9 papers
Post-Training Corrections for Improved Time-Series Forecasting
Hamza Cherkaoui, Malik Tiomoko, Giuseppe Paolo +4
Time-series forecasting is a critical task in various business domains, but it remains inherently challenging. Typically, large forecasting models are trained in a single, resource…
Solving a Million-Step LLM Task with Zero Errors
Elliot Meyerson, Giuseppe Paolo, Roberto Dailey +6
LLMs have achieved remarkable breakthroughs in reasoning, insights, and tool use, but chaining these abilities into extended processes at the scale of those routinely executed by h…
From Data to Rewards: a Bilevel Optimization Perspective on Maximum Likelihood Estimation
Abdelhakim Benechehab, Gabriel Singer, Corentin Léger +5
Generative models form the backbone of modern machine learning, underpinning state-of-the-art systems in text, vision, and multimodal applications. While Maximum Likelihood Estimat…
Kolb-Based Experiential Learning for Generalist Agents with Human-Level Kaggle Data Science Performance
Antoine Grosnit, Alexandre Maraval, Refinath S N +16
Human expertise emerges through iterative cycles of interaction, reflection, and internal model updating, which are central to cognitive theories such as Kolb's experiential learni…
TAG: A Decentralized Framework for Multi-Agent Hierarchical Reinforcement Learning
Giuseppe Paolo, Abdelhakim Benechehab, Hamza Cherkaoui +2
Hierarchical organization is fundamental to biological systems and human societies, yet artificial intelligence systems often rely on monolithic architectures that limit adaptabili…
AdaPTS: Adapting Univariate Foundation Models to Probabilistic Multivariate Time Series Forecasting
Abdelhakim Benechehab, Vasilii Feofanov, Giuseppe Paolo +3
Pre-trained foundation models (FMs) have shown exceptional performance in univariate time series forecasting tasks. However, several practical challenges persist, including managin…