Publications

Towards a Mechanistic Explanation of Diffusion Model Generalization
Matthew Niedoba
Berend Zwartsenberg
Kevin Patrick Murphy
Frank N. Wood
We propose a mechanism for diffusion generalization based on local denoising operations. Through analysis of network and empirical denoisers… (voir plus), we identify local inductive biases in diffusion models. We demonstrate that local denoising operations can be used to approximate the optimal diffusion denoiser. Using a collection of patch-based, local empirical denoisers, we construct a denoiser which approximates the generalization behaviour of diffusion model denoisers over forward and reverse diffusion processes.
2025-10-05
Proceedings of the 42nd International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
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 Vázquez
Christopher Pal
Perouz Taslakian
Spandana Gella
Sai Rajeswar
Human Annotator
Autonomous agents that navigate Graphical User Interfaces (GUIs) to automate tasks like document editing and file management can greatly enh… (voir plus)ance computer workflows. While existing research focuses on online settings, desktop environments, critical for many professional and everyday tasks, remain underexplored due to data collection challenges and licensing issues. We introduce UI-Vision, the first comprehensive, license-permissive benchmark for offline, fine-grained evaluation of computer use agents in real-world desktop environments. Unlike online benchmarks, UI-Vision provides: (i) dense, high-quality annotations of human demonstrations, including bounding boxes, UI labels, and action trajectories (clicks, drags, and keyboard inputs) across 83 software applications, and (ii) three fine-to-coarse grained tasks—Element Grounding, Layout Grounding, and Action Prediction—with well-defined metrics to rigorously evaluate agents’ performance in desktop environments. Our evaluation reveals critical limitations in state-of-the-art models like UI-TARS-72B, including issues with understanding professional software, spatial reasoning, and complex actions like drag-and-drop. These findings highlight the challenges in developing fully autonomous computer-use agents. With UI-Vision, we aim to advance the development of more capable agents for real-world desktop tasks.
2025-10-05
Proceedings of the 42nd International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
When to retrain a machine learning model
Florence Regol
Leo Schwinn
Kyle Sprague
Mark J. Coates
Thomas Markovich
A significant challenge in maintaining real-world machine learning models is responding to the continuous and unpredictable evolution of dat… (voir plus)a. Most practitioners are faced with the difficult question: when should I retrain or update my machine learning model? This seemingly straightforward problem is particularly challenging for three reasons: 1) decisions must be made based on very limited information - we usually have access to only a few examples, 2) the nature, extent, and impact of the distribution shift are unknown, and 3) it involves specifying a cost ratio between retraining and poor performance, which can be hard to characterize. Existing works address certain aspects of this problem, but none offer a comprehensive solution. Distribution shift detection falls short as it cannot account for the cost trade-off; the scarcity of the data, paired with its unusual structure, makes it a poor fit for existing offline reinforcement learning methods, and the online learning formulation overlooks key practical considerations. To address this, we present a principled formulation of the retraining problem and propose an uncertainty-based method that makes decisions by continually forecasting the evolution of model performance evaluated with a bounded metric. Our experiments, addressing classification tasks, show that the method consistently outperforms existing baselines on 7 datasets. We thoroughly assess its robustness to varying cost trade-off values and mis-specified cost trade-offs.
2025-10-05
Proceedings of the 42nd International Conference on Machine Learning (publié)
proceedings.mlr.press
proceedings.mlr.press
Democratizing Game Modding with GenAI: A Case Study of StarCharM, a Stardew Valley Character Maker
Hamid Zand Miralvand
Mohammad Ronagh Nikghalb
Mohammad Darandeh
Abidullah Khan
Ian Arawjo
Jinghui Cheng
Game modding offers unique and personalized gaming experiences, but the technical complexity of creating mods often limits participation to … (voir plus)skilled users. We envision a future where every player can create personalized mods for their games. To explore this space, we designed StarCharM, a GenAI-based non-player character (NPC) creator for Stardew Valley. Our tool enables players to iteratively create new NPC mods, requiring minimal user input while allowing for fine-grained adjustments through user control. We conducted a user study with ten Stardew Valley players who had varied mod usage experiences to understand the impacts of StarCharM and provide insights into how GenAI tools may reshape modding, particularly in NPC creation. Participants expressed excitement in bringing their character ideas to life, although they noted challenges in generating rich content to fulfill complex visions. While they believed GenAI tools like StarCharM can foster a more diverse modding community, some voiced concerns about diminished originality and community engagement that may come with such technology. Our findings provided implications and guidelines for the future of GenAI-powered modding tools and co-creative modding practices.
