Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Quentin LE
Computer Science > Computer Vision and Pattern Recognition
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Computer Science > Artificial Intelligence
The goal of a world model is to capture the dynamics of an environment. This has the great appeal that it allows agents to plan and simulate a course of actions with the help of a world model. For these uses to be reliable, however, the learned dynamics must behave well beyond the specific state-action combinations observed in expert rollouts.
Electrical Engineering and Systems Science > Audio and Speech Processing
Vocal intensity conversion renders a recorded utterance at a different vocal intensity, rather than simply scaling its amplitude, while preserving its content and speaker identity. Existing systems control intensity through a reference utterance or a few discrete categories. Instead, we control the conversion with any target sound pressure level (SPL) on a continuous dB scale.
Computer Science > Computer Vision and Pattern Recognition
Video carries the temporal structure of the physical world, yet learning representations from it has remained computationally expensive: prevailing self-supervised methods either prevent representation collapse through architectural asymmetries, coupling an exponential-moving-average target encoder, a stop-gradient, and a capacity-limited predictor, or circumvent it by reconstructing masked content in pixel space.
Computer Science > Machine Learning
[Submitted on 21 Apr 2026] Title:Accelerating trajectory optimization with Sobolev-trained diffusion policies View a PDF of the paper titled Accelerating trajectory optimization with Sobolev-trained diffusion policies, by Th\'eotime Le Hellard and 3 other authors View PDF HTML (experimental) Abstract:Trajectory Optimization (TO) solvers exploit known system dynamics to compute locally optimal trajectories through iterative improvements.
Causal-JEPA: Learning World Models through Object-Level Latent Interventions
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
stable-worldmodel-v1: Reproducible World Modeling Research and Evaluation
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
[2508.00620] Backdoor Attacks on Deep Learning Face Detection
arXiv:2508.00620 (cs) View PDF HTML (experimental) Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Machine Learning (cs.LG) Cite as: arXiv:2508.00620 [cs.CV] (or arXiv:2508.00620v1 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2508.00620 Submission history From: Yannick Teglia [ view email] [v1] Fri, 1 Aug 2025 13:29:26 UTC (3,590 KB) Bibliographic Tools Bibliographic Explorer Toggle Bibliographic...
SARS-CoV-2 lineage-dependent temporal phylogenetic distribution and viral load in immunocompromised and immunocompetent individuals - Virology Journal
References Tarhini H et al. « Long-Term Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) Infectiousness Among Three Immunocompromised Patients: From Prolonged Viral Shedding to SARS-CoV-2 Superinfection », J. Infect. Dis., vol. 223, no 9, pp. 1522–1527, mai., 2021, https://doi.org/10.1093/infdis/jiab075 Niyonkuru M et al. « Prolonged viral shedding of SARS-CoV-2 in two immunocompromised patients, a case report », BMC Infect. Dis., vol. 21, no 1, p.
[2402.11616] Conservation of Ramsey's theorem for pairs and well-foundedness
arXiv:2402.11616 (math) Download PDF Comments: Subjects: Logic (math.LO) Cite as: arXiv:2402.11616 [math.LO] (or arXiv:2402.11616v1 [math.LO] for this version) https://doi.org/10.48550/arXiv.2402.11616 Submission history From: Ludovic Levy Patey [ view email] [v1] Sun, 18 Feb 2024 15:16:24 UTC (37 KB) Bibliographic Tools Bibliographic Explorer Toggle Bibliographic Explorer () Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code,...
Contact Models in Robotics: a Comparative Analysis
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Neutrophil Activation and Immune Thrombosis Profiles Persist in Convalescent COVID-19
Journal of Clinical Immunology, Mar 2023 This is a preview of a remote PDF: https://link.springer.com/content/pdf/10.1007/s10875-023-01459-x.pdf Hocini, Hakim, Wiedemann, Aurélie, Blengio, Fabiola, Lefebvre, Cécile, Cervantes-Gonzalez, Minerva, Foucat, Emile, Tisserand, Pascaline, Surenaud, Mathieu, Coléon, Séverin, Prague, Mélanie, Guillaumat, Lydia, Krief, Corinne, Fenwick, Craig, Laouénan, Cédric, Bouadma, Lila, Ghosn, Jade, Pantaleo, Giuseppe, Thiébaut, Rodolphe, Lévy, Yves, Abel,...
[2203.03986] Leveraging Randomized Smoothing for Optimal Control of Nonsmooth Dynamical Systems
[Submitted on 8 Mar 2022 ( v1 ), last revised 22 Jan 2024 (this version, v3)] Title:Leveraging Randomized Smoothing for Optimal Control of Nonsmooth Dynamical Systems Download a PDF of the paper titled Leveraging Randomized Smoothing for Optimal Control of Nonsmooth Dynamical Systems, by Quentin Le Lidec and 4 other authors Download PDF Abstract:Optimal control (OC) algorithms such as Differential Dynamic Programming (DDP) take advantage of the derivatives of the dynamics to efficiently...
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Quentin
Contact Quentin, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack