Publications

Child- and Proxy-reported Differences in Patient-reported Outcome and Experience Measures in Pediatric Surgery: Systematic Review and Meta-analysis
Zanib Nafees
Siena O'Neill
Alexandra Dimmer
Elena Guadagno
Julia Ferreira
Nancy Mayo
Dan Poenaru
2025-01-01
Journal of Pediatric Surgery (publié)
doi.org
Combining Domain and Alignment Vectors Provides Better Knowledge-Safety Trade-offs in LLMs
Megh Thakkar
Quentin Fournier
Matthew D Riemer
Pin-Yu Chen
Amal Zouaq
Payel Das
Sarath Chandar
2025-01-01
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) (publié)
doi.org
Ctrl-V: Higher Fidelity Autonomous Vehicle Video Generation with Bounding-Box Controlled Object Motion
Ge Ya Luo
Zhi Hao Luo
Anthony Gosselin
Alexia Jolicoeur-Martineau
Chris Pal
2025-01-01
Trans. Mach. Learn. Res. (publié)
openreview.net
openreview.net
Deep Clustering with Self-Supervision using Pairwise Similarities
Mohammadreza Sadeghi
Sareh Soleimani
Narges Armanfard
Deep clustering incorporates embedding into clustering to find a lower-dimensional space appropriate for clustering. In this paper, we propo… (voir plus)se a novel deep clustering framework with self-supervision using pairwise similarities (DCSS). The proposed method consists of two successive phases. In the first phase, we propose to form hypersphere-like groups of similar data points, i.e. one hypersphere per cluster, employing an autoencoder that is trained using cluster-specific losses. The hyper-spheres are formed in the autoencoder's latent space. In the second phase, we propose to employ pairwise similarities to create a
2025-01-01
IEEE Access (publié)
doi.org
arxiv.org
Deflated Dynamics Value Iteration
Jongmin Lee
Amin Rakhsha
Ernest K. Ryu
Amir-massoud Farahmand
The Value Iteration (VI) algorithm is an iterative procedure to compute the value function of a Markov decision process, and is the basis of… (voir plus) many reinforcement learning (RL) algorithms as well. As the error convergence rate of VI as a function of iteration
2025-01-01
Trans. Mach. Learn. Res. (publié)
doi.org
arxiv.org
Dehumanizing Machines: Mitigating Anthropomorphic Behaviors in Text Generation Systems
Myra Cheng
Su Lin Blodgett
Alicia DeVrio
Lisa Egede
Alexandra Olteanu
As text generation systems' outputs are increasingly anthropomorphic -- perceived as human-like -- scholars have also raised increasing conc… (voir plus)erns about how such outputs can lead to harmful outcomes, such as users over-relying or developing emotional dependence on these systems. How to intervene on such system outputs to mitigate anthropomorphic behaviors and their attendant harmful outcomes, however, remains understudied. With this work, we aim to provide empirical and theoretical grounding for developing such interventions. To do so, we compile an inventory of interventions grounded both in prior literature and a crowdsourced study where participants edited system outputs to make them less human-like. Drawing on this inventory, we also develop a conceptual framework to help characterize the landscape of possible interventions, articulate distinctions between different types of interventions, and provide a theoretical basis for evaluating the effectiveness of different interventions.
