Publications

The 1st International Workshop on Graph Foundation Models (GFM).
Haitao Mao
Jianan Zhao
Xiaoxin He
Zhikai Chen
Qian Huang
Zhaocheng Zhu
Jian Tang
Micheal Bronstein
Xavier Bresson
Bryan Hooi
Haiyang Zhang
Xianfeng Tang
Luo Chen
Jiliang Tang
Foundation models such as GPT-4 for natural language processing (NLP), Flamingo for computer vision (CV), have set new benchmarks in AI by d… (see more)elivering state-of-the-art results across various tasks with minimal task-specific data. Despite their success, the application of these models to the graph domain is challenging due to the relational nature of graph-structured data. To address this gap, we propose the Graph Foundation Model (GFM) Workshop, the first workshop for GFMs, dedicated to exploring the adaptation and development of foundation models specifically designed for graph data. The GFM workshop focuses on two critical questions: (1) How can the underlying capabilities of existing foundation models be effectively applied to graph data? (2) What foundational principles should guide the creation of models tailored to the graph domain? Through a curated set of panel sections, keynote talks, and paper presentations, our workshop intends to catalyze innovative approaches and theoretical frameworks for Graph Foundation Models (GFMs). We target a broad audience, encompassing researchers, practitioners, and students, and aim to lay the groundwork for the next wave of breakthroughs in integrating graph data with foundation models.
2024-05-12
Companion Proceedings of the ACM on Web Conference 2024 (published)
doi.org
Uncertainty-aware hybrid paradigm of nonlinear MPC and model-based RL for offroad navigation: Exploration of transformers in the predictive model
Faraz Lotfi
Khalil Virji
Farnoosh Faraji
Lucas Berry
Andrew Holliday
David Meger
Gregory Dudek
In this paper, we investigate a hybrid scheme that combines nonlinear model predictive control (MPC) and model-based reinforcement learning … (see more)(RL) for navigation planning of an autonomous model car across offroad, unstructured terrains without relying on predefined maps. Our innovative approach takes inspiration from BADGR, an LSTM-based network that primarily concentrates on environment modeling, but distinguishes itself by substituting LSTM modules with transformers to greatly elevate the performance our model. Addressing uncertainty within the system, we train an ensemble of predictive models and estimate the mutual information between model weights and outputs, facilitating dynamic horizon planning through the introduction of variable speeds. Further enhancing our methodology, we incorporate a nonlinear MPC controller that accounts for the intricacies of the vehicle's model and states. The model-based RL facet produces steering angles and quantifies inherent uncertainty. At the same time, the nonlinear MPC suggests optimal throttle settings, striking a balance between goal attainment speed and managing model uncertainty influenced by velocity. In the conducted studies, our approach excels over the existing baseline by consistently achieving higher metric values in predicting future events and seamlessly integrating the vehicle's kinematic model for enhanced decision-making. The code and the evaluation data are available at https://github.com/FARAZLOTFI/offroad_autonomous_navigation/).
2024-05-12
2024 IEEE International Conference on Robotics and Automation (ICRA) (published)
doi.org
arxiv.org
Advancing Fairness in Cardiac Care: Strategies for Mitigating Bias in Artificial Intelligence Models Within Cardiology
Alexis Nolin-Lapalme, BSc
Denis Corbin, MSc
Olivier Tastet, MSc
Robert Avram, MD, MSc
Julie G. Hussin, PhD
2024-05-10
Canadian Journal of Cardiology (published)
doi.org
An AI-Resilient Text Rendering Technique for Reading and Skimming Documents
Ziwei Gu
Ian Arawjo
Kenneth Li
Jonathan K. Kummerfeld
Elena L. Glassman
2024-05-10
Proceedings of the CHI Conference on Human Factors in Computing Systems (published)
doi.org
arxiv.org
ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing
Ian Arawjo
Chelse Swoopes
Priyan Vaithilingam
Martin Wattenberg
Elena L. Glassman
Evaluating outputs of large language models (LLMs) is challenging, requiring making -- and making sense of -- many responses. Yet tools that… (see more) go beyond basic prompting tend to require knowledge of programming APIs, focus on narrow domains, or are closed-source. We present ChainForge, an open-source visual toolkit for prompt engineering and on-demand hypothesis testing of text generation LLMs. ChainForge provides a graphical interface for comparison of responses across models and prompt variations. Our system was designed to support three tasks: model selection, prompt template design, and hypothesis testing (e.g., auditing). We released ChainForge early in its development and iterated on its design with academics and online users. Through in-lab and interview studies, we find that a range of people could use ChainForge to investigate hypotheses that matter to them, including in real-world settings. We identify three modes of prompt engineering and LLM hypothesis testing: opportunistic exploration, limited evaluation, and iterative refinement.
2024-05-10
Proceedings of the CHI Conference on Human Factors in Computing Systems (published)
doi.org
arxiv.org
DirectGPT: A Direct Manipulation Interface to Interact with Large Language Models
Damien Masson
Sylvain Malacria
Géry Casiez
Daniel Vogel
2024-05-10
Proceedings of the CHI Conference on Human Factors in Computing Systems (published)
doi.org
arxiv.org
Schrödinger's Update: User Perceptions of Uncertainties in Proprietary Large Language Model Updates
Zilin Ma
Yiyang Mei
Krzysztof Z. Gajos
Ian Arawjo
2024-05-10
Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (published)
doi.org
Calibration‐free parallel transmission of the cervical, thoracic, and lumbar spinal cord at <scp>7T</scp>
Christoph S. Aigner
Manuel F. Sánchez Alarcon
Alexandre D'Astous
Eva Alonso‐Ortiz
Julien Cohen‐Adad
Sebastian Schmitter
The development of universal shims represents a significant advance by eliminating time‐consuming subject‐specific pTx adjustments. This… (see more) approach is expected to make UHF spinal cord imaging more accessible and user‐friendly, particularly for non‐pTx experts.
