Publications

Increasing the Utility of Synthetic Images through Chamfer Guidance
Nicola Dall'Asen
Xiaofeng Zhang
Reyhane Askari Hemmat
Melissa Hall
Jakob Verbeek
Adriana Romero Soriano
Michal Drozdzal
Conditional image generative models hold considerable promise to produce infinite amounts of synthetic training data. Yet, recent progress i… (see more)n generation quality has come at the expense of generation diversity, limiting the utility of these models as a source of synthetic training data. Although guidance-based approaches have been introduced to improve the utility of generated data by focusing on quality or diversity, the (implicit or explicit) utility functions oftentimes disregard the potential distribution shift between synthetic and real data. In this work, we introduce Chamfer Guidance: a training-free guidance approach which leverages a handful of real exemplar images to characterize the quality and diversity of synthetic data. We show that by leveraging the proposed Chamfer Guidance, we can boost the diversity of the generations w.r.t. a dataset of real images while maintaining or improving the generation quality on ImageNet-1k and standard geo-diversity benchmarks. Our approach achieves state-of-the-art few-shot performance with as little as 2 exemplar real images, obtaining 96.4\% in terms of precision, and 86.4\% in terms of distributional coverage, which increase to 97.5\% and 92.7\%, respectively, when using 32 real images. We showcase the benefits of the Chamfer Guidance generation by training downstream image classifiers on synthetic data, achieving accuracy boost of up to 15\% for in-distribution over the baselines, and up to 16\% in out-of-distribution. Furthermore, our approach does not require using the unconditional model, and thus obtains a 31\% reduction in FLOPs w.r.t. classifier-free-guidance-based approaches at sampling time.
2025-08-14
ArXiv (preprint)
doi.org
arxiv.org
Street Review: A Participatory AI-Based Framework for Assessing Streetscape Inclusivity
Rashid A. Mushkani
Shin (Alexandre) Koseki
2025-08-14
ArXiv (preprint)
doi.org
arxiv.org
Street Review: A Participatory AI-Based Framework for Assessing Streetscape Inclusivity
Rashid A. Mushkani
Shin (Alexandre) Koseki
Urban centers undergo social, demographic, and cultural changes that shape public street use and require systematic evaluation of public spa… (see more)ces. This study presents Street Review, a mixed-methods approach that combines participatory research with AI-based analysis to assess streetscape inclusivity. In Montr\'eal, Canada, 28 residents participated in semi-directed interviews and image evaluations, supported by the analysis of approximately 45,000 street-view images from Mapillary. The approach produced visual analytics, such as heatmaps, to correlate subjective user ratings with physical attributes like sidewalk, maintenance, greenery, and seating. Findings reveal variations in perceptions of inclusivity and accessibility across demographic groups, demonstrating that incorporating diverse user feedback can enhance machine learning models through careful data-labeling and co-production strategies. The Street Review framework offers a systematic method for urban planners and policy analysts to inform planning, policy development, and management of public streets.
2025-08-14
ArXiv (preprint)
doi.org
arxiv.org
The Interpolation Constraint in the RV Analysis of M Dwarfs Using Empirical Templates
Dhvani Doshi
Nicolas B. Cowan
E. Artigau
René Doyon
Andr'e M. Silva
K. Al Moulla
Yashar Hezaveh
Precise radial velocity (pRV) measurements of M dwarfs in the near-infrared rely on empirical templates due to the lack of accurate stellar … (see more)spectral models in this regime. Templates are assumed to approximate the true spectrum when constructed from many observations or in the high signal-to-noise limit. We develop a numerical simulation that generates SpectroPolarimètre InfraRouge (SPIRou)-like pRV observations from PHOENIX spectra, constructs empirical templates, and estimates radial velocities (RVs). This simulation solely considers photon noise and evaluates when empirical templates remain reliable for pRV analysis. Our results reveal a previously unrecognized noise source in templates created from stacking registered observations, establishing a noise floor for such template-based pRV measurements. We find that these templates inherently include distortions in stellar line shapes due to imperfect interpolation at the detector’s sampling resolution. The magnitude of this interpolation error depends on sampling resolution and RV content. Consequently, for stars with higher RV content, such as cooler M dwarfs, interpolation noise has a larger relative impact, making their performance comparable to hotter M dwarfs when using detectors with low sampling. For a typical M4V star, SPIRou’s spectral and sampling resolution imposes an RV uncertainty floor of 0.5–0.8 m s−1, independent of the star’s magnitude or the telescope’s aperture. These findings reveal a limitation of template-based pRV methods, underscoring the need for improved spectral modeling and better-than-Nyquist detector sampling to reach the next level of RV precision.
