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

Site web

Google Scholar

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

Abhinav Gupta

Doctorat - Université de Montréal

Doctorat

Superviseur⋅e principal⋅e :

Amal Zouaq

aditya.sharma@mila.quebec

Doctorat - Université de Montréal

picheale@mila.quebec

Github

Amine El-hattami

Doctorat - Polytechnique Montréal

elhattaa@mila.quebec

Abdou Mousas

Doctorat - Université de Montréal

mousasab@mila.quebec

Anthony Gosselin

Maîtrise recherche - Polytechnique Montréal

anthony.gosselin@mila.quebec

Site web

Github

Google Scholar

Sam Chen

Doctorat - McGill University

Superviseur⋅e principal⋅e :

Maîtrise recherche - Université de Montréal

Co-superviseur⋅e :

Derek Nowrouzezahrai

chris.emezue@mila.quebec

Doctorat - Polytechnique Montréal

christopher.beckham@mila.quebec

Ge Ya (olga Luo) Luo

Doctorat - Université de Montréal

xugeya@mila.quebec

Georges Belanger Albarran

Maîtrise recherche - Université de Montréal

georges.belangeralbarran@mila.quebec

Baudchon Hugo Baudchon

Collaborateur·rice de recherche - Université de Montréal

Superviseur⋅e principal⋅e :

Étienne Laliberté

hugo.baudchon@mila.quebec

Github

Jae Hyun Lim

Doctorat - Université de Montréal

Doctorat - Polytechnique Montréal

Doctorat - École de technologie suprérieure

juan.rodriguez@mila.quebec

Site web

Github

Google Scholar

Julien Roy

Doctorat - Polytechnique Montréal

Co-superviseur⋅e :

Luke Rowe

Doctorat - Université de Montréal

Superviseur⋅e principal⋅e :

Liam Paull

luke.rowe@mila.quebec

Github

Google Scholar

Martin Weiss

Doctorat - Polytechnique Montréal

Postdoctorat - Université de Montréal

mats-leon.richter@mila.quebec

Github

Matthew Fortier

Maîtrise recherche - Polytechnique Montréal

matthew.fortier@mila.quebec

Github

Google Scholar

Mattie Tesfaldet

Doctorat - McGill University

Superviseur⋅e principal⋅e :

Derek Nowrouzezahrai

mattie.tesfaldet@mila.quebec

Collaborateur·rice de recherche

michelle.lin@mila.quebec

Site web

Github

Google Scholar

Paul Barde

Doctorat - McGill University

Superviseur⋅e principal⋅e :

Doctorat - Polytechnique Montréal

girgisro@mila.quebec

Shubham Agarwal

Postdoctorat - HEC Montréal

Superviseur⋅e principal⋅e :

Laurent Charlin

shubham.agarwal@mila.quebec

Maîtrise recherche - Polytechnique Montréal

chamorrs@mila.quebec

Google Scholar

Simon Guiroy

Doctorat - Université de Montréal

Co-superviseur⋅e :

Sarath Chandar Anbil Parthipan

Doctorat - Université de Montréal

voletivi@mila.quebec

Z Luo

Doctorat - Polytechnique Montréal

luozhiha@mila.quebec

Billets de blogue

Direct Behavior Specification via Constrained Reinforcement Learning

31 août 2022

Spécification directe du comportement par apprentissage par renforcement sous contrainte

par

Julien Roy

Roger Girgis

Joshua Romoff

Pierre-Luc Bacon

Chris Pal

Lire l'article

Publications

Proactive Contact Tracing

Prateek Gupta

Tegan Maharaj

Martin Weiss

Nasim Rahaman

Hannah Alsdurf

Nanor Minoyan

Soren Harnois-Leblanc

Joanna Merckx

andrew williams

Victor Schmidt

Pierre-Luc St-Charles

Akshay Patel

Yang Zhang

David Buckeridge

Chris Pal

Bernhard Schölkopf

Yoshua Bengio

2023-03-13

PLOS Digital Health (publié)

doi.org

Score-based Diffusion Models in Function Space

Jae Hyun Lim

Nikola B. Kovachki

R. Baptista

Christopher Beckham

Kamyar Azizzadenesheli

Jean Kossaifi

Vikram Voleti

Jiaming Song

Karsten Kreis

J. Kautz

Chris Pal

Arash Vahdat

Animashree Anandkumar

2023-02-14

ArXiv (prépublication)

doi.org

arxiv.org

Language Decision Transformers with Exponential Tilt for Interactive Text Environments