2024-05-09
Magnetic Resonance in Medicine (published)
doi.org
Exploring the digital divide: results of a survey informing mobile application development
Maira Corinne Claudio
Zachary Rehany
Katerina Stachtari
Elena Guadagno
Esli Osmanlliu
Dan Poenaru
Introduction Mobile health apps risk widening health disparities if they overlook digital inclusion. The digital divide, encompassing access… (see more), familiarity, and readiness, poses a significant barrier to medical interventions. Existing literature lacks exploration of the digital divide's contributing factors. Hence, data are needed to comprehend the challenges in developing inclusive health apps. Methods We created a survey to gauge internet and smartphone access, smartphone familiarity, and readiness for using mobile health apps among caregivers of pediatric patients in tertiary care. Open-ended questions solicited feedback and suggestions on mobile health applications. Responses were categorized by similarity and compared. Developed with patient partners, the survey underwent cognitive testing and piloting for accuracy. Results Data from 209 respondents showed that 23% were affected by the digital divide, mainly due to unfamiliarity with digital skills. Among 49 short text responses about health app concerns, 31 mentioned security and confidentiality, with 7 mentioning the impersonal nature of such apps. Desired features included messaging healthcare providers, scheduling, task reminders, and simplicity. Conclusions This study underscores a digital divide among caregivers of pediatric patients, with nearly a quarter affected primarily due to a lack of digital comfort. Respondents emphasized user-friendliness and online security for health apps. Future apps should prioritize digital inclusion by addressing the significant barriers and carefully considering patient and family concerns.
2024-05-09
Frontiers Digit. Health (published)
doi.org
G4SATBench: Benchmarking and Advancing SAT Solving with Graph Neural Networks
Zhaoyu Li
Jinpei Guo
Xujie Si
2024-05-09
TMLR (accepted)
doi.org
openreview.net
Repeat it without me: Crowdsourcing the T<sub>1</sub> mapping common ground via the ISMRM reproducibility challenge
Mathieu Boudreau
Agah Karakuzu
Julien Cohen‐Adad
Ecem Bozkurt
Madeline Carr
Marco Castellaro
Luis Concha
Mariya Doneva
Seraina A. Dual
Alex Ensworth
Alexandru Foias
Véronique Fortier
Refaat E. Gabr
Guillaume Gilbert
Carri K. Glide‐Hurst
Matthew Grech‐Sollars
Siyuan Hu
Oscar Jalnefjord
Jorge Jovicich
Kübra Keskin … (see 22 more)
Peter Koken
Anastasia Kolokotronis
Simran Kukran
Nam G. Lee
Ives R. Levesque
Bochao Li
Dan Ma
Burkhard Mädler
Nyasha G. Maforo
Jamie Near
Erick Pasaye
Alonso Ramirez‐Manzanares
Ben Statton
Christian Stehning
Stefano Tambalo
Ye Tian
Chenyang Wang
Kilian Weiss
Niloufar Zakariaei
Shuo Zhang
Ziwei Zhao
Nikola Stikov
Eighteen submissions (39 phantom and 56 human datasets) on scanners by three MRI vendors were collected at 3 T (except one, at 0.35 T). … (see more)The mean coefficient of variation was 6.1% for intersubmission phantom measurements, and 2.9% for intrasubmission measurements. For humans, the intersubmission/intrasubmission coefficient of variation was 5.9/3.2% in the genu and 16/6.9% in the cortex. An interactive dashboard for data visualization was also developed: https://rrsg2020.dashboards.neurolibre.org.The T1 intersubmission variability was twice as high as the intrasubmission variability in both phantoms and human brains, indicating that the acquisition details in the original paper were insufficient to reproduce a quantitative MRI protocol. This study reports the inherent uncertainty in T1 measures across independent research groups, bringing us one step closer to a practical clinical baseline of T1 variations in vivo.
2024-05-09
Magnetic Resonance in Medicine (published)
doi.org
Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems
David Dalrymple
David
Joar Max Viktor Skalse
Yoshua Bengio
Stuart Russell
Max Tegmark
Sanjit A. Seshia
Steve Omohundro
Christian Szegedy
Ben Goldhaber
Nora Ammann
Alessandro Abate
Joe Halpern
Clark Barrett
Ding Zhao
Zhi-Xuan Tan
Jeannette Wing
Joshua B. Tenenbaum
Ensuring that AI systems reliably and robustly avoid harmful or dangerous behaviours is a crucial challenge, especially for AI systems with … (see more)a high degree of autonomy and general intelligence, or systems used in safety-critical contexts. In this paper, we will introduce and define a family of approaches to AI safety, which we will refer to as guaranteed safe (GS) AI. The core feature of these approaches is that they aim to produce AI systems which are equipped with high-assurance quantitative safety guarantees. This is achieved by the interplay of three core components: a world model (which provides a mathematical description of how the AI system affects the outside world), a safety specification (which is a mathematical description of what effects are acceptable), and a verifier (which provides an auditable proof certificate that the AI satisfies the safety specification relative to the world model). We outline a number of approaches for creating each of these three core components, describe the main technical challenges, and suggest a number of potential solutions to them. We also argue for the necessity of this approach to AI safety, and for the inadequacy of the main alternative approaches.
2024-05-09
ArXiv (preprint)
doi.org
arxiv.org