Xu, Yisen Wang, Aaron Courville

* Accepted to ICML2021 as long talk 

  Access Paper or Ask Questions

A Variational Perspective on Diffusion-Based Generative Models and Score Matching


Jun 05, 2021
Chin-Wei Huang, Jae Hyun Lim, Aaron Courville


  Access Paper or Ask Questions

Hierarchical Video Generation for Complex Data


Jun 04, 2021
Lluis Castrejon, Nicolas Ballas, Aaron Courville


  Access Paper or Ask Questions

Understanding by Understanding Not: Modeling Negation in Language Models


May 07, 2021
Arian Hosseini, Siva Reddy, Dzmitry Bahdanau, R Devon Hjelm, Alessandro Sordoni, Aaron Courville


  Access Paper or Ask Questions

Iterated learning for emergent systematicity in VQA


May 03, 2021
Ankit Vani, Max Schwarzer, Yuchen Lu, Eeshan Dhekane, Aaron Courville

* Published as a conference paper at ICLR 2021. 9 pages main, 21 pages total including references and appendix 

  Access Paper or Ask Questions

Touch-based Curiosity for Sparse-Reward Tasks


Apr 01, 2021
Sai Rajeswar, Cyril Ibrahim, Nitin Surya, Florian Golemo, David Vazquez, Aaron Courville, Pedro O. Pinheiro


  Access Paper or Ask Questions

Learning Task Decomposition with Ordered Memory Policy Network


Mar 19, 2021
Yuchen Lu, Yikang Shen, Siyuan Zhou, Aaron Courville, Joshua B. Tenenbaum, Chuang Gan


  Access Paper or Ask Questions

Continuous Coordination As a Realistic Scenario for Lifelong Learning


Mar 04, 2021
Hadi Nekoei, Akilesh Badrinaaraayanan, Aaron Courville, Sarath Chandar


  Access Paper or Ask Questions

Emergent Communication under Competition


Jan 25, 2021
Michael Noukhovitch, Travis LaCroix, Angeliki Lazaridou, Aaron Courville

* To be presented at AAMAS 2021 

  Access Paper or Ask Questions

StructFormer: Joint Unsupervised Induction of Dependency and Constituency Structure from Masked Language Modeling


Dec 15, 2020
Yikang Shen, Yi Tay, Che Zheng, Dara Bahri, Donald Metzler, Aaron Courville


  Access Paper or Ask Questions

Convex Potential Flows: Universal Probability Distributions with Optimal Transport and Convex Optimization


Dec 10, 2020
Chin-Wei Huang, Ricky T. Q. Chen, Christos Tsirigotis, Aaron Courville


  Access Paper or Ask Questions

Gradient Starvation: A Learning Proclivity in Neural Networks


Nov 23, 2020
Mohammad Pezeshki, Sékou-Oumar Kaba, Yoshua Bengio, Aaron Courville, Doina Precup, Guillaume Lajoie


  Access Paper or Ask Questions

Unsupervised Learning of Dense Visual Representations


Nov 11, 2020
Pedro O. Pinheiro, Amjad Almahairi, Ryan Y. Benmaleck, Florian Golemo, Aaron Courville


  Access Paper or Ask Questions

NU-GAN: High resolution neural upsampling with GAN


Oct 22, 2020
Rithesh Kumar, Kundan Kumar, Vicki Anand, Yoshua Bengio, Aaron Courville


  Access Paper or Ask Questions

Neural Approximate Sufficient Statistics for Implicit Models


Oct 20, 2020
Yanzhi Chen, Dinghuai Zhang, Michael Gutmann, Aaron Courville, Zhanxing Zhu


  Access Paper or Ask Questions

Recursive Top-Down Production for Sentence Generation with Latent Trees


Oct 09, 2020
Shawn Tan, Yikang Shen, Timothy J. O'Donnell, Alessandro Sordoni, Aaron Courville


