collaborators

5 papers

cs.AI2026

Position Spaces and Graphs

Rita-Nathalia Assaf, Tom Davot, Frédéric Lardeux +1

In this paper, we introduce position graphs, a graph-based reasoning framework based on the formalization of position spaces. This framework utilizes two strict partial orders, rep…

cs.CL2026

Progress Ratio Embeddings: An Impatience Signal for Robust Length Control in Neural Text Generation

Ivanhoé Botcazou, Tassadit Amghar, Sylvain Lamprier +1

Modern neural language models achieve high accuracy in text generation, yet precise control over generation length remains underdeveloped. In this paper, we first investigate a rec…

cs.AI2026

Stein Variational Black-Box Combinatorial Optimization

Thomas Landais, Olivier Goudet, Adrien Goëffon +2

Combinatorial black-box optimization in high-dimensional settings demands a careful trade-off between exploiting promising regions of the search space and preserving sufficient exp…

cs.LG2026

Black-Box Combinatorial Optimization with Order-Invariant Reinforcement Learning

Olivier Goudet, Quentin Suire, Adrien Goëffon +2

We introduce an order-invariant reinforcement learning framework for black-box combinatorial optimization. Classical estimation-of-distribution algorithms (EDAs) often rely on lear…

cs.NE2025

Discovering new robust local search algorithms with neuro-evolution

Mohamed Salim Amri Sakhri, Adrien Goëffon, Olivier Goudet +2

This paper explores a novel approach aimed at overcoming existing challenges in the realm of local search algorithms. Our aim is to improve the decision process that takes place wi…