Publications

CoB Doped Ni-MOF/NF Composite Catalyst for Efficient Hydrogen Evolution Reaction in Alkaline Media
Haibo Liu
Hongming Zhang
Jiasheng Wang
Bo Li
Hanqing Zhao
Yicong Zhu
Yuchen Zhang
Junteng Lv
Zhiwu Qiao
Jinxiang Yang
The advancement of efficient and stable non-precious metal electrocatalysts is crucial for promoting the development of alkaline water elect… (voir plus)rolysis, a key clean energy technology for hydrogen production. This study presents a rational design of a self-supported CoB@Ni-MOF/NF catalyst for scalable hydrogen production, constructed by building a hierarchical Ni-MOF/NF conductive scaffold, incorporating amorphous CoB active phases, and establishing a synergistic Ni-Co-B interface. The optimized electrode exhibits exceptional hydrogen evolution reaction performance in alkaline media, achieving an ultralow overpotential of 33.2 mV at 10 mA cm-2-performance that rivals some noble-metal-doped systems—along with stable operation exceeding 28 hours. Comprehensive characterization confirms that the superior activity originates from abundant accessible active sites and optimized reaction energetics enabled by the composite architecture, offering a generalizable design strategy that integrates MOFs, conductive substrates, and transition metal borides for advanced energy conversion materials.
2026-03-16
Journal of the Electrochemical Society (publié)
doi.org
Contextual Preference Distribution Learning
Benjamin Hudson
Laurent Charlin
Emma Frejinger
Decision-making problems often feature uncertainty stemming from heterogeneous and context-dependent human preferences. To address this, we … (voir plus)propose a sequential learning-and-optimization pipeline to learn preference distributions and leverage them to solve downstream problems, for example risk-averse formulations. We focus on human choice settings that can be formulated as (integer) linear programs. In such settings, existing inverse optimization and choice modelling methods infer preferences from observed choices but typically produce point estimates or fail to capture contextual shifts, making them unsuitable for risk-averse decision-making. Using a bounded-variance score function gradient estimator, we train a predictive model mapping contextual features to a rich class of parameterizable distributions. This approach yields a maximum likelihood estimate. The model generates scenarios for unseen contexts in the subsequent optimization phase. In a synthetic ridesharing environment, our approach reduces average post-decision surprise by up to 114
2026-03-16
arXiv (prépublication)
doi.org
arxiv.org
Navigating ternary doping in Li-ion cathodes with closed-loop multi-objective Bayesian optimization
Nooshin Zeinali Galabi
Cheng-Hao Liu
Moksh Jain
Marc Kamel
Shipeng Jia
Yoshua Bengio
Eric McCalla
To further improve secondary battery materials, we are increasingly exploring highly complex composition spaces in attempts to optimize mult… (voir plus)iple properties simultaneously. While our past work has done this in systematic manners using high-throughput experimentation, the exponential increase in the search space with triple doping makes grid search prohibitively expensive. Here, we demonstrate a closed-loop, multi-objective machine learning approach to guide the high-throughput workflow to efficiently navigate a space with approximately 14 million unique combinations. The test system is LiCoPO4 which we have previously explored using systematic codoping that was effective in optimizing one property only: energy density. To learn multiple electrochemical metrics, we first pretrain a set transformer on the public Materials Project database as a feature extractor, then attach a multi-task Gaussian process head and finetune the entire model on our high-throughput data. Through 3 rounds of active learning, we demonstrate that with a very small number of samples (as few as 125 random compositions and 63 predicted) we are able to simultaneously optimize four key electrochemical properties. Relative to the undoped system, the best composition raises our composite figure of merit by up to five times. This establishes an end-to-end workflow for accelerated battery materials design to be used in the rapidly growing field of autonomous materials discovery.
