Publications

Reliable dynamic causality analysis for efficient prescriptive maintenance of degraded industrial equipment
Karim Nadim
Ahmed Ragab
Hakim Ghezzaz
Mohamed-Salah Ouali
Developing efficient prescriptive maintenance strategies is essential in mitigating the performance degradation of equipment in energy-inten… (voir plus)sive process industries. This paper proposes an innovative approach that integrates data-driven causality analysis and reinforcement learning (RL) to reduce/slow-down the equipment degradation. The degradation is first modeled by constructing representative health indicators (HIs) using deep learning autoencoders. The HIs are then exploited using clustering and interpretable machine learning techniques to identify the degradation's root causes. Afterward, a dynamic causal model is discovered in the form of a Petri net (PN) using process mining techniques. The causal model incorporates the temporal information and sequential relationships between the identified root causes. Finally, an RL agent is integrated with the PN model to recommend the optimal sequence of events that diminishes the performance degradation rate. The proposed approach is tested successfully on a complex case study of a black liquor concentrator in a Kraft pulp mill that is subjected to a decline in operational performance and capacity due to the fouling degradation phenomenon. The obtained results show that the fouling rate was minimized, leading to an approximate 30 % saving in maintenance costs and a reduction of around 4.8 kt CO2/year in greenhouse gas emissions.
2026-01-19
Journal of Loss Prevention in the Process Industries (publié)
doi.org
Automatic Recursion Elimination using Recurrence Relations for Synthesis of Stack-free Hardware
Adam Musa
Christophe Dubach
High-level Synthesis (HLS) eases hardware design by offering a higher level of abstraction. However, high-level programming concepts, such a… (voir plus)s recursion, are costly to synthesize, if at all possible. Recursion typically relies on a dynamic call stack, whose hardware implementation is resource-intensive and inefficient. Existing approaches solve this issue by replacing recursion with iteration using explicit stack arrays or by detecting specific patterns (e.g., tail recursion) to avoid using the stack. This paper introduces a novel technique for transforming recursive functions into equivalent stack-free iterative implementations. Using static analysis, a recurrence relation is extracted from the function, representing it as a sequence bounded by the order of the relation. This relation is then used to optimize the process of incrementalization, constructing a synthesizable, stackfree version of the function that uses a bounded static array. This approach is evaluated on a set of recursive benchmarks used in prior work. It eliminates recursion from 9 out of 19 benchmarks and achieves a
2026-01-18
Asia and South Pacific Design Automation Conference (publié)
doi.org
<scp>CISO</scp> : Species distribution modelling Conditioned on Incomplete Species Observations
Hager Radi Abdelwahed
Mélisande Teng
Robin Zbinden
Laura Pollock
Hugol Larochelle
D. Tuia
Rolnick David
Species distribution models (SDMs) are widely used to predict species' geographic distributions, serving as critical tools for ecological re… (voir plus)search and conservation planning. Typically, SDMs relate species occurrences to environmental variables representing abiotic factors, such as temperature, precipitation, and soil properties. However, species distributions are also strongly influenced by biotic interactions with other species, which are often overlooked in traditional models. While some methods, such as joint species distribution models (JSDMs), partially address this limitation by incorporating biotic interactions, they often assume symmetrical pairwise relationships between species and require consistent co‐occurrence data. In practice, species observations are often sparse, and the availability of information about the presence or absence of other species varies significantly across locations. To address these challenges, we propose CISO, a deep learning‐based method for species distribution modelling Conditioned on Incomplete Species Observations. CISO enables predictions to be conditioned on a flexible number of species observations alongside environmental variables, accommodating the variability and incompleteness of available biotic data. We demonstrate our approach using three datasets representing different species groups: sPlotOpen for plants, SatBird for birds, and a new dataset, SatButterfly, for butterflies. Our results show that including partial biotic information improves predictive performance on spatially separate test sets. When conditioned on a subset of species within the same dataset, CISO outperforms alternative methods in predicting the distribution of the remaining species for plants and birds. Furthermore, we show that combining and conditioning on observations from multiple datasets can improve the prediction of species occurrences in scenarios with sufficient co‐occurrences between datasets to train CISO effectively. Our results show that CISO is a promising ecological tool, capable of incorporating incomplete biotic information and identifying potential interactions between species from disparate taxa.
