7 papers
A Training-Free Regeneration Paradigm: Contrastive Reflection Memory Guided Self-Verification and Self-Improvement
Yuran Li, Di Wu, Benoit Boulet
Verification-guided self-improvement has recently emerged as a promising approach to improving the accuracy of large language model (LLM) outputs. However, existing approaches face…
Causal Feature Selection for Weather-Driven Residential Load Forecasting
Elise Zhang, François Mirallès, Stéphane Dellacherie +2
Weather is a dominant external driver of residential electricity demand, but adding many meteorological covariates can inflate model complexity and may even impair accuracy. Select…
DRDT3: Diffusion-Refined Decision Test-Time Training Model
Xingshuai Huang, Di Wu, Benoit Boulet
Decision Transformer (DT), a trajectory modelling method, has shown competitive performance compared to traditional offline reinforcement learning (RL) approaches on various classi…
Goal-Conditioned Data Augmentation for Offline Reinforcement Learning
Xingshuai Huang, Di Wu, Benoit Boulet
Offline reinforcement learning (RL) enables policy learning from pre-collected offline datasets, relaxing the need to interact directly with the environment. However, limited by th…
Leveraging LLMs as Meta-Judges: A Multi-Agent Framework for Evaluating LLM Judgments
Yuran Li, Jama Hussein Mohamud, Chongren Sun +2
Large language models (LLMs) are being widely applied across various fields, but as tasks become more complex, evaluating their responses is increasingly challenging. Compared to h…
MXMap: A Multivariate Cross Mapping Framework for Causal Discovery in Dynamical Systems
Elise Zhang, François Mirallès, Raphaël Rousseau-Rizzi +3
Convergent Cross Mapping (CCM) is a powerful method for detecting causality in coupled nonlinear dynamical systems, providing a model-free approach to capture dynamic causal intera…