Nicolas Gontier

Pau Rodriguez

Issam Hadj Laradji

David Vazquez

Chris Pal

2023-02-10

ArXiv (preprint)

openreview.net

ArK: Augmented Reality with Knowledge Emergent Infrastructure

Qiuyuan Huang

J. Park

Abhinav Gupta

Pan Lu

Paul N. Bennett

Ran Gong

Subhojit Som

Baolin Peng

Owais Khan Mohammed

Chris Pal

Yejin Choi

Jianfeng Gao

Despite the growing adoption of mixed reality and interactive AI, it remains challenging to generate high-quality 2D/3D scenes in unseen env… (voir plus)ironments. Typically, an AI agent requires collecting extensive training data for every new task, which can be costly or impossible for many domains. In this study, we develop an infinite agent that learns to transfer knowledge memory from general foundation models (e.g., GPT4, DALLE) to novel domains or scenarios for scene understanding and generation in physical or virtual worlds. Central to our approach is the interactive emerging mechanism, dubbed Augmented Reality with Knowledge Emergent Infrastructure (ArK) , which leverages knowledge-memory to generate scenes in unseen physical worlds and virtual reality environments. The knowledge interactive emergent ability (Figure 1) is demonstrated through i) micro-action of cross-modality : in multi-modality models to collect a large amount of relevant knowledge-memory data for each interaction task (e.g., unseen scene understanding) from the physical reality; and ii) macro-behavior of reality-agnostic : in mix-reality environments to improve interactions that tailor to different characterized roles, target variables, collaborative information, and so on. We validate ArK’s effectiveness in scene generation and editing tasks and show that our ArK approach, combined with large foundation models, significantly improves the quality of generated 2D/3D scenes, highlighting its potential in applications such as metaverse and gaming simulation.

2023-01-01

(publié)

www.semanticscholar.org

Block-State Transformers

Mahan Fathi

Jonathan Pilault

Pierre-Luc Bacon

Chris Pal

Orhan Firat

Ross Goroshin

2023-01-01

NeurIPS (publié)

arxiv.org

Exploring validation metrics for ofﬂine model-based optimisation

Christopher Beckham

Alexandre Piché

David Vazquez

Chris Pal

In ofﬂine model-based optimisation (MBO) we are interested in using machine learning to de-sign candidates that maximise some measure of d… (voir plus)esirability through an expensive but real-world scoring process. Ofﬂine MBO tries to approximate this expensive scoring function and use that to evaluate generated designs, however evaluation is non-exact because one approximation is being evaluated with another. Instead, we ask ourselves: if we did have the real world scoring function at hand, what cheap-to-compute validation metrics would correlate best with this? Since the real-world scoring function is available for simulated MBO datasets, insights obtained from this can be transferred over to real-world ofﬂine MBO tasks where the real-world scoring function is expensive to compute. To address this, we propose a conceptual evaluation framework that is amenable to measuring extrapolation, and apply this to conditional denoising diffusion models. Empirically, we ﬁnd that two validation metrics – agreement and Frechet distance – correlate quite well with the ground truth. When there is high variability in conditional generation, feedback is required in the form of an approximated version of the real-world scoring function. Furthermore, we ﬁnd that generating high-scoring samples may require heavily weighting the generative model in favour of sample quality, potentially at the cost of sample diversity.

2023-01-01

(publié)

www.semanticscholar.org

Towards Learning to Imitate from a Single Video Demonstration

Glen Berseth

Florian Golemo

Chris Pal

Agents that can learn to imitate given video observation -- \emph{without direct access to state or action information} are more applicable … (voir plus)to learning in the natural world. However, formulating a reinforcement learning (RL) agent that facilitates this goal remains a significant challenge. We approach this challenge using contrastive training to learn a reward function comparing an agent's behaviour with a single demonstration. We use a Siamese recurrent neural network architecture to learn rewards in space and time between motion clips while training an RL policy to minimize this distance. Through experimentation, we also find that the inclusion of multi-task data and additional image encoding losses improve the temporal consistency of the learned rewards and, as a result, significantly improves policy learning. We demonstrate our approach on simulated humanoid, dog, and raptor agents in 2D and a quadruped and a humanoid in 3D. We show that our method outperforms current state-of-the-art techniques in these environments and can learn to imitate from a single video demonstration.

arxiv.org

Workflow Discovery from Dialogues in the Low Data Regime

Amine El hattami

Issam Hadj Laradji

Stefania Raimondo

David Vazquez

Pau Rodriguez

Chris Pal

Text-based dialogues are now widely used to solve real-world problems. In cases where solution strategies are already known, they can someti… (voir plus)mes be codified into workflows and used to guide humans or artificial agents through the task of helping clients. We introduce a new problem formulation that we call Workflow Discovery (WD) in which we are interested in the situation where a formal workflow may not yet exist. Still, we wish to discover the set of actions that have been taken to resolve a particular problem. We also examine a sequence-to-sequence (Seq2Seq) approach for this novel task. We present experiments where we extract workflows from dialogues in the Action-Based Conversations Dataset (ABCD). Since the ABCD dialogues follow known workflows to guide agents, we can evaluate our ability to extract such workflows using ground truth sequences of actions. We propose and evaluate an approach that conditions models on the set of possible actions, and we show that using this strategy, we can improve WD performance. Our conditioning approach also improves zero-shot and few-shot WD performance when transferring learned models to unseen domains within and across datasets. Further, on ABCD a modified variant of our Seq2Seq method achieves state-of-the-art performance on related but different problems of Action State Tracking (AST) and Cascading Dialogue Success (CDS) across many evaluation metrics.

