Chris Pal

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

Shubham Agarwal

Postdoctorat - HEC

Superviseur⋅e principal⋅e :

Paul Barde

Doctorat - McGill

Superviseur⋅e principal⋅e :

Derek Nowrouzezahrai

paul.b.barde@gmail.com

Doctorat - Polytechnique

Georges Belanger Albarran

Maîtrise recherche - UdeM

Simon Chamorro

Maîtrise recherche - Polytechnique

Can (Sam) Chen

Doctorat - McGill

Superviseur⋅e principal⋅e :

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Glen Berseth

Amine El-hattami

Doctorat - Polytechnique

Chris Emezue

Maîtrise recherche - UdeM

Co-superviseur⋅e :

Maîtrise recherche - Polytechnique

Sarath Chandar Anbil Parthipan

Roger Girgis

Doctorat - Polytechnique

Anthony Gosselin

Maîtrise recherche - Polytechnique

Doctorat - UdeM

Co-superviseur⋅e :

Doctorat - UdeM

Baudchon Hugo Baudchon

Maîtrise recherche - UdeM

Superviseur⋅e principal⋅e :

Doctorat - UdeM

Collaborateur·rice de recherche

Olga Luo

Doctorat - UdeM

Z Luo

Doctorat - Polytechnique

Doctorat - UdeM

Doctorat - UdeM

Doctorat - UdeM

Doctorat - Polytechnique

Postdoctorat - UdeM

Doctorat - École de technologie suprérieure

Luke Rowe

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Liam Paull

Julien Roy

Doctorat - Polytechnique

Co-superviseur⋅e :

Doctorat

Superviseur⋅e principal⋅e :

Doctorat - McGill

Superviseur⋅e principal⋅e :

Doctorat - UdeM

Doctorat - Polytechnique

Spécification directe du comportement par apprentissage par renforcement sous contrainte

Billets de blogue

Direct Behavior Specification via Constrained Reinforcement Learning

31 août 2022

par

Julien Roy

Roger Girgis

Joshua Romoff

Pierre-Luc Bacon

Chris Pal

Lire l'article

Publications

InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation

Gaurav Sahu

Abhay Puri

Juan A. Rodriguez

Alexandre Drouin

Perouz Taslakian

Valentina Zantedeschi

Alexandre Lacoste

David Vazquez

Nicolas Chapados

Sai Rajeswar

Issam Hadj Laradji

2024-07-08

ArXiv (prépublication)

RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content

Joao Monteiro

Pierre-Andre Noel

Étienne Marcotte

Sai Rajeswar

Valentina Zantedeschi

David Vazquez

Nicolas Chapados

Perouz Taslakian

Large Language Models (LLMs) are trained on vast amounts of data, most of which is automatically scraped from the internet. This data includ… (voir plus)es encyclopedic documents that harbor a vast amount of general knowledge (e.g., Wikipedia) but also potentially overlap with benchmark datasets used for evaluating LLMs. Consequently, evaluating models on test splits that might have leaked into the training set is prone to misleading conclusions. To foster sound evaluation of language models, we introduce a new test dataset named RepLiQA, suited for question-answering and topic retrieval tasks. RepLiQA is a collection of five splits of test sets, four of which have not been released to the internet or exposed to LLM APIs prior to this publication. Each sample in RepLiQA comprises (1) a reference document crafted by a human annotator and depicting an imaginary scenario (e.g., a news article) absent from the internet; (2) a question about the document's topic; (3) a ground-truth answer derived directly from the information in the document; and (4) the paragraph extracted from the reference document containing the answer. As such, accurate answers can only be generated if a model can find relevant content within the provided document. We run a large-scale benchmark comprising several state-of-the-art LLMs to uncover differences in performance across models of various types and sizes in a context-conditional language modeling setting. Released splits of RepLiQA can be found here: https://huggingface.co/datasets/ServiceNow/repliqa.

2024-06-17

ArXiv (prépublication)

Exploring validation metrics for offline model-based optimisation with diffusion models

Christopher Beckham

Alexandre Piché

David Vazquez

2024-06-13

TMLR (accepté)

Ctrl-V: Higher Fidelity Video Generation with Bounding-Box Controlled Object Motion

Ge Ya Luo

Zhi Hao Luo

Anthony Gosselin

Alexia Jolicoeur-Martineau

With recent advances in video prediction, controllable video generation has been attracting more attention. Generating high fidelity videos … (voir plus)according to simple and flexible conditioning is of particular interest. To this end, we propose a controllable video generation model using pixel level renderings of 2D or 3D bounding boxes as conditioning. In addition, we also create a bounding box predictor that, given the initial and ending frames' bounding boxes, can predict up to 15 bounding boxes per frame for all the frames in a 25-frame clip. We perform experiments across 3 well-known AV video datasets: KITTI, Virtual-KITTI 2 and BDD100k.

2024-06-09

ArXiv (prépublication)

XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference

Jo˜ao Monteiro

Étienne Marcotte

Pierre-Andre Noel

Valentina Zantedeschi

David Vazquez

Nicolas Chapados

Perouz Taslakian

In-context learning (ICL) approaches typically leverage prompting to condition decoder-only language model generation on reference informati… (voir plus)on. Just-in-time processing of a context is inefficient due to the quadratic cost of self-attention operations, and caching is desirable. However, caching transformer states can easily require almost as much space as the model parameters. When the right context isn't known in advance, caching ICL can be challenging. This work addresses these limitations by introducing models that, inspired by the encoder-decoder architecture, use cross-attention to condition generation on reference text without the prompt. More precisely, we leverage pre-trained decoder-only models and only train a small number of added layers. We use Question-Answering (QA) as a testbed to evaluate the ability of our models to perform conditional generation and observe that they outperform ICL, are comparable to fine-tuned prompted LLMs, and drastically reduce the space footprint relative to standard KV caching by two orders of magnitude.

