From the 1 of 5 linked papers with an AI index.
5 papers
Top- Pareto Bandits: Hypervolume Regret for Multi-Objective Slate Selection
Nicolas Gutowski, Fabien Chhel, Alexandre Letard +1
The paper studies stochastic multi‑objective bandits where a slate of k arms is chosen each round, and proposes an optimistic algorithm (THV-UCB) that greedily selects arms to maxi…
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…
ACT: Agentic Classification Tree
Vincent Grari, Tim Arni, Thibault Laugel +3
When used in high-stakes settings, AI systems are expected to produce decisions that are transparent, interpretable and auditable, a requirement increasingly expected by regulation…
Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning
Thomas Carta, Clément Romac, Thomas Wolf +3
Recent works successfully leveraged Large Language Models' (LLM) abilities to capture abstract knowledge about world's physics to solve decision-making problems. Yet, the alignment…
Structural Deep Encoding for Table Question Answering
Raphaël Mouravieff, Benjamin Piwowarski, Sylvain Lamprier
Although Transformers-based architectures excel at processing textual information, their naive adaptation for tabular data often involves flattening the table structure. This simpl…