2026-01-18
Methods in Ecology and Evolution (publié)
doi.org
Mapping the Perseus galaxy cluster with XRISM
Congyao Zhang
Irina Zhuravleva
Hannah McCall
Elena Bellomi
Nhut Truong
John ZuHone
Eugene Churazov
Megan E. Eckart
Yutaka Fujita
Julie Hlavacek-Larrondo
Yuto Ichinohe
Maxim Markevitch
Kyoko Matsushita
François Mernier
Eric D. Miller
Koji Mori
Hiroshi Nakajima
Anna Ogorzalek
Frederick S. Porter
Ayşegül Tümer … (voir 3 de plus)
Shutaro Ueda
Norbert Werner
Annie Heinrich
We present extended gas kinematic maps of the Perseus cluster based on a combination of five new XRISM/Resolve pointings observed in 2025 wi… (voir plus)th four performance verification datasets from 2024, totaling a net exposure of 745 ks. To date, Perseus remains the only cluster that has been extensively mapped out to ≃0.7 r 2500 by XRISM/Resolve, while simultaneously offering sufficient spatial resolution to resolve gaseous substructures driven by mergers and active galactic nucleus (AGN) feedback. Our observations cover multiple radial directions and a broad range of dynamical scales, enabling us to characterize the kinematic properties of the intracluster medium up to a scale of ∼500 kpc. In the measurements, we detected high-velocity dispersions (≃300km s −1 ) in the eastern region of the cluster that are spatially coincident with the extended X-ray surface brightness excess and correspond to a nonthermal pressure fraction of ≃7 − 13%. The velocity field outside the AGN-dominant region can be effectively described by a single, large-scale kinematic driver based on the velocity structure function, which statistically favors an energy injection scale of at least a few hundred kpc. The estimated turbulent dissipation energy is comparable to the gravitational potential energy released by a recent merger, implying a significant role of turbulent cascade in the merger energy conversion. In the bulk velocity field, we observed a dipole-like pattern along the east-west direction with an amplitude of ≃ ± 200 − 300 km s −1 , indicating rotational motions induced by the recent merger event. This feature constrains the viewing direction to ≃30° −50° relative to the normal of the merger plane. Our hydrodynamic simulations suggest that Perseus has experienced at least two energetic mergers since redshift z ∼ 1, the most recent of which is associated with the radio galaxy IC310, in agreement with recent SRG/eROSITA findings. This study showcases exciting scientific opportunities for future missions with high-resolution spectroscopic capabilities (e.g., HUBS, LEM, and NewAthena).
2026-01-18
Astronomy & Astrophysics (publié)
doi.org
arxiv.org
Multi-Agent AI Framework for Threat Mitigation and Resilience in Machine Learning Systems
Armstrong Foundjem
Lionel Nganyewou Tidjon
Leuson Da Silva
Foutse Khomh
Machine learning (ML) increasingly underpins foundation models and autonomous pipelines in high-stakes domains such as finance, healthcare, … (voir plus)and national infrastructure, rendering these systems prime targets for sophisticated adversarial threats. Attackers now leverage advanced Tactics, Techniques, and Procedures (TTPs) spanning data poisoning, model extraction, prompt injection, automated jailbreaking, training data exfiltration, and—more recently—preference-guided black-box optimization that exploits models’ own comparative judgments to craft successful attacks iteratively. These emerging text-only, query-based methods demonstrate that larger and better-calibrated models can be paradoxically more vulnerable to introspection-driven jailbreaks and cross-modal manipulations. While traditional cybersecurity frameworks offer partial mitigation, they lack ML-specific threat modeling and fail to capture evolving attack vectors across foundation, multimodal, and federated settings. Objective: This research empirically characterizes modern ML security risks by identifying dominant attacker TTPs, exposed vulnerabilities, and lifecycle stages most frequently targeted in foundation-model, multimodal, and retrieval-augmented (RAG) pipelines. The study also assesses the scalability of current defenses against generative and introspection-based attacks, highlighting the need for adaptive, ML-aware security mechanisms. Methods: We conduct a large-scale empirical analysis of ML security, extracting 93 distinct threats from multiple sources: real-world incidents in MITRE ATLAS (26), the AI Incident Database (12), and peer-reviewed literature (55), supplemented by 854 ML repositories from GitHub and the Python Advisory database. A multi-agent reasoning system with enhanced Retrieval-Augmented Generation (RAG)—powered by ChatGPT-4o (temperature 0.4)—automatically extracts TTPs, vulnerabilities, and lifecycle stages from over 300 scientific articles using evidence-grounded reasoning. The resulting ontology-driven threat graph supports cross-source validation and lifecycle mapping. Results: Our analysis uncovers