Publications

What are we measuring? A critical examination of MO-MuJoCo and evaluation consistency in continuous multi-objective reinforcement learning
Although Multi-Objective Reinforcement Learning (MORL) research relies heavily on MO-MuJoCo as its go-to continuous control benchmark, the v… (voir plus)alidity of the conclusions drawn from it remain underexamined. In this paper, we first discuss three structural limitations of MO-MuJoCo; 1) its objectives are decomposed from pre-existing scalar rewards rather than independently motivated goals; 2) environments repeat the same underlying trade-off structure across varied locomotion morphologies, providing \textit{surface variety} without genuine \textit{problem diversity}; and 3) empirically approximated Pareto fronts appear broadly convex across research, potentially failing to stress-test the limitations of scalarization-based techniques. Setting these concerns aside, we further demonstrate that algorithmic rankings under MO-MuJoCo are highly sensitive to often undocumented evaluation choices in research papers. Across five evaluation axes, including reference point selection, weight distribution, normalization, return type, and front extraction method, pairwise algorithm rankings reverse in up to 47\% of configurations. Variance decomposition reveals that normalization alone accounts for nearly 69\% of hypervolume variance, suppressing the algorithm impact. Ultimately, we argue that progress in MORL research requires not only increased scrutiny of the benchmarks we rely upon, but also greater clarity in how results obtained within them are reported.
Artificial intelligence in implementation science and practice: a living scoping review
Guillaume Fontaine
Olivia Di Lalla
Rachael Laritz
Jeremiah Durran
Chi Zhang
Jeffery Chan
Laura Crump
Alenda Dwiadila Matra Putra
Ruopeng An
Rinad S. Beidas
Christine Fahim
Elvin Geng
Ian D. Graham
Janna Hastings
Sylvie D. Lambert
France Légaré
Susan Michie
Byron J. Powell
Justin Presseau … (voir 6 de plus)
Joseph Elias
Thomas Rudge
Sharon E. Straus
James Thomas
Vivian Welch
Natalie Taylor
Artificial intelligence (AI) encompasses computational systems that perform tasks typically requiring human intelligence, including machine … (voir plus)learning, generative AI, and agentic applications. The use of AI to support implementation activities is growing, but its applications and evaluation remain poorly characterised. We conducted the first cycle of a living scoping review to identify how AI is being used and evaluated across implementation science and practice. We followed JBI and Cochrane guidance and reported findings per PRISMA-ScR and PRISMA-LSR. We searched six databases through April 6, 2026, and included sources describing or evaluating AI to support implementation research or practice activities. We excluded adjacent uses such as knowledge synthesis automation. We extracted study characteristics, AI approaches, implementation tasks, evaluation methods, outcomes, and risks, and synthesised findings descriptively. We identified 7,203 records and included 40 sources, 34 (85%) of which were published since 2021. Thirty-one sources described, developed, or evaluated a specific AI system, comprising 22 primary research articles, three protocols, three conference abstracts, and three other sources. The remaining nine conceptual, methodological, framework or review articles discussed potential applications of AI in implementation science. Across all 40 sources, AI was most often used or proposed to support evaluation (25/40), implementation strategy selection and tailoring (23/40), barrier and facilitator assessment (21/40), and implementation monitoring (20/40). Among the 31 sources involving a specific AI system, the use of conventional machine learning was most common (10/31), followed by generative AI (7/31), multicomponent AI systems or studies comparing AI approaches (5/31), and non-generative deep learning (3/31). Implementation-related outcomes were reported or prospectively specified in 25/31 sources, technical performance in 19/31, human-centred outcomes in 12/31, time or efficiency in 10/31, clinical or health system outcomes in 9/31, equity in 3/31, and cost or resource outcomes in 2/31. Risks were discussed in about half of sources, although assessment of harms and environmental or societal consequences was rare. AI is in a nascent stage of supporting implementation science and practice. Reported use is narrow and methodologically underdeveloped, and much routine use is likely unpublished. The field needs rigorous, comparative, prospective, and equity-attentive research to establish whether and how AI improves implementation methods, processes, and outcomes. Open Science Framework, May 2025: https://doi.org/10.17605/OSF.IO/2Q5DV
