Publications

AIFM-ed Curriculum Framework for Postgraduate Family Medicine Education on Artificial Intelligence: Mixed Methods Study
Raymond Tolentino
Fanny Hersson-Edery
Mark Yaffe
Samira Abbasgholizadeh-Rahimi
As health care moves to a more digital environment, there is a growing need to train future family doctors on the clinical uses of artificia… (see more)l intelligence (AI). However, family medicine training in AI has often been inconsistent or lacking. The aim of the study is to develop a curriculum framework for family medicine postgraduate education on AI called “Artificial Intelligence Training in Postgraduate Family Medicine Education” (AIFM-ed). First, we conducted a comprehensive scoping review on existing AI education frameworks guided by the methodological framework developed by Arksey and O’Malley and Joanna Briggs Institute methodological framework for scoping reviews. We adhered to the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) checklist for reporting the results. Next, 2 national expert panels were conducted. Panelists included family medicine educators and residents knowledgeable in AI from family medicine residency programs across Canada. Participants were purposively sampled, and panels were held via Zoom, recorded, and transcribed. Data were analyzed using content analysis. We followed the Standards for Reporting Qualitative Research for panels. An integration of the scoping review results and 2 panel discussions of 14 participants led to the development of the AIFM-ed curriculum framework for AI training in postgraduate family medicine education with five key elements: (1) need and purpose of the curriculum, (2) learning objectives, (3) curriculum content, (4) organization of curriculum content, and (5) implementation aspects of the curriculum. Using the results of this study, we developed the AIFM-ed curriculum framework for AI training in postgraduate family medicine education. This framework serves as a structured guide for integrating AI competencies into medical education, ensuring that future family physicians are equipped with the necessary skills to use AI effectively in their clinical practice. Future research should focus on the validation and implementation of the AIFM-ed framework within family medicine education. Institutions also are encouraged to consider adapting the AIFM-ed framework within their own programs, tailoring it to meet the specific needs of their trainees and health care environments.
2025-04-24
JMIR Medical Education (published)
doi.org
RLeXplore: Accelerating Research in Intrinsically-Motivated Reinforcement Learning
Mingqi Yuan
Roger Creus Castanyer
Bin Li
Xin Jin
Glen Berseth
Wenjun Zeng
2025-04-24
Transactions on Machine Learning Research (accepted)
doi.org
openreview.net
A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning
Prateek Yadav
Colin Raffel
Mohammed Muqeeth
Lucas Caccia
Haokun Liu
Tianlong Chen
Mohit Bansal
Leshem Choshen
Alessandro Sordoni
The availability of performant pre-trained models has led to a proliferation of fine-tuned expert models that are specialized to a particula… (see more)r domain or task. Model MoErging methods aim to recycle expert models to create an aggregate system with improved performance or generalization. A key component of MoErging methods is the creation of a router that decides which expert model(s) to use for a particular input or application. The promise, effectiveness, and large design space of MoErging has spurred the development of many new methods over the past few years. This rapid pace of development has made it challenging to compare different MoErging methods, which are rarely compared to one another and are often validated in different experimental setups. To remedy such gaps, we present a comprehensive survey of MoErging methods that includes a novel taxonomy for cataloging key design choices and clarifying suitable applications for each method. Apart from surveying MoErging research, we inventory software tools and applications that make use of MoErging. We additionally discuss related fields of study such as model merging, multitask learning, and mixture-of-experts models. Taken as a whole, our survey provides a unified overview of existing MoErging methods and creates a solid foundation for future work in this burgeoning field.
2025-04-24
TMLR (accepted)
doi.org
openreview.net
3DMolFormer: A Dual-Channel Framework for Structure-Based Drug Discovery
Xiuyuan Hu
Guoqing Liu
Can (Sam) Chen
Yang Zhao
Hao Zhang
Xue Liu
Structure-based drug discovery, encompassing the tasks of protein-ligand docking and pocket-aware 3D drug design, represents a core challeng… (see more)e in drug discovery. However, no existing work can deal with both tasks to effectively leverage the duality between them, and current methods for each task are hindered by challenges in modeling 3D information and the limitations of available data. To address these issues, we propose 3DMolFormer, a unified dual-channel transformer-based framework applicable to both docking and 3D drug design tasks, which exploits their duality by utilizing docking functionalities within the drug design process. Specifically, we represent 3D pocket-ligand complexes using parallel sequences of discrete tokens and continuous numbers, and we design a corresponding dual-channel transformer model to handle this format, thereby overcoming the challenges of 3D information modeling. Additionally, we alleviate data limitations through large-scale pre-training on a mixed dataset, followed by supervised and reinforcement learning fine-tuning techniques respectively tailored for the two tasks. Experimental results demonstrate that 3DMolFormer outperforms previous approaches in both protein-ligand docking and pocket-aware 3D drug design, highlighting its promising application in structure-based drug discovery. The code is available at: https://github.com/HXYfighter/3DMolFormer .
