Diffusion scientifique

Dernières publications

Focus on Relevant Road Users with Multi-Rules Reachable Sets
Communication lors d'une conférence

Monica Fossati, Ezio Malis, Philippe Martinet

Autonomous driving in urban environments poses significant challenges due to the presence of numerous heterogeneous agents, which may or may not comply with traffic rules. Considering all agents in the scene when exploring possible future scenarios can be computationally…

INT CL A
T-CoLoc: Leveraging Tethers for Reliable Co-Localization within an Underwater ROV Chain
Communication lors d'une conférence

Juliette Drupt, Claire Dune, Andrew I. Comport, Vincent Hugel

Underwater Remotely Operated Vehicles (ROVs) exchange data with a control station via a communication cable. One or more intermediate robots can be placed along this tether to manage its shape and minimize the mechanical effects on the ROV. This work deals with the localization…

INT CL A
Compressible Tasks in Green Data Centers as Grid-Forming Support Assets
Communication lors d'une conférence

Anna Vandi, Ramon Aparicio-Pardo, Guillaume Urvoy-Keller

Renewable microgrids can help data centers cope with the increasing demand for cloud-based services, but they pay the price of the double uncertainty of workload and renewable resource availability. The mismatch between demand and renewable supply prevents microgrid-based data…

INT CL
The Closed Hull Game and the Closed Interval Game
Communication lors d'une conférence

Samuel N Araújo, Fabricio Benevides, Nicolas Martins, Nicolas Nisse, Rudini Sampaio

Given a set S of vertices in a graph G, its geodesic interval is the set I(S) containing S and all vertices on a shortest path between vertices of S. A set S is convex if I(S) = S. Moreover, the convex hull H(S) of S is the smallest convex set containing S. In 1984, Harary…

INT CL A
Stick-Breaking Embedded Topic Model with Continuous Optimal Transport for Online Analysis of Document Streams
Communication lors d'une conférence

Federica Granese, Serena Villata, Charles Bouveyron

Online topic models are unsupervised algorithms to identify latent topics in data streams that continuously evolve over time. Although these methods naturally align with real-world scenarios, they have received considerably less attention from the community compared to their…

INT CL
Robust fine-tuning from non-robust pre-trained models: mitigating suboptimal transfer with epsilon-scheduling
Communication lors d'une conférence

Jonas Ngnawé, Maxime Heuillet, Sabyasachi Sahoo, Yann Pequignot, Ola Ahmad, Audrey Durand, Frédéric Precioso, Christian Gagné

Fine-tuning pretrained models is a standard and effective workflow in modern machine learning. However, robust fine-tuning (RFT), which aims to simultaneously achieve adaptation to a downstream task and robustness to adversarial examples, remains challenging. Despite the…

INT CL A
Toutes les publications i3S (sur le site HAL)