2024-04-23

ArXiv (prépublication)

CtRL-Sim: Reactive and Controllable Driving Agents with Offline Reinforcement Learning

Luke Rowe

Roger Girgis

Anthony Gosselin

Bruno Carrez

Florian Golemo

Felix Heide

Liam Paull

Evaluating autonomous vehicle stacks (AVs) in simulation typically involves replaying driving logs from real-world recorded traffic. However… (voir plus), agents replayed from offline data do not react to the actions of the AV, and their behaviour cannot be easily controlled to simulate counterfactual scenarios. Existing approaches have attempted to address these shortcomings by proposing methods that rely on heuristics or learned generative models of real-world data but these approaches either lack realism or necessitate costly iterative sampling procedures to control the generated behaviours. In this work, we take an alternative approach and propose CtRL-Sim, a method that leverages return-conditioned offline reinforcement learning within a physics-enhanced Nocturne simulator to efficiently generate reactive and controllable traffic agents. Specifically, we process real-world driving data through the Nocturne simulator to generate a diverse offline reinforcement learning dataset, annotated with various reward terms. With this dataset, we train a return-conditioned multi-agent behaviour model that allows for fine-grained manipulation of agent behaviours by modifying the desired returns for the various reward components. This capability enables the generation of a wide range of driving behaviours beyond the scope of the initial dataset, including those representing adversarial behaviours. We demonstrate that CtRL-Sim can efficiently generate diverse and realistic safety-critical scenarios while providing fine-grained control over agent behaviours. Further, we show that fine-tuning our model on simulated safety-critical scenarios generated by our model enhances this controllability.

2024-03-29

ArXiv (prépublication)

Language Models Can Reduce Asymmetry in Information Markets

Nasim Rahaman

Martin Weiss

Manuel Wüthrich

Yoshua Bengio

Erran L. Li

Bernhard Schölkopf

2024-03-21

ArXiv (prépublication)

Multi-Resolution Continuous Normalizing Flows

Vikram Voleti

Chris Finlay

Adam M. Oberman

2024-03-21

Annals of Mathematics and Artificial Intelligence (publié)

IntentGPT: Few-shot Intent Discovery with Large Language Models

Juan A. Rodriguez

Nicholas Botzer

David Vazquez

Marco Pedersoli

Issam Hadj Laradji

2024-03-11

ICLR.cc/2024/Workshop/LLMAgents (poster)

Self-evaluation and self-prompting to improve the reliability of LLMs

Alexandre Piché

Aristides Milios

Dzmitry Bahdanau

In order to safely deploy Large Language Models (LLMs), they must be capable of dynamically adapting their behavior based on their level of … (voir plus)knowledge and uncertainty associated with specific topics. This adaptive behavior, which we refer to as self-restraint, is non-trivial to teach since it depends on the internal knowledge of an LLM. By default, LLMs are trained to maximize the next token likelihood which does not teach the model to modulate its answer based on its level of uncertainty. In order to learn self-restraint, we devise a simple objective that can encourage the model to produce generation that the model is confident in. To optimize this objective, we introduce ReSearch, an iterative search algorithm based on self-evaluation and self-prompting. Our method results in fewer hallucinations overall, both for known and unknown topics, as the model learns to selectively restrain itself. In addition, our method elegantly incorporates the ability to decline, when the model assesses that it cannot provide a response without a high proportion of hallucination.

2024-03-04

ICLR.cc/2024/Workshop/SeT_LLM (publié)

Self-evaluation and self-prompting to improve the reliability of LLMs

Alexandre Piché

Aristides Milios

Dzmitry Bahdanau

2024-03-04

ICLR.cc/2024/Workshop/SeT_LLM (publié)

LitLLM: A Toolkit for Scientific Literature Review

Shubham Agarwal

Issam Hadj Laradji

Laurent Charlin

Conducting literature reviews for scientific papers is essential for understanding research, its limitations, and building on existing work.… (voir plus) It is a tedious task which makes an automatic literature review generator appealing. Unfortunately, many existing works that generate such reviews using Large Language Models (LLMs) have significant limitations. They tend to hallucinate-generate non-actual information-and ignore the latest research they have not been trained on. To address these limitations, we propose a toolkit that operates on Retrieval Augmented Generation (RAG) principles, specialized prompting and instructing techniques with the help of LLMs. Our system first initiates a web search to retrieve relevant papers by summarizing user-provided abstracts into keywords using an off-the-shelf LLM. Authors can enhance the search by supplementing it with relevant papers or keywords, contributing to a tailored retrieval process. Second, the system re-ranks the retrieved papers based on the user-provided abstract. Finally, the related work section is generated based on the re-ranked results and the abstract. There is a substantial reduction in time and effort for literature review compared to traditional methods, establishing our toolkit as an efficient alternative. Our open-source toolkit is accessible at https://github.com/shubhamagarwal92/LitLLM and Huggingface space (https://huggingface.co/spaces/shubhamagarwal92/LitLLM) with the video demo at https://youtu.be/E2ggOZBAFw0.

2024-02-02

ArXiv (prépublication)