collaborators

5 papers

cs.LG2025

Adaptive Regime-Switching Forecasts with Distribution-Free Uncertainty: Deep Switching State-Space Models Meet Conformal Prediction

Echo Diyun LU, Charles Findling, Marianne Clausel +3

Regime transitions routinely break stationarity in time series, making calibrated uncertainty as important as point accuracy. We study distribution-free uncertainty for regime-swit…

cs.LG2025

Position: Causal Machine Learning Requires Rigorous Synthetic Experiments for Broader Adoption

Audrey Poinsot, Panayiotis Panayiotou, Alessandro Leite +3

Causal machine learning has the potential to revolutionize decision-making by combining the predictive power of machine learning algorithms with the theory of causal inference. How…

cs.CL2025

From Bytes to Ideas: Language Modeling with Autoregressive U-Nets

Mathurin Videau, Badr Youbi Idrissi, Alessandro Leite +3

Tokenization imposes a fixed granularity on the input text, freezing how a language model operates on data and how far in the future it predicts. Byte Pair Encoding (BPE) and simil…

cs.CL2024

Evolutionary Pre-Prompt Optimization for Mathematical Reasoning

Mathurin Videau, Alessandro Leite, Marc Schoenauer +1

Recent advancements have highlighted that large language models (LLMs), when given a small set of task-specific examples, demonstrate remarkable proficiency, a capability that exte…

cs.CV2024

Mixture of Experts in Image Classification: What's the Sweet Spot?

Mathurin Videau, Alessandro Leite, Marc Schoenauer +1

Mixture-of-Experts (MoE) models have shown promising potential for parameter-efficient scaling across domains. However, their application to image classification remains limited, o…