multiple unreported threats beyond current ATLAS coverage, including model-stealing attacks against commercial LLM APIs, data leakage through parameter memorization, and preference-guided query optimization enabling text-only jailbreaks and multimodal adversarial examples. Gradient-based obstinate attacks, MASTERKEY automated jailbreaking, federated learning poisoning, diffusion backdoor embedding, and preference-oriented optimization leakage emerge as dominant TTPs, disproportionately impacting pretraining and inference. Graph-based dependency analysis shows that specific ML libraries and model hubs exhibit dense vulnerability clusters lacking effective issue-tracking and patch-propagation mechanisms. Conclusion: This study underscores the urgent need for adaptive, ML-specific security frameworks that address introspection-based and preference-guided attacks alongside classical adversarial vectors. Robust dependency management, automated threat intelligence, and continuous monitoring are essential to mitigate supply-chain and inference-time risks throughout the ML lifecycle. By unifying empirical evidence from incidents, literature, and repositories, this research delivers a comprehensive threat landscape for next-generation AI systems and establishes a foundation for proactive, multi-agent security governance in the era of large-scale and generative AI.
2026-01-18
ACM Transactions on Software Engineering and Methodology (publié)
doi.org
Toward Faithful Explanations in Acoustic Anomaly Detection
Maab Elrashid
Anthony Deschênes
Yusuf Cem Sübakan
Mirco Ravanaelli
Rémi Georges
Michael Morin
Interpretability is essential for user trust in real-world anomaly detection applications. However, deep learning models, despite their stro… (voir plus)ng performance, often lack transparency. In this work, we study the interpretability of autoencoder-based models for audio anomaly detection, by comparing a standard autoencoder (AE) with a mask autoencoder (MAE) in terms of detection performance and interpretability. We applied several attribution methods, including error maps, saliency maps, SmoothGrad, Integrated Gradients, GradSHAP, and Grad-CAM. Although MAE shows a slightly lower detection, it consistently provides more faithful and temporally precise explanations, suggesting a better alignment with true anomalies. To assess the relevance of the regions highlighted by the explanation method, we propose a perturbation-based faithfulness metric that replaces them with their reconstructions to simulate normal input. Our findings, based on experiments in a real industrial scenario, highlight the importance of incorporating interpretability into anomaly detection pipelines and show that masked training improves explanation quality without compromising performance.
2026-01-18
ArXiv (prépublication)
doi.org
arxiv.org
Press Start to Charge: Videogaming the Online Centralized Charging Scheduling Problem
Alireza Ghahtarani
Martin Cousineau
Amir-massoud Farahmand
Jorge E. Mendoza
2026-01-17
ArXiv (prépublication)
doi.org
arxiv.org
Same/Other/All K‐Fold Cross‐Validation for Estimating Similarity of Patterns in Data Subsets
Toby Dylan Hocking
Gabrielle Thibault
C. S. Bodine
Paul Nelson Arellano
Alexander F. Shenkin
Olivia Jasmine Lindly
2026-01-15
Statistical Analysis and Data Mining: An ASA Data Science Journal (publié)
doi.org
Discrete Feynman-Kac Correctors
Mohsin Hasan
Viktor Ohanesian
Artem Gazizov
Yoshua Bengio
Alán Aspuru-Guzik
Roberto Bondesan
Marta Skreta
Kirill Neklyudov
Discrete diffusion models have recently emerged as a promising alternative to the autoregressive approach for generating discrete sequences.… (voir plus) Sample generation via gradual denoising or demasking processes allows them to capture hierarchical non-sequential interdependencies in the data. These custom processes, however, do not assume a flexible control over the distribution of generated samples. We propose Discrete Feynman-Kac Correctors, a framework that allows for controlling the generated distribution of discrete masked diffusion models at inference time. We derive Sequential Monte Carlo (SMC) algorithms that, given a trained discrete diffusion model, control the temperature of the sampled distribution (i.e. perform annealing), sample from the product of marginals of several diffusion processes (e.g. differently conditioned processes), and sample from the product of the marginal with an external reward function, producing likely samples from the target distribution that also have high reward. Notably, our framework does not require any training of additional models or fine-tuning of the original model. We illustrate the utility of our framework in several applications including: efficient sampling from the annealed Boltzmann distribution of the Ising model, improving the performance of language models for code generation and amortized learning, as well as reward-tilted protein sequence generation.