2025-04-22
International Conference on Learning Representations (Accept (Poster))
doi.org
openreview.net
Accelerating Training with Neuron Interaction and Nowcasting Networks
Boris Knyazev
Abhinav Moudgil
Guillaume Lajoie
Eugene Belilovsky
Simon Lacoste-Julien
Neural network training can be accelerated when a learnable update rule is used in lieu of classic adaptive optimizers (e.g. Adam). However,… (see more) learnable update rules can be costly and unstable to train and use. Recently, Jang et al. (2023) proposed a simpler approach to accelerate training based on weight nowcaster networks (WNNs). In their approach, Adam is used for most of the optimization steps and periodically, only every few steps, a WNN nowcasts (predicts near future) parameters. We improve WNNs by proposing neuron interaction and nowcasting (NiNo) networks. In contrast to WNNs, NiNo leverages neuron connectivity and graph neural networks to more accurately nowcast parameters. We further show that in some networks, such as Transformers, modeling neuron connectivity accurately is challenging. We address this and other limitations, which allows NiNo to accelerate Adam training by up to 50% in vision and language tasks.
2025-04-22
International Conference on Learning Representations (Accept (Poster))
doi.org
openreview.net
AdaFisher: Adaptive Second Order Optimization via Fisher Information
Damien Martins Gomes
Yanlei Zhang
Eugene Belilovsky
Guy Wolf
Mahdi S. Hosseini
First-order optimization methods are currently the mainstream in training deep neural networks (DNNs). Optimizers like Adam incorporate limi… (see more)ted curvature information by employing the diagonal matrix preconditioning of the stochastic gradient during the training. Despite their widespread, second-order optimization algorithms exhibit superior convergence properties compared to their first-order counterparts e.g. Adam and SGD. However, their practicality in training DNNs is still limited due to increased per-iteration computations compared to the first-order methods. We present \emph{AdaFisher}--an adaptive second-order optimizer that leverages a \emph{diagonal block-Kronecker} approximation of the Fisher information matrix for adaptive gradient preconditioning. AdaFisher aims to bridge the gap between enhanced \emph{convergence/generalization} capabilities and computational efficiency in second-order optimization framework for training DNNs. Despite the slow pace of second-order optimizers, we showcase that AdaFisher can be reliably adopted for image classification, language modeling and stands out for its stability and robustness in hyper-parameter tuning. We demonstrate that AdaFisher \textbf{outperforms the SOTA optimizers} in terms of both accuracy and convergence speed. Code is available from https://github.com/AtlasAnalyticsLab/AdaFisher.
2025-04-22
International Conference on Learning Representations (Accept (Poster))
doi.org
openreview.net
Adaptive Teachers for Amortized Samplers
Minsu Kim
Sanghyeok Choi
Taeyoung YUN
Emmanuel Bengio
Leo Feng
Jarrid Rector-Brooks
Sungsoo Ahn
Jinkyoo Park
Nikolay Malkin
Yoshua Bengio
Amortized inference is the task of training a parametric model, such as a neural network, to approximate a distribution with a given unnorma… (see more)lized density where exact sampling is intractable. When sampling is implemented as a sequential decision-making process, reinforcement learning (RL) methods, such as generative flow networks, can be used to train the sampling policy. Off-policy RL training facilitates the discovery of diverse, high-reward candidates, but existing methods still face challenges in efficient exploration. We propose to use an adaptive training distribution (the \teacher) to guide the training of the primary amortized sampler (the \student). The \teacher, an auxiliary behavior model, is trained to sample high-loss regions of the \student and can generalize across unexplored modes, thereby enhancing mode coverage by providing an efficient training curriculum. We validate the effectiveness of this approach in a synthetic environment designed to present an exploration challenge, two diffusion-based sampling tasks, and four biochemical discovery tasks demonstrating its ability to improve sample efficiency and mode coverage. Source code is available at https://github.com/alstn12088/adaptive-teacher.