  Access Paper or Ask Questions

Supervised Seeded Iterated Learning for Interactive Language Learning


Oct 06, 2020
Yuchen Lu, Soumye Singhal, Florian Strub, Olivier Pietquin, Aaron Courville


  Access Paper or Ask Questions

Integrating Categorical Semantics into Unsupervised Domain Translation


Oct 03, 2020
Samuel Lavoie-Marchildon, Faruk Ahmed, Aaron Courville

* 21 pages. In submission to the International Conference on Learning Representation (ICLR) 2021 

  Access Paper or Ask Questions

Data-Efficient Reinforcement Learning with Momentum Predictive Representations


Jul 12, 2020
Max Schwarzer, Ankesh Anand, Rishab Goel, R Devon Hjelm, Aaron Courville, Philip Bachman

* The first two authors contributed equally to this work 

  Access Paper or Ask Questions

Generative Graph Perturbations for Scene Graph Prediction


Jul 11, 2020
Boris Knyazev, Harm de Vries, Cătălina Cangea, Graham W. Taylor, Aaron Courville, Eugene Belilovsky

* https://oolworkshop.github.io/program/ool_21.html, ICML Workshop 2020 on "Object-Oriented Learning (OOL): Perception, Representation, and Reasoning" 

  Access Paper or Ask Questions

AR-DAE: Towards Unbiased Neural Entropy Gradient Estimation


Jun 09, 2020
Jae Hyun Lim, Aaron Courville, Christopher Pal, Chin-Wei Huang

* accepted in ICML 2020 

  Access Paper or Ask Questions

Graph Density-Aware Losses for Novel Compositions in Scene Graph Generation


May 17, 2020
Boris Knyazev, Harm de Vries, Cătălina Cangea, Graham W. Taylor, Aaron Courville, Eugene Belilovsky

* 17 pages, the code is available at https://github.com/bknyaz/sgg 

  Access Paper or Ask Questions

A Large-Scale, Open-Domain, Mixed-Interface Dialogue-Based ITS for STEM


May 06, 2020
Iulian Vlad Serban, Varun Gupta, Ekaterina Kochmar, Dung D. Vu, Robert Belfer, Joelle Pineau, Aaron Courville, Laurent Charlin, Yoshua Bengio

* 6 pages, 1 figure, 1 table, accepted for publication in the 21st International Conference on Artificial Intelligence in Education (AIED 2020) 

  Access Paper or Ask Questions

Pix2Shape: Towards Unsupervised Learning of 3D Scenes from Images using a View-based Representation


Apr 17, 2020
Sai Rajeswar, Fahim Mannan, Florian Golemo, Jérôme Parent-Lévesque, David Vazquez, Derek Nowrouzezahrai, Aaron Courville

* International Journal of Computer Vision, (2020), 1-16 
* This is a pre-print of an article published in International Journal of Computer Vision. The final authenticated version is available online at: https://doi.org/10.1007/s11263-020-01322-1 

  Access Paper or Ask Questions

Countering Language Drift with Seeded Iterated Learning


Apr 06, 2020
Yuchen Lu, Soumye Singhal, Florian Strub, Olivier Pietquin, Aaron Courville


  Access Paper or Ask Questions

Pix2Shape -- Towards Unsupervised Learning of 3D Scenes from Images using a View-based Representation


Mar 23, 2020
Sai Rajeswar, Fahim Mannan, Florian Golemo, Jérôme Parent-Lévesque, David Vazquez, Derek Nowrouzezahrai, Aaron Courville

* International Journal of Computer Vision, (2020), 1-16 
* This is a pre-print of an article published in International Journal of Computer Vision. The final authenticated version is available online at: https://doi.org/10.1007/s11263-020-01322-1 

  Access Paper or Ask Questions

Out-of-Distribution Generalization via Risk Extrapolation (REx)


Mar 13, 2020
David Krueger, Ethan Caballero, Joern-Henrik Jacobsen, Amy Zhang, Jonathan Binas, Remi Le Priol, Aaron Courville


  Access Paper or Ask Questions