From the 5 of 167 papers with an AI index.
50 citations
- Centre National de la Recherche ScientifiqueFR96 papers
- Sorbonne UniversitéFR76 papers
- Université Paris CitéFR54 papers
- Université Paris Sciences et LettresFR47 papers
- Laboratoire de Physique de l'Ecole Normale SupérieureFR40 papers
- Université Paris-SaclayFR29 papers
- Département de mathématiques et applicationsFR25 papers
- Sorbonne Paris CitéFR23 papers
- Laboratoire Kastler BrosselFR19 papers
- Département d'InformatiqueFR17 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR16 papers
- CEA Paris-SaclayFR14 papers
9 papers · 1 filter
Chaining 2-FWL GNNs for Combinatorial Graph Alignment
Marc Lelarge
For the combinatorial graph alignment problem (GAP) -- finding the node correspondence that maximizes the number of common edges (nce) between two unlabeled graphs -- properly init…
Budgeted Online Influence Maximization
Pierre Perrault, Jennifer Healey, Zheng Wen +1
We introduce a new budgeted framework for online influence maximization, considering the total cost of an advertising campaign instead of the common cardinality constraint on a cho…
Multi-Component VAE with Gaussian Markov Random Field
Fouad Oubari, Mohamed El-Baha, Raphael Meunier +2
Multi-component datasets with intricate dependencies, like industrial assemblies or multi-modal imaging, challenge current generative modeling techniques. Existing Multi-component…
Fast 3D Diffusion for Scalable Granular Media Synthesis
Muhammad Moeeze Hassan, Régis Cottereau, Filippo Gatti +1
Discrete Element Method (DEM) simulations of granular media are computationally intensive, particularly during initialization phases dominated by large displacements and kinetic en…
Guided Flow Policy: Learning from High-Value Actions in Offline Reinforcement Learning
Franki Nguimatsia Tiofack, Théotime Le Hellard, Fabian Schramm +2
Offline reinforcement learning often relies on behavior regularization that enforces policies to remain close to the dataset distribution. However, such approaches fail to distingu…
Humanity's Last Exam
Long Phan, Alice Gatti, Ziwen Han +1144
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…