2026-03-16
Advanced Materials (publié)
doi.org
SLowRL: Safe Low-Rank Adaptation Reinforcement Learning for Locomotion
Elham Daneshmand
Shafeef Omar
Glen Berseth
Majid Khadiv
Hsiu-Chin Lin
Sim-to-real transfer of locomotion policies often leads to performance degradation due to the inevitable sim-to-real gap. Naively fine-tunin… (voir plus)g these policies directly on hardware is problematic, as it poses risks of mechanical failure and suffers from high sample inefficiency. In this paper, we address the challenge of safely and efficiently fine-tuning reinforcement learning (RL) policies for dynamic locomotion tasks. Specifically, we focus on fine-tuning policies learned in simulation directly on hardware, while explicitly enforcing safety constraints. In doing so, we introduce SLowRL, a framework that combines Low-Rank Adaptation (LoRA) with training-time safety enforcement via a recovery policy. We evaluate our method both in simulation and on a real Unitree Go2 quadruped robot for jump and trot tasks. Experimental results show that our method achieves a
2026-03-16
arXiv (prépublication)
doi.org
arxiv.org
Use of Conventional Artificial Intelligence Methods in the Identification of Frailty: A Scoping Review
Kunal Ashok Dalsania
Alixe Ménard
Shruthi Sundararaman
Arya Rahgozar
Solange Rito Lima
Xintong Lu
Aya Al‐Ali
Krishnpriya Singh
Ramtin Hakimjavadi
Hui Yan
Claire Sethuram
Howard Bergman
Jim LaPlante
Daniel I. McIsaac
Samira Abbasgholizadeh Rahimi
Nadia Sourial
Manpreet Thandi
Sabrina Wong
Clare Liddy
Karen Bandeen‐Roche … (voir 1 de plus)
Sathya Karunananthan
OSF Registries [https://doi.org/10.17605/OSF.IO/T54G8].
2026-03-16
Journal of the American Geriatrics Society (publié)
doi.org
CUBE: A Standard for Unifying Agent Benchmarks
Alexandre Lacoste
Nicolas Gontier
Oleh Shliazhko
Aman Jaiswal
Kusha Sareen
Shailesh Nanisetty
Joan Cabezas
Manuel Del Verme
Omar G. Younis
Simone Baratta
Matteo Avalle
Imene Kerboua
Xing Han Lu
Elron Bandel
Michal Shmueli-Scheuer
Asaf Yehudai
Leshem Choshen
Jonathan Lebensold
Sean Hughes
Massimo Caccia … (voir 6 de plus)
Alexandre Drouin
Siva Reddy
Tao Yu
Yu Su
Graham Neubig
Dawn Song
The proliferation of agent benchmarks has created critical fragmentation that threatens research productivity. Each new benchmark requires s… (voir plus)ubstantial custom integration, creating an "integration tax" that limits comprehensive evaluation. We propose CUBE (Common Unified Benchmark Environments), a universal protocol standard built on MCP and Gym that allows benchmarks to be wrapped once and used everywhere. By separating task, benchmark, package, and registry concerns into distinct API layers, CUBE enables any compliant platform to access any compliant benchmark for evaluation, RL training, or data generation without custom integration. We call on the community to contribute to the development of this standard before platform-specific implementations deepen fragmentation as benchmark production accelerates through 2026.
2026-03-15
arXiv (prépublication)
doi.org
arxiv.org
Deriving Hyperparameter Scaling Laws via Modern Optimization Theory
Egor Shulgin
Dimitri von Rütte
Tianyue H. Zhang
Niccolò Ajroldi
Bernhard Schölkopf
Antonio Orvieto
Hyperparameter transfer has become an important component of modern large-scale training recipes. Existing methods, such as muP, primarily f… (voir plus)ocus on transfer between model sizes, with transfer across batch sizes and training horizons often relying on empirical scaling rules informed by insights from timescale preservation, quadratic proxies, and continuous-time approximations. We study hyperparameter scaling laws for modern first-order optimizers through the lens of recent convergence bounds for methods based on the Linear Minimization Oracle (LMO), a framework that includes normalized SGD, signSGD (approximating Adam), and Muon. Treating bounds in recent literature as a proxy and minimizing them across different tuning regimes yields closed-form power-law schedules for learning rate, momentum, and batch size as functions of the iteration or token budget. Our analysis, holding model size fixed, recovers most insights and observations from the literature under a unified and principled perspective, with clear directions open for future research. Our results draw particular attention to the interaction between momentum and batch-size scaling, suggesting that optimal performance may be achieved with several scaling strategies.
2026-03-15
arXiv (prépublication)
doi.org
arxiv.org
Lifelong Learning and Personalization in Long-Term Human-Robot Interaction (LEAP-HRI): Evolving Assistance for Everyday Life
Bahar Irfan
Nikhil Churamani
Michelle Zhao
Rajat Kumar Jenamani
Ali Ayub
Silvia Rossi
Today's high-capacity generalist robot policies provide a strong foundation for broad task-level competence, yet achieving effective and equ… (voir plus)itable support for people in everyday settings remains a significant challenge. Real-world environments are dynamic and unstructured, and human needs evolve over time, requiring robots that can adapt accordingly. The ultimate evaluator of any robotic system is the person it assists, and personalization is essential to ensuring equitable and meaningful support across diverse users and contexts. Developing robots that can continually learn from interaction, adapt their behaviors over time, and flexibly assume roles as learners and collaborators is a critical step toward realizing effective integration of robots into daily life. With this year's theme of "Evolving Assistance for Everyday Life", and in alignment with the conference theme "HRI Empowering Society", the sixth edition of the "Lifelong Learning and Personalization in Long-Term Human-Robot Interaction (LEAP-HRI)" workshop aims to bring together insights across diverse disciplines, focusing on how robots can progressively adapt their support to suit diverse individuals, each with unique and changing needs, across real-world contexts. Through this lens, the workshop aims to discuss current and future directions in how assistive systems can flexibly respond, continually improve over time, and deliver more inclusive and empowering support in everyday life.
