Portrait de Chris Pal

Chris Pal

Membre académique principal
christopher.pal@mila.quebec
Chaire en IA Canada-CIFAR
Professeur titulaire, Polytechnique Montréal, Département de génie informatique et de génie logiciel
Professeur associé, Université de Montréal, Département d'informatique et de recherche opérationnelle
Sujets de recherche
Apprentissage profond
Site web
Google Scholar
X

Biographie

Christopher Pal est titulaire d'une chaire en IA Canada-CIFAR, professeur titulaire à Polytechnique Montréal et professeur adjoint au Département d'informatique et de recherche opérationnelle (DIRO) de l'Université de Montréal. Il est également chercheur émérite à ServiceNow Research. Il est engagé dans la recherche sur l'intelligence artificielle et l'apprentissage automatique depuis plus de 25 ans, publiant souvent des travaux sur les méthodes de modélisation du langage à grande échelle et les techniques de modélisation générative. Il a obtenu un doctorat en informatique à l'Université de Waterloo.

Étudiants actuels

Mai Ababneh
Collaborateur·rice de recherche - Formerly McGill (but ending)
ababneh.mai@gmail.com
Shubham Agarwal
Postdoctorat - HEC
Superviseur⋅e principal⋅e :
Laurent Charlin
Site web
Github
Google Scholar
Paul Barde
Collaborateur·rice de recherche - McGill
Superviseur⋅e principal⋅e :
Derek Nowrouzezahrai
paul.b.barde@gmail.com
Site web
Github
Google Scholar
Hugo Baudchon
Maîtrise recherche - UdeM
Github
Chris Beckham
Doctorat - Polytechnique
Can (Sam) Chen
Collaborateur·rice alumni - McGill
Superviseur⋅e principal⋅e :
Xue (Steve) Liu
chencan421@gmail.com
Site web
Léa Demeule
Doctorat - UdeM
Superviseur⋅e principal⋅e :
Glen Berseth
Site web
Github
Amine El-hattami
Doctorat - Polytechnique
Chris Emezue
Maîtrise recherche - UdeM
Co-superviseur⋅e :
Derek Nowrouzezahrai
Site web
Github
Google Scholar
Matthew Fortier
Collaborateur·rice alumni - Polytechnique
Github
Google Scholar
Roger Girgis
Doctorat - Polytechnique
Florian Golemo
Postdoctorat - McGill
fgolemo@gmail.com
Site web
Github
Google Scholar
Anthony Gosselin
Maîtrise recherche - Polytechnique
Site web
Github
Google Scholar
Simon Guiroy
Doctorat - UdeM
Co-superviseur⋅e :
Sarath Chandar
Site web
Github
Google Scholar
Yousef Kotp
Maîtrise recherche - Concordia
Co-superviseur⋅e :
Mahdi Hosseini
Site web
Github
Google Scholar
Jae Hyun Lim
Collaborateur·rice de recherche - UdeM
Site web
Github
Google Scholar
Michelle Lin
Maîtrise recherche - UdeM
Site web
Github
Google Scholar
Olga Luo
Doctorat - UdeM
Aristides Milios
Doctorat - UdeM
Site web
Github
Google Scholar
Joel Moniz
Doctorat - Polytechnique
Jonathan Pilault
Doctorat - Polytechnique
Github
Google Scholar
Juan Rodriguez
Doctorat - École de technologie suprérieure
Site web
Github
Google Scholar
Luke Rowe
Doctorat - UdeM
Superviseur⋅e principal⋅e :
Liam Paull
Site web
Github
Google Scholar
Gaurav Sahu
Postdoctorat - HEC
Superviseur⋅e principal⋅e :
Laurent Charlin
Site web
Github
Google Scholar
Aditya Sharma
Doctorat - Polytechnique
Superviseur⋅e principal⋅e :
Amal Zouaq
Site web
Github
Google Scholar
Mattie Tesfaldet
Doctorat - McGill
Superviseur⋅e principal⋅e :
Derek Nowrouzezahrai
Site web
Github
Google Scholar
Martin Weiss
Doctorat - Polytechnique
Site web
Github
Google Scholar
Matthew Wiens
Doctorat - UdeM
Site web

