Chris Pal

Biography

Christopher Pal is a Canada CIFAR AI Chair, full professor at Polytechnique Montréal and adjunct professor in the Department of Computer Science and Operations Research (DIRO) at Université de Montréal. He is also a Distinguished Scientist at ServiceNow Research.

Pal has been involved in AI and machine learning research for over twenty-five years and has published extensively on large-scale language modelling methods and generative modelling techniques. He has a PhD in computer science from the University of Waterloo.

Current Students

Mai Ababneh

Research Intern - Formerly McGill University (but ending)

ababneh.mai@gmail.com

Shubham Agarwal

Postdoctorate - HEC Montréal

Principal supervisor :

Paul Barde

Collaborating researcher - McGill University

Principal supervisor :

Derek Nowrouzezahrai

paul.b.barde@gmail.com

Master's Research - Université de Montréal

Chris Beckham

PhD - Polytechnique Montréal

Can (Sam) Chen

Collaborating Alumni - McGill University

Principal supervisor :

PhD - Université de Montréal

Principal supervisor :

PhD - Polytechnique Montréal

Chris Emezue

Master's Research - Université de Montréal

Co-supervisor :

Collaborating Alumni - Polytechnique Montréal

Roger Girgis

PhD - Polytechnique Montréal

Florian Golemo

Postdoctorate - McGill University

Master's Research - Polytechnique Montréal

PhD - Université de Montréal

Co-supervisor :

Yousef Kotp

Master's Research - Concordia University

Co-supervisor :

Collaborating researcher - Université de Montréal

Master's Research - Université de Montréal

Olga Luo

PhD - Université de Montréal

Aristides Milios

PhD - Université de Montréal

Joel Moniz

PhD - Polytechnique Montréal

Jonathan Pilault

PhD - Polytechnique Montréal

Juan Rodriguez

PhD - École de technologie suprérieure

Luke Rowe

PhD - Université de Montréal

Principal supervisor :

Gaurav Sahu

Postdoctorate - HEC Montréal

Principal supervisor :

PhD - Polytechnique Montréal

Principal supervisor :

PhD - McGill University

Principal supervisor :

PhD - Polytechnique Montréal

PhD - Université de Montréal

Direct Behavior Specification via Constrained Reinforcement Learning

Blog Posts

August 31, 2022

Julien Roy

Roger Girgis

Joshua Romoff

Pierre-Luc Bacon

Chris Pal

Read the article

Publications

Spatio-Temporal Conditional Diffusion Models for Forecasting Future Multiple Sclerosis Lesion Masks Conditioned on Treatments

Gian Mario Favero

Ge Ya Luo

Douglas Arnold

Image-based personalized medicine has the potential to transform healthcare, particularly for diseases that exhibit heterogeneous progressio… (see more)n such as Multiple Sclerosis (MS). In this work, we introduce the first treatment-aware spatio-temporal diffusion model that is able to generate future masks demonstrating lesion evolution in MS. Our voxel-space approach incorporates multi-modal patient data, including MRI and treatment information, to forecast new and enlarging T2 (NET2) lesion masks at a future time point. Extensive experiments on a multi-centre dataset of 2131 patient 3D MRIs from randomized clinical trials for relapsing-remitting MS demonstrate that our generative model is able to accurately predict NET2 lesion masks for patients across six different treatments. Moreover, we demonstrate our model has the potential for real-world clinical applications through downstream tasks such as future lesion count and location estimation, binary lesion activity classification, and generating counterfactual future NET2 masks for several treatments with different efficacies. This work highlights the potential of causal, image-based generative models as powerful tools for advancing data-driven prognostics in MS.

2025-08-09

ArXiv (preprint)

Spatio-Temporal Conditional Diffusion Models for Forecasting Future Multiple Sclerosis Lesion Masks Conditioned on Treatments

Gian Mario Favero

Ge Ya Luo

Douglas Arnold

2025-08-09

ArXiv (preprint)

The Promise of RL for Autoregressive Image Editing

Saba Ahmadi

Rabiul Awal

Ankur Sikarwar

Amirhossein Kazemnejad

Ge Ya Luo

Juan A. Rodriguez

Sai Rajeswar

We explore three strategies to enhance performance on a wide range of image editing tasks: supervised fine-tuning (SFT), reinforcement learn… (see more)ing (RL), and Chain-of-Thought (CoT) reasoning. In order to study all these components in one consistent framework, we adopt an autoregressive multimodal model that processes textual and visual tokens in a unified manner. We find RL combined with a large multi-modal LLM verifier to be the most effective of these strategies. As a result, we release EARL: Editing with Autoregression and RL, a strong RL-based image editing model that performs competitively on a diverse range of edits compared to strong baselines, despite using much less training data. Thus, EARL pushes the frontier of autoregressive multimodal models on image editing. We release our code, training data, and trained models at https://github.com/mair-lab/EARL.