2023-01-01

Trans. Mach. Learn. Res. (publié)

doi.org

openreview.net

Implicit Offline Reinforcement Learning via Supervised Learning

Alexandre Piché

Rafael Pardinas

David Vazquez

Igor Mordatch

Chris Pal

Offline Reinforcement Learning (RL) via Supervised Learning is a simple and effective way to learn robotic skills from a dataset of varied b… (voir plus)ehaviors. It is as simple as supervised learning and Behavior Cloning (BC) but takes advantage of the return information. On BC tasks, implicit models have been shown to match or outperform explicit ones. Despite the benefits of using implicit models to learn robotic skills via BC, Offline RL via Supervised Learning algorithms have been limited to explicit models. We show how implicit models leverage return information and match or outperform explicit algorithms to acquire robotic skills from fixed datasets. Furthermore, we show how closely related our implicit methods are to other popular RL via Supervised Learning algorithms.

2022-12-09

NeurIPS.cc/2022/Workshop/DeepRL (inconnu)

doi.org

openreview.net

SMPL-IK: Learned Morphology-Aware Inverse Kinematics for AI Driven Artistic Workflows

Vikram Voleti

Boris Oreshkin

Florent Bocquelet

Félix Harvey

Louis-Simon Ménard

Chris Pal

2022-11-22

SIGGRAPH Asia 2022 Technical Communications (publié)

doi.org

arxiv.org

Does Entity Abstraction Help Generative Transformers Reason?

Nicolas Gontier

Siva Reddy

Chris Pal

We study the utility of incorporating entity type abstractions into pre-trained Transformers and test these methods on four NLP tasks requir… (voir plus)ing different forms of logical reasoning: (1) compositional language understanding with text-based relational reasoning (CLUTRR), (2) abductive reasoning (ProofWriter), (3) multi-hop question answering (HotpotQA), and (4) conversational question answering (CoQA). We propose and empirically explore three ways to add such abstraction: (i) as additional input embeddings, (ii) as a separate sequence to encode, and (iii) as an auxiliary prediction task for the model. Overall, our analysis demonstrates that models with abstract entity knowledge performs better than without it. The best abstraction aware models achieved an overall accuracy of 88.8% and 91.8% compared to the baseline model achieving 62.9% and 89.8% on CLUTRR and ProofWriter respectively. However, for HotpotQA and CoQA, we find that F1 scores improve by only 0.5% on average. Our results suggest that the benefit of explicit abstraction is significant in formally defined logical reasoning settings requiring many reasoning hops, but point to the notion that it is less beneficial for NLP tasks having less formal logical structure.

2022-11-20

TMLR (accepted)

openreview.net

MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation

Vikram Voleti

Alexia Jolicoeur-Martineau

Chris Pal

Video prediction is a challenging task. The quality of video frames from current state-of-the-art (SOTA) generative models tends to be poor … (voir plus)and generalization beyond the training data is difficult. Furthermore, existing prediction frameworks are typically not capable of simultaneously handling other video-related tasks such as unconditional generation or interpolation. In this work, we devise a general-purpose framework called Masked Conditional Video Diffusion (MCVD) for all of these video synthesis tasks using a probabilistic conditional score-based denoising diffusion model, conditioned on past and/or future frames. We train the model in a manner where we randomly and independently mask all the past frames or all the future frames. This novel but straightforward setup allows us to train a single model that is capable of executing a broad range of video tasks, specifically: future/past prediction -- when only future/past frames are masked; unconditional generation -- when both past and future frames are masked; and interpolation -- when neither past nor future frames are masked. Our experiments show that this approach can generate high-quality frames for diverse types of videos. Our MCVD models are built from simple non-recurrent 2D-convolutional architectures, conditioning on blocks of frames and generating blocks of frames. We generate videos of arbitrary lengths autoregressively in a block-wise manner. Our approach yields SOTA results across standard video prediction and interpolation benchmarks, with computation times for training models measured in 1-12 days using

openreview.net

La recherche en IA au service du monde réel

Boussole des politiques en IA

Vie étudiante et ressources

Chris Pal

Biographie

Étudiants actuels

Billets de blogue

Publications

La recherche en IA au service du monde réel

Boussole des politiques en IA

Vie étudiante et ressources

Mots-clés populaires:

Chris Pal

Biographie

Étudiants actuels

Billets de blogue

Publications