2025-01-01
ACL (1) (publié)
doi.org
arxiv.org
Diffusion Models as Constrained Samplers for Optimization with Unknown Constraints
Lingkai Kong
Yuanqi Du
Wenhao Mu
Kirill Neklyudov
Valentin De Bortoli
Dongxia Wu
Haorui Wang
Aaron Ferber
Yi-An Ma
Carla P. Gomes
Chao Zhang
Addressing real-world optimization problems becomes particularly challenging when analytic objective functions or constraints are unavailabl… (voir plus)e. While numerous studies have addressed the issue of unknown objectives, limited research has focused on scenarios where feasibility constraints are not given explicitly. Overlooking these constraints can lead to spurious solutions that are unrealistic in practice. To deal with such unknown constraints, we propose to perform optimization within the data manifold using diffusion models. To constrain the optimization process to the data manifold, we reformulate the original optimization problem as a sampling problem from the product of the Boltzmann distribution defined by the objective function and the data distribution learned by the diffusion model. Depending on the differentiability of the objective function, we propose two different sampling methods. For differentiable objectives, we propose a two-stage framework that begins with a guided diffusion process for warm-up, followed by a Langevin dynamics stage for further correction. For non-differentiable objectives, we propose an iterative importance sampling strategy using the diffusion model as the proposal distribution. Comprehensive experiments on a synthetic dataset, six real-world black-box optimization datasets, and a multi-objective molecule optimization dataset show that our method achieves better or comparable performance with previous state-of-the-art baselines.
2025-01-01
AISTATS (publié)
doi.org
arxiv.org
Diffusion Tree Sampling: Scalable inference-time alignment of diffusion models
Vineet Jain
Kusha Sareen
Mohammad Pedramfar
Siamak Ravanbakhsh
2025-01-01
arXiv.org (prépublication)
doi.org
Diffusion-Based Adversarial Purification for Intrusion Detection
Mohamed Amine Merzouk
Erwan Beurier
Reda Yaich
N. Cuppens-Boulahia
Frédéric Cuppens
Foutse Khomh
2025-01-01
Database Security (publié)
doi.org
A Distributed ADMM-based Deep Learning Approach for Thermal Control in Multi-Zone Buildings
Vincent Taboga
Hanane Dagdougui
The surge in electricity use, coupled with the dependency on intermittent renewable energy sources, poses significant hurdles to effectively… (voir plus) managing power grids, particularly during times of peak demand. Demand Response programs and energy conservation measures are essential to operate energy grids while ensuring a responsible use of our resources This research combines distributed optimization using ADMM with Deep Learning models to plan indoor temperature setpoints effectively. A two-layer hierarchical structure is used, with a central building coordinator at the upper layer and local controllers at the thermal zone layer. The coordinator must limit the building's maximum power by translating the building's total power to local power targets for each zone. Local controllers can modify the temperature setpoints to meet the local power targets. The resulting control algorithm, called Distributed Planning Networks, is designed to be both adaptable and scalable to many types of buildings, tackling two of the main challenges in the development of such systems. The proposed approach is tested on an 18-zone building modeled in EnergyPlus. The algorithm successfully manages Demand Response peak events.
2025-01-01
IEEE Transactions on Automation Science and Engineering (publié)
doi.org
arxiv.org
A Distributed ADMM-Based Deep Learning Approach for Thermal Control in Multi-Zone Buildings Under Demand Response Events.
Vincent Taboga
Hanane Dagdougui
2025-01-01
IEEE Trans Autom. Sci. Eng. (publié)
doi.org
arxiv.org
An Effective Theory of Bias Amplification
Arjun Subramonian
Samuel J. Bell
Levent Sagun
Elvis Dohmatob
Machine learning models may capture and amplify biases present in data, leading to disparate test performance across social groups. To bette… (voir plus)r understand, evaluate, and mitigate these possible biases, a deeper theoretical understanding of how model design choices and data distribution properties could contribute to bias is needed. In this work, we contribute a precise analytical theory in the context of ridge regression, both with and without random projections, where the former models neural networks in a simplified regime. Our theory offers a unified and rigorous explanation of machine learning bias, providing insights into phenomena such as bias amplification and minority-group bias in various feature and parameter regimes. For example, we demonstrate that there may be an optimal regularization penalty or training time to avoid bias amplification, and there can be fundamental differences in test error between groups that do not vanish with increased parameterization. Importantly, our theoretical predictions align with several empirical observations reported in the literature. We extensively empirically validate our theory on diverse synthetic and semi-synthetic datasets.
2025-01-01
ICLR (publié)
doi.org
arxiv.org