2025-08-01

ArXiv (preprint)

Evaluating and Improving LitLLMs with Deep Research

Gaurav Sahu

Shubham Agarwal

Abhay Puri

Issam Hadj Laradji

Krishnamurthy Dj Dvijotham

Jason Stanley

Laurent Charlin

Literature reviews are an essential component of scientific research, but they remain time-intensive and challenging to write, especially du… (see more)e to the recent influx of research papers. This paper explores the zero-shot abilities of recent Large Language Models (LLMs) in assisting with the writing of literature reviews based on an abstract. We decompose the task into two components: (1) Retrieving related works given a query abstract and (2) Writing a literature review based on the retrieved results. We analyze how effective LLMs are for both components. For retrieval, we introduce a novel two-step search strategy that first uses an LLM to extract meaningful keywords from the abstract of a paper and then retrieves potentially relevant papers by querying an external knowledge base. Additionally, we study a prompting-based re-ranking mechanism with attribution and show that re-ranking doubles the normalized recall compared to naive search methods while providing insights into the LLM's decision-making process. In the generation phase, we propose a two-step approach that first outlines a plan for the review and then executes steps in the plan to generate the actual review. To evaluate different LLM-based literature review methods, we create test sets from arXiv papers using a protocol designed for rolling use with newly released LLMs to avoid test set contamination in zero-shot evaluations. We release this evaluation protocol to promote additional research and development in this regard. Our empirical results suggest that LLMs show promising potential for writing literature reviews when the task is decomposed into smaller components of retrieval and planning. Particularly, our ``Deep Research" retrieval variant improves coverage by over 5x compared to standard keyword search, addressing a key bottleneck in the pipeline. Further, we demonstrate that our planning-based approach achieves higher-quality reviews by minimizing hallucinated references in the generated review by 18-26\% compared to existing simpler LLM-based generation methods.

2025-07-31

colmweb.org/COLM/2025/Workshop/LM4Sci (published)

AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories

Xing Han Lu

Amirhossein Kazemnejad

Karolina Stanczak

Peter Shaw

Siva Reddy

Web agents enable users to perform tasks on web browsers through natural language interaction. Evaluating web agents trajectories is an impo… (see more)rtant problem, since it helps us determine whether the agent successfully completed the tasks. Rule-based methods are widely used for this purpose, but they are challenging to extend to new tasks and may not always recognize successful trajectories. We may achieve higher accuracy through human evaluation, but the process would be substantially slower and more expensive. Automatic evaluations with LLMs may avoid the challenges of designing new rules and manually annotating trajectories, enabling faster and cost-effective evaluation. However, it is unclear how effective they are at evaluating web agents. To this end, we propose AgentRewardBench, the first benchmark to assess the effectiveness of LLM judges for evaluating web agents. AgentRewardBench contains 1302 trajectories across 5 benchmarks and 4 LLMs. Each trajectory in AgentRewardBench is reviewed by an expert, who answers questions pertaining to the success, side effects, and repetitiveness of the agent. Using our benchmark, we evaluate 12 LLM judges and find that no single LLM excels across all benchmarks. We also find that the rule-based evaluation used by common benchmarks tends to underreport the success rate of web agents, highlighting a key weakness of rule-based evaluation and the need to develop more flexible automatic evaluations. We release the benchmark at: https://agent-reward-bench.github.io

2025-07-07

colmweb.org/COLM/2025/Conference (accepted)

BigCharts-R1: Enhanced Chart Reasoning with Visual Reinforcement Finetuning

Ahmed Masry

Abhay Puri

Masoud Hashemi

Juan A. Rodriguez

Megh Thakkar

Khyati Mahajan

Vikas Yadav

Sathwik Tejaswi Madhusudhan

Alexandre Piché

Dzmitry Bahdanau

David Vazquez

Enamul Hoque

Perouz Taslakian

Sai Rajeswar

Spandana Gella

2025-07-07

colmweb.org/COLM/2025/Conference (accepted)

Poutine: Vision-Language-Trajectory Pre-Training and Reinforcement Learning Post-Training Enable Robust End-to-End Autonomous Driving