2025-10-04
Proceedings of the ACM on Human-Computer Interaction (publié)
doi.org
arxiv.org
Refactoring with LLMs: Bridging Human Expertise and Machine Understanding
Yonnel Chen Kuang Piao
Jean Carlors Paul
Leuson Da Silva
Arghavan Moradi Dakhel
Mohammad Hamdaqa
Foutse Khomh
2025-10-03
ArXiv (prépublication)
doi.org
arxiv.org
Capacity Planning in Stable Matching
Federico Bobbio
Margarida Carvalho
Andrea Lodi
Ignacio Rios
Alfredo Torrico
We introduce the problem of jointly increasing school capacities and finding a student-optimal assignment in the expanded market. Due to the… (voir plus) impossibility of efficiently solving the problem with classical methods, we generalize existent mathematical programming formulations of stability constraints to our setting, most of which result in integer quadratically-constrained programs. In addition, we propose a novel mixed-integer linear programming formulation that is exponentially large on the problem size. We show that its stability constraints can be separated by exploiting the objective function, leading to an effective cutting-plane algorithm. We conclude the theoretical analysis of the problem by discussing some mechanism properties. On the computational side, we evaluate the performance of our approaches in a detailed study, and we find that our cutting-plane method outperforms our generalization of existing mixed-integer approaches. We also propose two heuristics that are effective for large instances of the problem. Finally, we use the Chilean school choice system data to demonstrate the impact of capacity planning under stability conditions. Our results show that each additional seat can benefit multiple students and that we can effectively target the assignment of previously unassigned students or improve the assignment of several students through improvement chains. These insights empower the decision-maker in tuning the matching algorithm to provide a fair application-oriented solution.
2025-10-02
Operations Research (publié)
doi.org
arxiv.org
Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoning
Jiashun Liu
Johan Samir Obando Ceron
Han Lu
Yancheng He
Weixun Wang
Wenbo Su
Bo Zheng
Pablo Samuel Castro
Aaron Courville
Ling Pan
Most recent RL for LLMs (RL4LLM) methods avoid explicit critics, replacing them with average advantage baselines. This shift is largely prag… (voir plus)matic: conventional value functions are computationally expensive to train at LLM scale and often fail under sparse rewards and long reasoning horizons. We revisit this bottleneck from an architectural perspective and introduce Asymmetric Proximal Policy Optimization (AsyPPO), a simple and scalable framework that restores the critics role while remaining efficient in large-model settings. AsyPPO employs a set of lightweight mini-critics, each trained on disjoint prompt shards. This design encourages diversity while preserving calibration, reducing value-estimation bias. Beyond robust estimation, AsyPPO leverages inter-critic uncertainty to refine the policy update: (i) masking advantages in states where critics agree and gradients add little learning signal, and (ii) filtering high-divergence states from entropy regularization, suppressing spurious exploration. After training on open-source data with only 5,000 samples, AsyPPO consistently improves learning stability and performance across multiple benchmarks over strong baselines, such as GRPO, achieving performance gains of more than six percent on Qwen3-4b-Base and about three percent on Qwen3-8b-Base and Qwen3-14b-Base over classic PPO, without additional tricks. These results highlight the importance of architectural innovations for scalable, efficient algorithms.
2025-10-01
ArXiv (prépublication)
doi.org
arxiv.org
Genetic contribution to asthma informs acute chest syndrome pathophysiology and risk stratification
Sara El Aouhel
Vanessa Bellegarde
Stennio Da
Silva Faria
Tristan St-Laurent
Estelle Lecluze
Anne-Laure Pham Hung d’Alexandry d’Orengiani
F. Galactéros
Pablo Bartolucci
Marc-André Legault
Guillaume Lettre
Thomas Pincez
2025-10-01
medRxiv (prépublication)
doi.org
GRACE: A Language Model Framework for Explainable Inverse Reinforcement Learning
Silvia Sapora
R Devon Hjelm
Alexander T Toshev
Omar Attia
Bogdan Mazoure
Inverse Reinforcement Learning aims to recover reward models from expert demonstrations, but traditional methods yield"black-box"models that… (voir plus) are difficult to interpret and debug. In this work, we introduce GRACE (Generating Rewards As CodE), a method for using Large Language Models within an evolutionary search to reverse-engineer an interpretable, code-based reward function directly from expert trajectories. The resulting reward function is executable code that can be inspected and verified. We empirically validate GRACE on the BabyAI and AndroidWorld benchmarks, where it efficiently learns highly accurate rewards, even in complex, multi-task settings. Further, we demonstrate that the resulting reward leads to strong policies, compared to both competitive Imitation Learning and online RL approaches with ground-truth rewards. Finally, we show that GRACE is able to build complex reward APIs in multi-task setups.
