Laurent Charlin

University of Toronto

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 Model/Code and Paper
IG-RL: Inductive Graph Reinforcement Learning for Massive-Scale Traffic Signal Control

Mar 19, 2020
François-Xavier Devailly, Denis Larocque, Laurent Charlin

* 11 pages, 9 figures, 1 table 

  Access Model/Code and Paper
Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning

Mar 12, 2020
Massimo Caccia, Pau Rodriguez, Oleksiy Ostapenko, Fabrice Normandin, Min Lin, Lucas Caccia, Issam Laradji, Irina Rish, Alexande Lacoste, David Vazquez, Laurent Charlin


  Access Model/Code and Paper
Online Continual Learning with Maximally Interfered Retrieval

Aug 23, 2019
Rahaf Aljundi, Lucas Caccia, Eugene Belilovsky, Massimo Caccia, Min Lin, Laurent Charlin, Tinne Tuytelaars


  Access Model/Code and Paper
Exact Combinatorial Optimization with Graph Convolutional Neural Networks

Jun 07, 2019
Maxime Gasse, Didier Chételat, Nicola Ferroni, Laurent Charlin, Andrea Lodi


  Access Model/Code and Paper
Continual Learning of New Sound Classes using Generative Replay

Jun 03, 2019
Zhepei Wang, Cem Subakan, Efthymios Tzinis, Paris Smaragdis, Laurent Charlin


  Access Model/Code and Paper
Towards Deep Conversational Recommendations

Dec 18, 2018
Raymond Li, Samira Kahou, Hannes Schulz, Vincent Michalski, Laurent Charlin, Chris Pal

* 17 pages, 5 figures, Accepted at 32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Montr\'eal, Canada 

  Access Model/Code and Paper
Language GANs Falling Short

Nov 08, 2018
Massimo Caccia, Lucas Caccia, William Fedus, Hugo Larochelle, Joelle Pineau, Laurent Charlin


  Access Model/Code and Paper
The Deconfounded Recommender: A Causal Inference Approach to Recommendation

Aug 20, 2018
Yixin Wang, Dawen Liang, Laurent Charlin, David M. Blei

* 14 pages, 3 figures 

  Access Model/Code and Paper
Focused Hierarchical RNNs for Conditional Sequence Processing

Jun 12, 2018
Nan Rosemary Ke, Konrad Zolna, Alessandro Sordoni, Zhouhan Lin, Adam Trischler, Yoshua Bengio, Joelle Pineau, Laurent Charlin, Chris Pal

* To appear at ICML 2018 

  Access Model/Code and Paper
Sparse Attentive Backtracking: Long-Range Credit Assignment in Recurrent Networks

Nov 07, 2017
Nan Rosemary Ke, Anirudh Goyal, Olexa Bilaniuk, Jonathan Binas, Laurent Charlin, Chris Pal, Yoshua Bengio


  Access Model/Code and Paper
Learnable Explicit Density for Continuous Latent Space and Variational Inference

Oct 06, 2017
Chin-Wei Huang, Ahmed Touati, Laurent Dinh, Michal Drozdzal, Mohammad Havaei, Laurent Charlin, Aaron Courville

* 2 figures, 5 pages, submitted to ICML Principled Approaches to Deep Learning workshop 

  Access Model/Code and Paper
A Survey of Available Corpora for Building Data-Driven Dialogue Systems

Mar 21, 2017
Iulian Vlad Serban, Ryan Lowe, Peter Henderson, Laurent Charlin, Joelle Pineau

* 56 pages including references and appendix, 5 tables and 1 figure; Under review for the Dialogue & Discourse journal. Update: paper has been rewritten and now includes several new datasets 

  Access Model/Code and Paper
How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation

Jan 03, 2017
Chia-Wei Liu, Ryan Lowe, Iulian V. Serban, Michael Noseworthy, Laurent Charlin, Joelle Pineau

* First 4 authors had equal contribution. 13 pages, 5 tables, 6 figures. EMNLP 2016 

  Access Model/Code and Paper
Generative Deep Neural Networks for Dialogue: A Short Review

Nov 18, 2016
Iulian Vlad Serban, Ryan Lowe, Laurent Charlin, Joelle Pineau

* 6 pages, 1 figure, 3 tables; NIPS 2016 workshop on Learning Methods for Dialogue 

  Access Model/Code and Paper
On the Evaluation of Dialogue Systems with Next Utterance Classification

Jul 23, 2016
Ryan Lowe, Iulian V. Serban, Mike Noseworthy, Laurent Charlin, Joelle Pineau

* Accepted to SIGDIAL 2016 (short paper). 5 pages 

  Access Model/Code and Paper
A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues

Jun 14, 2016
Iulian Vlad Serban, Alessandro Sordoni, Ryan Lowe, Laurent Charlin, Joelle Pineau, Aaron Courville, Yoshua Bengio

* 15 pages, 5 tables, 4 figures 

  Access Model/Code and Paper
Modeling User Exposure in Recommendation

Feb 04, 2016
Dawen Liang, Laurent Charlin, James McInerney, David M. Blei

* 11 pages, 4 figures. WWW'16 

  Access Model/Code and Paper
Dynamic Poisson Factorization

Sep 15, 2015
Laurent Charlin, Rajesh Ranganath, James McInerney, David M. Blei

* RecSys 2015 

  Access Model/Code and Paper
Deep Exponential Families

Nov 10, 2014
Rajesh Ranganath, Linpeng Tang, Laurent Charlin, David M. Blei


  Access Model/Code and Paper
Active Learning for Matching Problems

Jun 18, 2012
Laurent Charlin, Rich Zemel, Craig Boutilier

* ICML2012 

  Access Model/Code and Paper
Hierarchical POMDP Controller Optimization by Likelihood Maximization

Jun 13, 2012
Marc Toussaint, Laurent Charlin, Pascal Poupart

* Appears in Proceedings of the Twenty-Fourth Conference on Uncertainty in Artificial Intelligence (UAI2008) 

  Access Model/Code and Paper
A Framework for Optimizing Paper Matching

Feb 14, 2012
Laurent Charlin, Richard S. Zemel, Craig Boutilier


  Access Model/Code and Paper