2025-04-22
International Conference on Learning Representations (Accept (Poster))
doi.org
openreview.net
AIMS.au: A Dataset for the Analysis of Modern Slavery Countermeasures in Corporate Statements
Adriana Eufrosina Bora
Pierre-Luc St-Charles
Mirko Bronzi
Arsène Fansi Tchango
Bruno Rousseau
Kerrie Mengersen
Despite over a decade of legislative efforts to address modern slavery in the supply chains of large corporations, the effectiveness of gove… (see more)rnment oversight remains hampered by the challenge of scrutinizing thousands of statements annually. While Large Language Models (LLMs) can be considered a well established solution for the automatic analysis and summarization of documents, recognizing concrete modern slavery countermeasures taken by companies and differentiating those from vague claims remains a challenging task. To help evaluate and fine-tune LLMs for the assessment of corporate statements, we introduce a dataset composed of 5,731 modern slavery statements taken from the Australian Modern Slavery Register and annotated at the sentence level. This paper details the construction steps for the dataset that include the careful design of annotation specifications, the selection and preprocessing of statements, and the creation of high-quality annotation subsets for effective model evaluations. To demonstrate our dataset's utility, we propose a machine learning methodology for the detection of sentences relevant to mandatory reporting requirements set by the Australian Modern Slavery Act. We then follow this methodology to benchmark modern language models under zero-shot and supervised learning settings.
2025-04-22
International Conference on Learning Representations (Accept (Poster))
doi.org
openreview.net
Algorithmic Fairness Through the Lens of Metrics and Evaluation (AFME) 2024
Miriam Rateike
Awa Dieng
Jamelle Watson-Daniels
Ferdinando Fioretto
Golnoosh Farnadi
2025-04-22
Proceedings of the Algorithmic Fairness Through the Lens of Metrics and Evaluation (published)
proceedings.mlr.press
proceedings.mlr.press
AssembleFlow: Rigid Flow Matching with Inertial Frames for Molecular Assembly
Hongyu Guo
Yoshua Bengio
Shengchao Liu
2025-04-22
International Conference on Learning Representations (Accept (Poster))
openreview.net
openreview.net
Beyond FVD: An Enhanced Metric for Evaluating Video Generation Distribution Quality
Ge Ya Luo
Gian Mario Favero
Zhi Hao Luo
Alexia Jolicoeur-Martineau
Christopher Pal
The Fréchet Video Distance (FVD) is a widely adopted metric for evaluating video generation distribution quality. However, its effectivenes… (see more)s relies on critical assumptions. Our analysis reveals three significant limitations: (1) the non-Gaussianity of the Inflated 3D Convnet (I3D) feature space; (2) the insensitivity of I3D features to temporal distortions; (3) the impractical sample sizes required for reliable estimation. These findings undermine FVD's reliability and show that FVD falls short as a standalone metric for video generation evaluation. After extensive analysis of a wide range of metrics and backbone architectures, we propose JEDi, the JEPA Embedding Distance, based on features derived from a Joint Embedding Predictive Architecture, measured using Maximum Mean Discrepancy with polynomial kernel. Our experiments on multiple open-source datasets show clear evidence that it is a superior alternative to the widely used FVD metric, requiring only 16% of the samples to reach its steady value, while increasing alignment with human evaluation by 34%, on average.Project page: https://oooolga.github.io/JEDi.github.io/.
2025-04-22
ICLR (Accept (Poster))
openreview.net
openreview.net
Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification
Yunzhen Feng
Elvis Dohmatob
Pu Yang
Francois Charton
Julia Kempe
Large Language Models (LLM) are increasingly trained on data generated by other LLM, either because generated text and images become part of… (see more) the pre-training corpus, or because synthetized data is used as a replacement for expensive human-annotation. This raises concerns about \emph{model collapse}, a drop in model performance when their training sets include generated data. Considering that it is easier for both humans and machines to tell between good and bad examples than to generate high-quality samples, we investigate the use of verification on synthesized data to prevent model collapse. We provide a theoretical characterization using Gaussian mixtures, linear classifiers, and linear verifiers to derive conditions with measurable proxies to assess whether the verifier can effectively select synthesized data that leads to optimal performance. We experiment with two practical tasks -- computing matrix eigenvalues with transformers and news summarization with LLMs -- which both exhibit model collapse when trained on generated data, and show that verifiers, even imperfect ones, can indeed be harnessed to prevent model collapse and that our proposed proxy measure strongly correlates with performance.
2025-04-22
International Conference on Learning Representations (Accept (Poster))
doi.org
openreview.net