2026-01-14
arXiv (prépublication)
doi.org
arxiv.org
Inference-time Physics Alignment of Video Generative Models with Latent World Models
Jianhao Yuan
Xiaofeng Zhang
Felix Friedrich
Nicolas Beltran-Velez
Melissa Hall
Reyhane Askari Hemmat
Xiaochuang Han
Nicolas Ballas
Michal Drozdzal
Adriana Romero
State-of-the-art video generative models produce promising visual content yet often violate basic physics principles, limiting their utility… (voir plus). While some attribute this deficiency to insufficient physics understanding from pre-training, we find that the shortfall in physics plausibility also stems from suboptimal inference strategies. We therefore introduce WMReward and treat improving physics plausibility of video generation as an inference-time alignment problem. In particular, we leverage the strong physics prior of a latent world model (here, VJEPA-2) as a reward to search and steer multiple candidate denoising trajectories, enabling scaling test-time compute for better generation performance. Empirically, our approach substantially improves physics plausibility across image-conditioned, multiframe-conditioned, and text-conditioned generation settings, with validation from human preference study. Notably, in the ICCV 2025 Perception Test PhysicsIQ Challenge, we achieve a final score of 62.64%, winning first place and outperforming the previous state of the art by 7.42%. Our work demonstrates the viability of using latent world models to improve physics plausibility of video generation, beyond this specific instantiation or parameterization.
2026-01-14
ArXiv (prépublication)
doi.org
arxiv.org
Multilinguality as Sense Adaptation
Jan Christian Blaise Cruz
David Ifeoluwa Adelani
Alham Fikri Aji
2026-01-14
ArXiv (prépublication)
doi.org
arxiv.org
BON in a Box: An Open and Collaborative Platform for Biodiversity Monitoring, Indicator Calculation, and Reporting
Jory Griffith
Jean-Michel Lord
Michael Catchen
María Isabel Arce-Plata
F Guillaume Blanchet
Mathusan Chandramohan
M Camila Diaz-Corzo
Gravel Dominique
César Gutiérrez
Isabelle S. Helfenstein
Sean Hoban
Jamie M. Kass
Linda Laikre
Guillaume Larocque
Deborah M. Leigh
Brian Leung
Alicia Mastretta‐Yanes
Katie L. Millette
Maria Alejandra Molina Berbeo
Dat Nguyen … (voir 27 de plus)
Kari Norman
María Helena Olaya-Rodríguez
Simon Pahls
Kaitlyn M. Pereira
Pedro R. Peres‐Neto
Timothée Poisot
Laura J. Pollock
Juan Carlos Rey-Velasco
Víctor J. Rincón-Parra
Claudia Roeoesli
François Rousseu
Lina María Sánchez-Clavijo
Meredith C. Schuman
Oliver Selmoni
Jessica M. da Silva
Erika Suárez-Valencia
Thilina D. Surasinghe
Eren Turak
Luis Urbina
Sarah Valentin
Noah Wightman
Juan Zuloaga
Maria Cecilia Londoño
Andrew Gonzalez
Manuel Galvez Bohorquez
Luis Felipe Verdeja González
Diego Moreno
Abstract The Convention on Biological Diversity’s Kunming–Montreal Global Biodiversity Framework (GBF) sets ambitious goals to protect a… (voir plus)nd restore biodiversity. It includes a monitoring framework that mandates countries to track progress toward these goals using indicators that summarize biodiversity trends. Calculating indicators is challenging for countries because of fragmented biodiversity monitoring efforts, technical barriers, a lack of available data and tools, and capacity bottlenecks. The BON in a Box platform for biodiversity monitoring and indicator calculation, developed by the Group on Earth Observations Biodiversity Observation Network, was created to address these challenges by providing open, transparent, and reproducible analysis pipelines that convert data into essential biodiversity variables and indicators. These pipelines are built by experts and contributed by the community, follow FAIR principles, and help scientists apply their research to coordinate biodiversity monitoring efforts, build capacity to track progress toward the GBF, and affect policy change.
2026-01-12
BioScience (publié)
doi.org