Determinants of functional burden pleiotropy and gene dosage responses across human traits
Sayeh Kazem
Kuldeep Kumar
Jane Yang
Florian Benitiere
Josephine Mollon
Thomas Renne
Laura M. Schultz
Emma E.M. Knowles
Worrawat Engchuan
Omar Shanta
Bhooma Thiruvahindrapuram
Jeffrey R. MacDonald
Celia M. T. Greenwood
Stephen W. Scherer
Laura Almasy
Jonathan Sebat
David C. Glahn
Sébastien Jacquemont
Pleiotropic and monotonic effects of gene dosage are central to understanding comorbidities in developmental pediatric and psychiatric disor… (voir plus)ders, yet the underlying biological processes are not well characterized. Here we develop a functional burden analysis to investigate the association of all protein-coding copy-number variants, genome-wide, with 43 complex traits in approximately 500,000 UK Biobank participants. We test variant associations disrupting 172 tissue or cell-type gene sets, finding associations for all traits, which we replicate in the All of Us cohort. Functional burden pleiotropy, defined as the number of traits significantly associated with a gene set, correlates with genetic constraint and is higher for brain than non-brain functions, even after normalizing for genetic constraint. Levels of pleiotropy, measured by burden correlation, are similar in deletions and loss-of-function single-nucleotide variants, and higher than in common variants and duplications. Most gene dosage responses are non-monotonic, with deletions and duplications showing same-direction effects, and monotonic responses decrease with genetic constraint. We observe associations between functional gene sets and traits for either deletions or duplications, but rarely both, with negatively correlated effect sizes. Together, these results link genetic constraint and brain-specific mechanisms to the whole-body multimorbidity of neurodevelopmental and psychiatric conditions. Gene dosage can help explain comorbidities in developmental pediatric and psychiatric disorders. Here, the authors map how rare copy-number variants disrupting tissue and cell-type gene sets shape 43 human traits.
Foreword to the special issue on responsible artificial intelligence: methodologies, implications, and practices
Ebrahim Bagheri
Robin Cohen
Faezeh Ensan
Benjamin C.M. Fung
Sébastien Gambs
Individual Disempowerment through an Advice Channel: Control Loss when Influence is Endogenous
An AI that can only give advice seems safe: the human is always free to ignore it. That is the premise of the boxing tradition in AI safety,… (voir plus) and its long-suspected weak point is that the human who reads the answers is part of the system. We make the fraction
Proceedings of the 26th Annual Conference of the European Association for Machine Translation
Dimitar Shterionov
Eva Vanmassenhove
Mirella De Sisto
Fred Blain
Javed Pourmostafa
Roshan Sharami
Lisa Lepp
Chiara Manna
Argentina Anna Rescigno
Aliana Karakanta
Manuel Lardelli
Natalia Resende
Elena Murgolo
Janiça Hackenbuchner
Anna Zaretskaya
Miquel Esplà-Gomis
Thierry Etchegoyhen
Dagmar Gromann
Rachel Bawden … (voir 4 de plus)
Barry Haddow
Sara Szoc
Mikel L. Forcada
Helena Moniz
Analyzing Flexible Search Distributions in Black-Box Optimization with Normalizing Flow-based Estimation of Distribution Algorithms
Black-box optimization often requires search distributions that can adapt to complex geometric structures under limited evaluation budgets. … (voir plus)We propose NF-EDA, a Normalizing Flow-based Estimation of Distribution Algorithm that replaces fixed Gaussian models with a learned, flexible search distribution. Beyond optimization performance, our goal is to better understand how increased distributional expressiveness affects search behavior. In contrast to classical Gaussian-based methods, NF-EDA can adapt to curved, asymmetric, and non-elliptical regions of the search space, enabling broader yet structured exploration during early stages of optimization. By tracking the evolution of the learned distribution over iterations, we analyze how NF-EDA reshapes its sampling behavior compared to predefined parametric approaches such as CMA-ES and Gaussian EDAs. Experimental results on selected COCO BBOB functions, including Rastrigin, Schwefel, Lunacek bi-Rastrigin, and Rosenbrock, show that NF-EDA achieves faster early progress and reduced variability across runs, particularly in higher-dimensional settings. An ablation against a Gaussian EDA with matching update rules further demonstrates that these effects arise from the learned flow transformation rather than from the surrounding EDA procedure alone. These findings highlight the importance of flexible search distributions for understanding and improving model-based black-box optimization.