2026-03-15
International Conference on Human-Robot Interaction (publié)
doi.org
Responsible Humanoids: A Contradiction in Terms?
Séverin Lemaignan
AJung Moon
Simon Coghlan
Emily C. Collins
Vanessa Evers
Nico Hochgeschwender
Sara Ljungblad
Michael Milford
Sarah Moth-Lund Christensen
Francisco J. Rodríguez Lera
Pericle Salvini
Yi Yang
In this paper, we critically examine the current "humanoid hype" in robotics, questioning its alignment with responsible robotics principles… (voir plus). While technical challenges drive internal fascination, the pervasive public image of humanoids demands deeper HRI engagement. We explore how responsible robotics concepts, such as privacy, dignity, and trust, are uniquely challenged or overlooked in the pursuit of anthropomorphic robot forms. By dissecting this hype, and mapping the main findings of the recently-published Roadmap for Responsible Robotics to the humanoids field, we aim to move beyond technical form-factor obsessions to understand the true societal implications and identify potential blind spots for the HRI community.
2026-03-15
IEEE/ACM Conference on Human-Robot Interaction (publié)
doi.org
Understanding Social Appropriateness Perceptions in Secondary Users of Domestic Robots
Rahatul Amin Ananto
Seol Han
Rachel Ruddy
AJung Moon
A new generation of robots are being developed to enter our homes in a matter of months. But has the industry appropriately accounted for th… (voir plus)e complexities of the social environment that we call home? We conducted an exploratory design workshop to examine what secondary users—those who are not expected to be owners but nonetheless daily users—deem to be socially appropriate behavior of a domestic robot. A total of 90 students from Mexico participated in the study. By analyzing they define and reason about appropriateness of robot behaviors in the home, we show why deployment of domestic robots require much more thoughtful considerations than implementation of simplified social rules; judgments of what is appropriate depend on context, roles, relationships, and individual boundaries, and can differ between primary and secondary users. We call on Human-Robot Interaction (HRI) practitioners to treat social appropriateness as a fluid, gradient factor at design time rather than a binary concept (appropriate/inappropriate).
2026-03-15
International Conference on Human-Robot Interaction (publié)
doi.org
Discovery of Sustainable Refrigerants through Physics-Informed RL Fine-Tuning of Sequence Models
Adrien Goldszal
Diego Calanzone
Vincent Taboga
Pierre-Luc Bacon
Most refrigerants currently used in air-conditioning systems, such as hydrofluorocarbons, are potent greenhouse gases and are being phased d… (voir plus)own. Large-scale molecular screening has been applied to the search for alternatives, but in practice only about 300 refrigerants are known, and only a few additional candidates have been suggested without experimental validation. This scarcity of reliable data limits the effectiveness of purely data-driven methods. We present Refgen, a generative pipeline that integrates machine learning with physics-grounded inductive biases. Alongside fine-tuning for valid molecular generation, Refgen incorporates predictive models for critical properties, equations of state, thermochemical polynomials, and full vapor compression cycle simulations. These models enable reinforcement learning fine-tuning under thermodynamic constraints, enforcing consistency and guiding discovery toward molecules that balance efficiency, safety, and environmental impact. By embedding physics into the learning process, Refgen leverages scarce data effectively and enables de novo refrigerant discovery beyond the known set of compounds.
2026-03-14
AI4X @ Neural Information Processing Systems (présentation orale)
doi.org
openreview.net
Power-Law Spectrum of the Random Feature Model
Elliot Paquette
Ke Liang Xiao
Yizhe Zhu
Scaling laws for neural networks, in which the loss decays as a power-law in the number of parameters, data, and compute, depend fundamental… (voir plus)ly on the spectral structure of the data covariance, with power-law eigenvalue decay appearing ubiquitously in vision and language tasks. A central question is whether this spectral structure is preserved or destroyed when data passes through the basic building block of a neural network: a random linear projection followed by a nonlinear activation. We study this question for the random feature model: given data
2026-03-14
arXiv (prépublication)
doi.org
arxiv.org