Publications

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
A. Chandar
2024-12-31
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) (published)
doi.org
Connectivity-Aware Task Offloading for Remote Northern Regions: a Hybrid LEO-MEO Architecture
Mohammed Almekhlafi
Antoine Lesage-Landry
Gunes Karabulut Kurt
Arctic regions, such as northern Canada, face significant challenges in achieving consistent connectivity and low-latency computing services… (see more) due to the sparse coverage of Low Earth Orbit (LEO) satellites. To enhance service reliability in remote areas, this paper proposes a hybrid satellite architecture for task offloading that combines Medium Earth Orbit (MEO) and LEO satellites. We develop an optimization framework to maximize task offloading admission rate while balancing the energy consumption and delay requirements. Accounting for satellite visibility and limited computing resources, our approach integrates dynamic path selection with frequency and computational resource allocation. Because the formulated problem is NP-hard, we reformulate it into a mixed-integer convex form using disjunctive constraints and convex relaxation techniques, enabling efficient use of off-the-shelf optimization solvers. Simulation results show that, compared to a standalone LEO network, the proposed hybrid LEO-MEO architecture improves the task admission rate by 15\% and reduces the average delay by 12\%. These findings highlight the architecture's potential to enhance connectivity and user experience in remote Arctic areas.
2024-12-31
2025 IEEE 36th International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) (published)
doi.org
arxiv.org
Correction to: Assessing the adoption of security policies by developers in terraform across different cloud providers
Alexandre Verdet
Mohammad Hamdaqa
Leuson Da Silva
Foutse Khomh
2024-12-31
Empir. Softw. Eng. (published)
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
Christopher Pal
2024-12-31
Trans. Mach. Learn. Res. (published)
openreview.net
openreview.net
A Decomposition-Based Framework for Large-Scale Multi-Period Log-Truck Routing and Scheduling: A Case Study in Canadian Forestry
Abdelhakim Abdellaoui
François Aubé
Loubna Benabbou
I. E. Hallaoui
Mouloud Amazouz
2024-12-31
IFAC-PapersOnLine (published)
doi.org
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… (see more)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
2024-12-31
IEEE Access (published)
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… (see more) many reinforcement learning (RL) algorithms as well. As the error convergence rate of VI as a function of iteration
2024-12-31
Trans. Mach. Learn. Res. (published)
doi.org
arxiv.org
Dehumanizing Machines: Mitigating Anthropomorphic Behaviors in Text Generation Systems
Myra Cheng
Su Lin Blodgett
Alicia DeVrio
Lisa Egede
A.R. Olteanu
As text generation systems' outputs are increasingly anthropomorphic -- perceived as human-like -- scholars have also raised increasing conc… (see more)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.
2024-12-31
ACL (1) (published)
doi.org
arxiv.org
Designing Experimental Setup Emulating Log-Loader Manipulator and Implementing Anti-Sway Trajectory Planner
Iman Jebellat
George Sideris
Rafid Saif
Inna Sharf
Forestry machines are not easily accessible for experimentation or demonstration of research results. These mobile robots are massive, very … (see more)expensive, and require a large outdoor space and permits to operate. These factors hinder conducting experiments on real forestry robots. Thus, it is essential to design experimental setups utilizing easily accessible robots in indoor labs that can effectively replicate the behavior of interest of a forestry machine. We design a setup to resemble a log-loader crane and grapple motions using a Kinova Jaco2 arm by manufacturing a specialized end-effector to attach passively to the Jaco2 arm. Passively attached grapple causes undesirable sway, which is problematic and dangerous in forestry. To address the sway problem, we employ dynamic programming to develop an anti-sway motion planner, and validate its performance for different point-to-point maneuvers in our experimental setup. We also repeat each experiment at least 6 times to ensure the repeatability and reliability of the experiments. The experimental results showcase the excellent sway-damping performance of our planner and also the very good repeatability of our experiments.
2024-12-31
IEEE International Conference on Robotics and Automation (published)
doi.org
Diffusion Models as Constrained Samplers for Optimization with Unknown Constraints
Lingkai Kong
Yuanqi Du
Wenhao Mu
Kirill Neklyudov
Valentin De Bortoli
Haorui Wang
Dongxia Wu
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… (see more)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.
2024-12-31
AISTATS (published)
doi.org
proceedings.mlr.press
Diffusion-Based Adversarial Purification for Intrusion Detection
Mohamed Amine Merzouk
Erwan Beurier
Reda Yaich
N. Cuppens-Boulahia
Frédéric Cuppens
Foutse Khomh
2024-12-31
Database Security (published)
doi.org
Discrete Audio Tokens: More Than a Survey!
Pooneh Mousavi
Gallil Maimon
Adel Moumen
Darius Petermann
Jiatong Shi
Haibin Wu
Haici Yang
Anastasia Kuznetsova
Artem Ploujnikov
Ricard Marxer
Bhuvana Ramabhadran
Benjamin Elizalde
Loren Lugosch
Jinyu Li
Yusuf Cem Sübakan
Phil Woodland
Minje Kim
Hung-yi Lee
Shinji Watanabe
Yossi Adi … (see 1 more)
Mirco Ravanaelli
Discrete audio tokens are compact representations that aim to preserve perceptual quality, phonetic content, and speaker characteristics whi… (see more)le enabling efficient storage and inference, as well as competitive performance across diverse downstream tasks. They provide a practical alternative to continuous features, enabling the integration of speech and audio into modern large language models (LLMs). As interest in token-based audio processing grows, various tokenization methods have emerged, and several surveys have reviewed the latest progress in the field. However, existing studies often focus on specific domains or tasks and lack a unified comparison across various benchmarks. This paper presents a systematic review and benchmark of discrete audio tokenizers, covering three domains: speech, music, and general audio. We propose a taxonomy of tokenization approaches based on encoder-decoder, quantization techniques, training paradigm, streamability, and application domains. We evaluate tokenizers on multiple benchmarks for reconstruction, downstream performance, and acoustic language modeling, and analyze trade-offs through controlled ablation studies. Our findings highlight key limitations, practical considerations, and open challenges, providing insight and guidance for future research in this rapidly evolving area. For more information, including our main results and tokenizer database, please refer to our website: https://poonehmousavi.github.io/dates-website/.
2024-12-31
Trans. Mach. Learn. Res. (published)
doi.org
openreview.net