Conductivity Preservation of Aryl Diazonium-Functionalized Bilayer Graphene Probed by Operando Hall
Bahar Molavi
Claudia M. Bazán
Tony Vuu
Jade Cimmino
Sébastien Côté
Delphine Bouilly
Thomas Szkopek
Abstract Covalent functionalization of graphene is a means to achieve robust immobilization of functional groups, but it results in a signif… (voir plus)icant loss of electrical conductivity in monolayer graphene (MonoG) due to the introduction of strong scattering by point defects. This work presents gate-activated covalent functionalization of bilayer graphene (BiG) integrated with an operando Hall characterization to measure the charge carrier density and mobility in real-time. Using an integrated Ag/AgCl gate electrode to modulate the BiG Fermi level, we achieve precise control over the covalent grafting of aryl diazonium groups on BiG. We demonstrate that BiG preserves the majority of its conductivity after functionalization by losing only 20% of its conductivity, whereas MonoG experiences 80% reduction in conductivity under similar conditions. BiG enables a significantly wider tuning range for surface coverage while preserving the conductivity. Operando Hall measurements of BiG functionalization reveal that the observed conductivity decrease is primarily driven by a reduction in charge mobility due to short-range scattering, while the charge carrier density changes only modestly. Furthermore, we characterize the impact of covalent attachments on the graphene density of states (DOS) and interfacial charge storage through Hall-derived quantum capacitance and electrochemical impedance spectroscopy (EIS). Finally, we demonstrate the application of carboxyphenyl functionalized BiG for pH sensing and present a site-binding model that describes the electrostatic coupling between site-binding coverage and the charge density within the conducting channel. This architecture provides a robust and tunable platform for graphene FET sensors.
Customers’ Multihoming Behavior in Ride-Hailing: Empirical Evidence from Uber and Lyft
Sandeep Chitla
Maxime C. Cohen
Srikanth Jagabathula
Dmitry Mitrofanov
Problem definition: Are customers loyal to a ride-hailing platform or they see this service as a commodity and multihome (i.e., check severa… (voir plus)l platforms before booking a ride)? Using a large panel dataset on ride-hailing transactions, we investigate to what extent customers multihome. Our dataset offers a unique opportunity to study this question as we observe the repeated choices of riders for both Uber and Lyft. Our dataset comprises more than 1.4 million rides completed by 162 thousand riders in NYC in 2018. Methodology/results: We develop a comprehensive structural model that incorporates both operational (price and waiting time) and behavioral factors (e.g., platform stickiness) to explain riders’ choices. Our model also accounts for the dynamic interactions between customers and platforms by assuming that riders update their beliefs on price and waiting time in a Bayesian fashion. Finally, the riders’ propensity to multihome is modeled by incorporating the consideration set formation of customers into our framework. We find that riders’ choices are not fully explained by operational factors, hence indicating that customers view the platforms as differentiated service providers. While 83.4% of riders took rides with a single platform, our model shows that even the remaining 16.6%, who used both Uber and Lyft at least once, considered both platforms only 43.4% of the time. Managerial implications: It is crucial for ride-hailing platforms to capture this single (or multi)-homing behavior while designing price discounts. Specifically, personalized discounts may be ineffective if the platform is not part of the customer’s consideration set. Our results show that targeting customers earlier in their lifecycle can enhance the platform’s market share by 77.56% more than their current discounting strategy. We also find that targeting customers with low search friction results in a 24.78% increase in market share relative to targeting customers with high search friction.
IP Protection in the Era of Visual Generative AI: A Survey
Shunchang Liu
Han Yu
Cao Yang
Chaochao Chen
Yuping Yan
Yaochu Jin
Lingjuan Lyu
The rapid evolution of visual generative AI has introduced a wide range of intellectual property risks, spanning the unauthorized learning, … (voir plus)reproduction, extraction, misuse, and redistribution of protected data and model assets. To address these risks, a growing body of technical defenses has been proposed. However, existing surveys typically organize this literature by lifecycle stage or technical mechanism, which can obscure the protective intent of different methods. This survey presents a two-dimensional taxonomy for IP protection in visual generative models. The primary axis is a Control Logic View, which classifies methods into Information Exposure Control, Generative Behavior Constraint, and Attribution&Accountability according to the risk variable they regulate. The secondary axis distinguishes Data IP from Model IP as cross-cutting asset dimensions. Under this framework, we systematically review protection methods, align evaluation protocols with protection objectives, and discuss open challenges including proactive model-level safeguards, standardized evaluation, robustness against adaptive attacks, and explainable evidence. This survey aims to offer a principled, systematic, and easy-to-follow overview for both new and experienced researchers in visual generative AI IP protection.