2025-10-01
ArXiv (prépublication)
doi.org
arxiv.org
Attention-Based Multi-Agent RL for Multi-Machine Tending Using Mobile Robots
Abdalwhab Bakheet Mohamed Abdalwhab
Giovanni Beltrame
Samira Ebrahimi Kahou
David St-Onge
Robotics can help address the growing worker shortage challenge of the manufacturing industry. As such, machine tending is a task collaborat… (voir plus)ive robots can tackle that can also greatly boost productivity. Nevertheless, existing robotics systems deployed in that sector rely on a fixed single-arm setup, whereas mobile robots can provide more flexibility and scalability. We introduce a multi-agent multi-machine-tending learning framework using mobile robots based on multi-agent reinforcement learning (MARL) techniques, with the design of a suitable observation and reward. Moreover, we integrate an attention-based encoding mechanism into the Multi-Agent Proximal Policy Optimization (MAPPO) algorithm to boost its performance for machine-tending scenarios. Our model (AB-MAPPO) outperforms MAPPO in this new challenging scenario in terms of task success, safety, and resource utilization. Furthermore, we provided an extensive ablation study to support our design decisions.
2025-09-30
AI (publié)
doi.org
Combining virtual reality and hypnosis to alleviate chronic pain in elderly with hand arthritis: protocol for a randomised phase II clinical trial
Valentyn Fournier
Marie-Fania Simard
Sai Yan Yuen
Joséphine Guiné
Floriane Rousseaux
Julie Lebeau
Karim Jerbi
Philippe Richebé
Mathieu Landry
Pierre Rainville
David Ogez
Chronic pain is a common health condition that significantly impacts the quality of life of those affected, affecting one in five people in … (voir plus)Canada. The prevalence of this condition tends to increase with age, making it a major health issue given the ageing population. However, its management remains inadequate and requires significant mobilisation of healthcare professionals as well as the development of multiple therapeutic solutions. Among these, non-pharmacological interventions such as hypnosis and virtual reality have proven effective. Nevertheless, while the existing literature seems promising, it presents methodological limitations. Therefore, this study aims to assess the effectiveness of an intervention combining virtual reality and hypnosis in an ageing population suffering from a widespread chronic pain condition, that is, hand arthritis. This study will be a single-centre randomised clinical trial. Participants will be randomly assigned to one of two conditions: one receiving an intervention combining virtual reality and hypnosis, and the other receiving only virtual reality. The effectiveness of the intervention on current perceived pain before and after the intervention (primary outcome) will be evaluated. Secondary outcomes will include anxiety and depressive symptoms, quality of life, relaxation and fatigue. Exploratory analyses will also be conducted to contribute to the emerging literature by examining physiological variables such as heart rate variability, respiratory rate and electrodermal activity during the intervention, and their relationship with primary and secondary outcomes. The project was approved by the Research Ethical Committee of the Hospital Maisonneuve-Rosemont (Project no 2024-3539). Participants will be asked to provide written consent for their participation. Results from this study will be shared through peer-reviewed publications, as well as oral and poster presentations at scientific events. The protocol for this study was preregistered on Open Science Framework and raw anonymised data will be available on this platform ( https://osf.io/vbh72/?view_only=1d17c5708f894faab6669d85e1fde75d ). NCT06833905 .
2025-09-30
BMJ Open (publié)
doi.org
Current landscape of clinical genetics knowledge and attitudes among Non-Geneticist Physicians - the McGill genetics education survey (McGES).
Sarah Abdullah-Maklan
Yannis Trakadis
2025-09-30
Journal of Community Genetics (publié)
doi.org