2025-08-14
ArXiv (preprint)
doi.org
arxiv.org
Nested-ReFT: Efficient Reinforcement Learning for Large Language Model Fine-Tuning via Off-Policy Rollouts
Maxime Heuillet
Yufei Cui
Boxing Chen
Audrey Durand
Prasanna Parthasarathi
2025-08-13
ArXiv (preprint)
doi.org
arxiv.org
Pathfinding: a neurodynamical account of intuition
Steven Kotler
Michael Mannino
Karl Friston
Gyorgy Buzsáki
J. A. Scott Kelso
Guillaume Dumas
2025-08-13
Communications Biology (published)
doi.org
WeDesign: Generative AI-Facilitated Community Consultations for Urban Public Space Design
Rashid A. Mushkani
Hugo Berard
Shin (Alexandre) Koseki
2025-08-13
ArXiv (preprint)
doi.org
arxiv.org
WeDesign: Generative AI-Facilitated Community Consultations for Urban Public Space Design
Rashid A. Mushkani
Hugo Berard
Shin (Alexandre) Koseki
Community consultations are integral to urban planning processes intended to incorporate diverse stakeholder perspectives. However, limited … (see more)resources, visual and spoken language barriers, and uneven power dynamics frequently constrain inclusive decision-making. This paper examines how generative text-to-image methods, specifically Stable Diffusion XL integrated into a custom platform (WeDesign), may support equitable consultations. A half-day workshop in Montreal involved five focus groups, each consisting of architects, urban designers, AI specialists, and residents from varied demographic groups. Additional data was gathered through semi-structured interviews with six urban planning professionals. Participants indicated that immediate visual outputs facilitated creativity and dialogue, yet noted issues in visualizing specific needs of marginalized groups, such as participants with reduced mobility, accurately depicting local architectural elements, and accommodating bilingual prompts. Participants recommended the development of an open-source platform incorporating in-painting tools, multilingual support, image voting functionalities, and preference indicators. The results indicate that generative AI can broaden participation and enable iterative interactions but requires structured facilitation approaches. The findings contribute to discussions on generative AI's role and limitations in participatory urban design.
2025-08-13
ArXiv (preprint)
doi.org
arxiv.org
A Guide to Robust Generalization: The Impact of Architecture, Pre-training, and Optimization Strategy
Maxime Heuillet
Rishika Bhagwatkar
Jonas Ngnawe
Yann Batiste Pequignot
Alexandre Larouche
Christian Gagné
Irina Rish
Ola Ahmad
Audrey Durand
Deep learning models operating in the image domain are vulnerable to small input perturbations. For years, robustness to such perturbations … (see more)was pursued by training models from scratch (i.e., with random initializations) using specialized loss objectives. Recently, robust fine-tuning has emerged as a more efficient alternative: instead of training from scratch, pretrained models are adapted to maximize predictive performance and robustness. To conduct robust fine-tuning, practitioners design an optimization strategy that includes the model update protocol (e.g., full or partial) and the specialized loss objective. Additional design choices include the architecture type and size, and the pretrained representation. These design choices affect robust generalization, which is the model's ability to maintain performance when exposed to new and unseen perturbations at test time. Understanding how these design choices influence generalization remains an open question with significant practical implications. In response, we present an empirical study spanning 6 datasets, 40 pretrained architectures, 2 specialized losses, and 3 adaptation protocols, yielding 1,440 training configurations and 7,200 robustness measurements across five perturbation types. To our knowledge, this is the most diverse and comprehensive benchmark of robust fine-tuning to date. While attention-based architectures and robust pretrained representations are increasingly popular, we find that convolutional neural networks pretrained in a supervised manner on large datasets often perform best. Our analysis both confirms and challenges prior design assumptions, highlighting promising research directions and offering practical guidance.
2025-08-12
ArXiv (preprint)
doi.org
arxiv.org
Multi-Modal Protein Representation Learning with CLASP
Nicolas Bolouri
Joseph Szymborski
Amin Emad
2025-08-12
bioRxiv (preprint)
doi.org
The Impact of a Pediatric Surgery Fundamentals Boot Camp on New Surgical Trainees' Perceived Knowledge and Confidence Levels.
Julia Ferreira
Simon Rahman
Fabio Botelho
Farhan Banji
W. A. Igrine
Gianluca Bertolizio
Sam Daniel
Thomas Engelhardt
Chantal Frigon
Lily H P Nguyen
Catherine Paquet
Dan Poenaru
Pramod Puligandla
Hussein Wissanji
Davinia Withington
Yasmine Yousef
Sherif Emil
2025-08-12
Journal of Pediatric Surgery (published)
doi.org
Deep Reinforcement Learning-Based Intrusion Detection System: Defending Edge Gateways Against Mirai and Gafgyt
Saeid Jamshidi
Amin Nikanjam
Kawser Wazed Nafi
Foutse Khomh
The rapid growth of the Internet of Things (IoT) has transformed industries, resulting in unprecedented opportunities alongside significant … (see more)cybersecurity challenges. Malware, for example, Mirai and Gafgyt, exploits IoT vulnerabilities, leading to large-scale attacks. Traditional Intrusion Detection Systems (IDS) struggle to detect these evolving threats due to their reliance on static rule-based or classic Machine Learning (ML) models, which lack adaptability to zero-day attacks and dynamic traffic patterns. This paper presents EdgeShield-DRL, a novel Deep Reinforcement Learning (DRL)-based IDS designed for IoT edge gateways. EdgeShield-DRL dynamically detects and mitigates evolving threats in real-time while ensuring efficient operation on resource-constrained edge devices. We evaluated EdgeShieldDRL on the N-BaIoT dataset, achieving a high detection accuracy of
2025-08-11
2025 12th International Conference on Future Internet of Things and Cloud (FiCloud) (published)
doi.org