Luke Rowe

Rodrigue De Schaetzen

Roger Girgis

We present Poutine, a 3B-parameter vision-language model (VLM) tailored for end-to-end autonomous driving in long-tail driving scenarios. Po… (see more)utine is trained in two stages. To obtain strong base driving capabilities, we train Poutine-Base in a self-supervised vision-language-trajectory (VLT) next-token prediction fashion on 83 hours of CoVLA nominal driving and 11 hours of Waymo long-tail driving. Accompanying language annotations are auto-generated with a 72B-parameter VLM. Poutine is obtained by fine-tuning Poutine-Base with Group Relative Policy Optimization (GRPO) using less than 500 preference-labeled frames from the Waymo validation set. We show that both VLT pretraining and RL fine-tuning are critical to attain strong driving performance in the long-tail. Poutine-Base achieves a rater-feedback score (RFS) of 8.12 on the validation set, nearly matching Waymo's expert ground-truth RFS. The final Poutine model achieves an RFS of 7.99 on the official Waymo test set, placing 1st in the 2025 Waymo Vision-Based End-to-End Driving Challenge by a significant margin. These results highlight the promise of scalable VLT pre-training and lightweight RL fine-tuning to enable robust and generalizable autonomy.

2025-06-12

ArXiv (preprint)

Poutine: Vision-Language-Trajectory Pre-Training and Reinforcement Learning Post-Training Enable Robust End-to-End Autonomous Driving

Luke Rowe

Rodrigue De Schaetzen

Roger Girgis

2025-06-12

ArXiv (preprint)

Spaced Scheduling for Large Language Model Training

Amine El hattami

Nicolas Chapados

2025-06-09

TMLR (accepted)

Ctrl-Crash: Controllable Diffusion for Realistic Car Crashes

Anthony Gosselin

Ge Ya Luo

Luis Lara

Florian Golemo

Derek Nowrouzezahrai

Alexia Jolicoeur-Martineau

Video diffusion techniques have advanced significantly in recent years; however, they struggle to generate realistic imagery of car crashes … (see more)due to the scarcity of accident events in most driving datasets. Improving traffic safety requires realistic and controllable accident simulations. To tackle the problem, we propose Ctrl-Crash, a controllable car crash video generation model that conditions on signals such as bounding boxes, crash types, and an initial image frame. Our approach enables counterfactual scenario generation where minor variations in input can lead to dramatically different crash outcomes. To support fine-grained control at inference time, we leverage classifier-free guidance with independently tunable scales for each conditioning signal. Ctrl-Crash achieves state-of-the-art performance across quantitative video quality metrics (e.g., FVD and JEDi) and qualitative measurements based on a human-evaluation of physical realism and video quality compared to prior diffusion-based methods.

2025-06-01

arXiv (published)

Ctrl-Crash: Controllable Diffusion for Realistic Car Crashes

Anthony Gosselin

Ge Ya Luo

Luis Lara

Florian Golemo

Derek Nowrouzezahrai

Alexia Jolicoeur-Martineau

2025-05-30

ArXiv (preprint)

Rendering-Aware Reinforcement Learning for Vector Graphics Generation

Juan A. Rodriguez

Haotian Zhang

Abhay Puri

Aarash Feizi

Rishav Pramanik

Pascal Wichmann

Arnab Mondal

Mohammad Reza Samsami

Rabiul Awal

Perouz Taslakian

Spandana Gella

Sai Rajeswar

David Vazquez

Marco Pedersoli

Scalable Vector Graphics (SVG) offer a powerful format for representing visual designs as interpretable code. Recent advances in vision-lang… (see more)uage models (VLMs) have enabled high-quality SVG generation by framing the problem as a code generation task and leveraging large-scale pretraining. VLMs are particularly suitable for this task as they capture both global semantics and fine-grained visual patterns, while transferring knowledge across vision, natural language, and code domains. However, existing VLM approaches often struggle to produce faithful and efficient SVGs because they never observe the rendered images during training. Although differentiable rendering for autoregressive SVG code generation remains unavailable, rendered outputs can still be compared to original inputs, enabling evaluative feedback suitable for reinforcement learning (RL). We introduce RLRF(Reinforcement Learning from Rendering Feedback), an RL method that enhances SVG generation in autoregressive VLMs by leveraging feedback from rendered SVG outputs. Given an input image, the model generates SVG roll-outs that are rendered and compared to the original image to compute a reward. This visual fidelity feedback guides the model toward producing more accurate, efficient, and semantically coherent SVGs. RLRF significantly outperforms supervised fine-tuning, addressing common failure modes and enabling precise, high-quality SVG generation with strong structural understanding and generalization.

2025-05-27

ArXiv (preprint)