Publications

The NaijaVoices Dataset: Cultivating Large-Scale, High-Quality, Culturally-Rich Speech Data for African Languages
Chris Emezue
The NaijaVoices Community
Busayo Awobade
Abraham Owodunni
Handel Emezue
Gloria Monica Tobechukwu Emezue
N. N. Emezue
Sewade Ogun
Bunmi Akinremi
David Ifeoluwa Adelani
Chris Pal
The development of high-performing, robust, and reliable speech technologies depends on large, high-quality datasets. However, African langu… (voir plus)ages -- including our focus, Igbo, Hausa, and Yoruba -- remain under-represented due to insufficient data. Popular voice-enabled technologies do not support any of the 2000+ African languages, limiting accessibility for circa one billion people. While previous dataset efforts exist for the target languages, they lack the scale and diversity needed for robust speech models. To bridge this gap, we introduce the NaijaVoices dataset, a 1,800-hour speech-text dataset with 5,000+ speakers. We outline our unique data collection approach, analyze its acoustic diversity, and demonstrate its impact through finetuning experiments on automatic speech recognition, averagely achieving 75.86% (Whisper), 52.06% (MMS), and 42.33% (XLSR) WER improvements. These results highlight NaijaVoices' potential to advance multilingual speech processing for African languages.
2025-05-26
ArXiv (prépublication)
doi.org
arxiv.org
The NaijaVoices Dataset: Cultivating Large-Scale, High-Quality, Culturally-Rich Speech Data for African Languages
Chris Emezue
The NaijaVoices Community
Busayo Awobade
Abraham Owodunni
Handel Emezue
Gloria Monica Tobechukwu Emezue
N. N. Emezue
Sewade Ogun
Bunmi Akinremi
David Ifeoluwa Adelani
Chris Pal
2025-05-01
arXiv (publié)
doi.org
arxiv.org
UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction
Shravan Nayak
Xiangru Jian
Kevin Qinghong Lin
Juan A. Rodriguez
Montek Kalsi
Rabiul Awal
Nicolas Chapados
M. Tamer Özsu
Aishwarya Agrawal
David Vazquez
Chris Pal
Perouz Taslakian
Spandana Gella
Sai Rajeswar
Human Annotator
2025-05-01
ICML.cc/2025/Conference (poster)
doi.org
openreview.net
Distilling semantically aware orders for autoregressive image generation
Rishav Pramanik
Antoine Poupon
Juan A. Rodriguez
Masih Aminbeidokhti
David Vazquez
Chris Pal
Zhaozheng Yin
Marco Pedersoli
2025-04-23
ArXiv (prépublication)
arxiv.org
arxiv.org
Distilling semantically aware orders for autoregressive image generation
Rishav Pramanik
Antoine Poupon
Juan A. Rodriguez
Masih Aminbeidokhti
David Vazquez
Chris Pal
Zhaozheng Yin
Marco Pedersoli
2025-04-23
ArXiv (prépublication)
doi.org
arxiv.org
StarVector: Generating Scalable Vector Graphics Code from Images and Text
Juan A. Rodriguez
Abhay Puri
Shubham Agarwal
Issam Hadj Laradji
Pau Rodriguez
Sai Rajeswar
David Vazquez
Chris Pal
Marco Pedersoli
2025-04-11
Proceedings of the AAAI Conference on Artificial Intelligence (publié)
doi.org
arxiv.org
AgentAda: Skill-Adaptive Data Analytics for Tailored Insight Discovery
Amirhossein Abaskohi
Amrutha Varshini Ramesh
Shailesh Nanisetty
Chirag Goel
David Vazquez
Chris Pal
Spandana Gella
Giuseppe Carenini
Issam Hadj Laradji
2025-04-10
ArXiv (prépublication)
arxiv.org
arxiv.org
AgentAda: Skill-Adaptive Data Analytics for Tailored Insight Discovery
Amirhossein Abaskohi
Amrutha Varshini Ramesh
Shailesh Nanisetty
Chirag Goel
David Vazquez
Chris Pal
Spandana Gella
Giuseppe Carenini
Issam Hadj Laradji
2025-04-01
arXiv (publié)
doi.org
arxiv.org
LitLLMs, LLMs for Literature Review: Are we there yet?
Shubham Agarwal
Gaurav Sahu
Abhay Puri
Issam Hadj Laradji
Krishnamurthy Dj Dvijotham
Jason Stanley
Laurent Charlin
Chris Pal
2025-04-01
TMLR (accepté)
openreview.net
openreview.net
Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environments
Luke Rowe
Roger Girgis
Anthony Gosselin
Liam Paull
Chris Pal
Felix Heide
2025-03-28
ArXiv (prépublication)
arxiv.org
arxiv.org
StarFlow: Generating Structured Workflow Outputs From Sketch Images
Patrice Bechard
Chao Wang
Amirhossein Abaskohi
Juan A. Rodriguez
Chris Pal
David Vazquez
Spandana Gella
Sai Rajeswar
Perouz Taslakian
2025-03-27
ArXiv (prépublication)
doi.org
arxiv.org
StarFlow: Generating Structured Workflow Outputs From Sketch Images
Patrice Bechard
Chao Wang
Amirhossein Abaskohi
Juan A. Rodriguez
Chris Pal
David Vazquez
Spandana Gella
Sai Rajeswar
Perouz Taslakian
2025-03-27
ArXiv (prépublication)
arxiv.org
arxiv.org