Complex Process
Complex processes, encompassing diverse domains from economic activity classification to autonomous landing and medical image analysis, are being investigated through advanced computational methods. Current research focuses on developing and applying novel algorithms, including large language models (LLMs), graph neural networks (GNNs), and various deep learning architectures, to improve the understanding, modeling, and automation of these processes. This work aims to enhance interpretability, efficiency, and accuracy in analyzing complex data and extracting meaningful insights, leading to improvements in diverse fields ranging from scientific research to industrial applications. The ultimate goal is to create more robust, efficient, and trustworthy systems for managing and interpreting complex information.
Papers
3D-Prover: Diversity Driven Theorem Proving With Determinantal Point Processes
Sean Lamont, Christian Walder, Amir Dezfouli, Paul Montague, Michael Norrish
ChuLo: Chunk-Level Key Information Representation for Long Document Processing
Yan Li, Soyeon Caren Han, Yue Dai, Feiqi Cao
Optimization of Complex Process, Based on Design Of Experiments, a Generic Methodology
Julien Baderot, Yann Cauchepin (UCA), Alexandre Seiller (UCA), Richard Fontanges, Sergio Martinez, Johann Foucher, Emmanuel Fuchs, Mehdi Daanoune, Vincent Grenier, Vincent Barra (UCA), Arnaud Guillin (UCA)