Worldwide Innovative Network Consortium: Building a Common Global Cancer Database
Wafik S. El‐Deiry
Yves A. Lussier
Razelle Kurzrock
Shai Magidi
Catherine Bresson
Shirin Abbasinejad Enger
Jia Liu
Jair Bar
Jeremy Lyle Warner
Tobias Meißner
Eitan Rubin
Jens Rueter
Himabindu Gaddipati
Mandar Kulkarni
Zhen Chen
Sewanti Atul Limaye
Rachel J. Elsey
Brenda Marilyn Rubenstein
Anthony Michael Joshua … (voir 30 de plus)
Humaid Obaid Al-Shamsi
Khaled M. Musallam
Fanny Wunder
Jacques Raynaud
Guy Berchem
Manon Gantenbein
Amal Al‐Omari
Said Dermime
Hikmat Abdel‐Razeq
Pierre Saintigny
Andrès M.R. Cervantes
Roger R. Reddel
Adel T. Aref
Juan Martín-Liberal
Conxi Lázaro
David Cordero
Marina Sekacheva
Raanan Berger
Conjeevaram S. Pramesh
Ioana Berindan‐Neagoe
Eugenia Girda
Alejandro Piris‐Giménez
Carol J. Farhangfar
Mohamed E. Salem
Rodrigo Dienstmann
Ramón Salazar
Naftali Z. Frankel
Zachary Batist
Yuri Quintana
Gerald Batist
This review shares the ongoing work of the global Worldwide Innovative Network (WIN) Consortium for Precision Medicine to synthesize emergin… (voir plus)g cancer treatment data and to define the requirements for a common global cancer database that can truly support precision oncology. We performed a narrative review of emerging cancer treatment data, molecular profiling technologies, and existing clinicogenomic databases, focusing on how tumors are characterized, how subgroups are defined, and how demographic, lifestyle, and environmental factors are captured. The growth in molecular profiling technologies and the development of new targeted therapies are transforming cancer care. Tumors, regardless of tissue origin, are increasingly defined as composites of multiple, often rare, subgroups, each with distinct biology and likely response to specific therapies, based on multidimensional profiling of the tumor and its microenvironment. The solution lies in building vast databases that capture racial and ethnic diversity, reflected in genomic data, as well as diet and lifestyle factors that may have epigenetic impact on gene expression and post-translational modifications. A truly inclusive and informative data set must reflect global diversity, and there are multiple examples of demography-dependent differences in genomic signals. With members caring for and studying patients with cancer across five continents, WIN is actively exploring pathways to create a global cancer database, rich in clinical and molecular detail, granular enough for precise analysis, and large enough to power artificial intelligence-driven insights, provided appropriate data quality, validation, and governance frameworks are in place. This review surveys the current landscape and outlines practical paths forward to achieve this goal.
Divergent specializations for motion-driven representations in higher lateral and dorsal visual areas
Sophia Robert
Maryam Vaziri-Pashkam
The human visual system integrates both static and dynamic information to support form and shape perception, yet the computational principle… (voir plus)s underlying the integration of motion for object recognition remain unclear. Artificial neural networks (ANNs) offer a computational framework for developing and testing hypotheses about these principles: if ANNs trained on motion-related tasks develop representations that align with brain activity and support object categorization, this would suggest that the training objectives and architectural constraints of these networks may capture key aspects of motion processing in biological visual systems in general, and motion processing for object recognition, in particular. Here, we investigated this question using “object kinematograms”, stimuli in which object form is conveyed solely through motion cues. We measured neural responses of two higher regions of the lateral and the dorsal visual pathways, respectively, with strong sensitivity to dynamic cues from objects: lateral occipitotemporal cortex (LOT bio ), and left supramarginal gyrus (SMG lh ), as well as primary visual cortex (V1). We compared brain responses to representations extracted from two neural networks: SlowFast, a dual-pathway architecture trained on action recognition that processes slow- and fast-varying visual information with cross-pathway integration, and DorsalNet, a model of the primate dorsal visual pathway trained on embodied self-motion estimation. Representational similarity analysis revealed distinct representational profiles across brain areas, demonstrating functional specialization in motion-based form processing. LOT bio was best characterized by the slow pathway of the SlowFast model, whereas SMG lh showed strong similarity to both models. Critically, we found that representations aligned with brain activity also better supported behavioral function: the full SlowFast model, incorporating both slow and fast pathways, outperformed other models in few-shot categorization of object kinematograms and showed the highest similarity to human perceptual judgments. These findings demonstrate that with appropriate inductive biases, specifically, dual-pathway architectures for multi-scale motion processing and training objectives focused on dynamic visual tasks, ANNs can develop functionally useful representations of motion-defined forms that exhibit better alignment with the visual regions involved in processing dynamic visual signals.