Marc Schoenauer

Recent advancements have highlighted that large language models (LLMs), when given a small set of task-specific examples, demonstrate remarkable proficiency, a capability that extends to complex reasoning tasks. In particular, the combination of few-shot learning with the chain-of-thought (CoT) approach has been pivotal in steering models towards more logically consistent conclusions (Wei et al., 2022b). This paper explores the optimization of example selection for designing effective CoT pre-prompts and shows that the choice of the optimization algorithm, typically in favor of comparison-based methods such as evolutionary computation, significantly enhances efficacy and feasibility. Specifically, thanks to a limited exploitative and overfitted optimization, Evolutionary Pre-Prompt Optimization (EPPO) brings an improvement over the naive few-shot approach, exceeding 10 absolute points in exact match scores on benchmark datasets such as GSM8k and MathQA. These gains are consistent across various contexts and are further amplified when integrated with self-consistency (SC).

This chapter provides a comprehensive overview of the rapidly evolving fields of artificial intelligence, data, and robotics (ADR), introducing the foundational concepts, transformative applications, and forward-looking frameworks that structure the book. Positioned within Europe’s broader digital innovation landscape, it highlights how ADR technologies are reshaping key sectors (including manufacturing, healthcare, mobility, and environmental sustainability) while underscoring the importance of ethical, human-centric, and sustainable approaches to their development. Organized around three core themes, Foundations, Transformations, and Future Directions, the chapter situates the contributions of each subsequent section, tracing current research priorities, emerging technological trajectories, and real-world deployments. By emphasizing multidisciplinary collaboration and strategic foresight, it outlines how integrating technical excellence with societal values can foster trustworthy, equitable, and resilient digital ecosystems. Serving as a roadmap for the chapters that follow, this overview aims to inspire coordinated efforts among researchers, industry leaders, policymakers, and citizens to harness the full potential of AI, data, and robotics for the benefit of society.

This chapter explores the convergence of generative AI and robotics within the broader context of Europe’s AI, data, and robotics (ADR) strategy. It examines how these powerful general-purpose technologies are reshaping innovation across strategic sectors while also presenting complex challenges in safety, trustworthiness, and sustainability. The chapter highlights Europe’s distinct approach anchored in values-driven innovation, technological sovereignty, and strategic autonomy and outlines the role of the ADRA partnership in steering this transformation. Through initiatives such as the SRIDA, high-impact pilots, and challenge-based innovation, ADRA is fostering a resilient European ecosystem that supports responsible, human-centric development of GenAI and Robotics. The chapter concludes by emphasizing the need for coordinated investment, policy alignment, and bold action to ensure Europe remains at the forefront of this rapidly evolving technological landscape.

After Learning Evolutionary Retrofitting (AfterLearnER) consists in applying evolutionary optimization to refine fully trained machine learning models by optimizing a set of carefully chosen parameters or hyperparameters of the model, with respect to some actual, exact, and hence possibly non-differentiable error signal, performed on a subset of the standard validation set. The efficiency of AfterLearnER is demonstrated by tackling non-differentiable signals such as threshold-based criteria in depth sensing, the word error rate in speech resynthesis, the number of kills per life at Doom, computational accuracy or BLEU in code translation, image quality in 3D generative adversarial networks (GANs), and user feedback in image generation via latent diffusion models (LDM). This retrofitting can be done after training, or dynamically at inference time by taking into account the user feedback. The advantages of AfterLearnER are its versatility, the possibility to use non-differentiable feedback, including human evaluations (i.e., no gradient is needed), the limited overfitting supported by a theoretical study, and its anytime behavior. Last but not least, AfterLearnER requires only a small amount of feedback, i.e., a few dozen to a few hundred scalars, compared to the tens of thousands needed in most related published works.

AfterLearnER (After Learning Evolutionary Retrofitting) consists in applying evolutionary optimization to refine fully trained machine learning models by optimizing a set of carefully chosen parameters or hyperpa- rameters of the model, with respect to some actual, exact, and hence possibly non-differentiable error signal, performed on a subset of the standard validation set. The efficiency of AfterLearnER is demonstrated by tackling non-differentiable signals such as threshold-based criteria in depth sensing, the word error rate in speech re-synthesis, the number of kills per life at Doom, computational accuracy or BLEU in code translation, image quality in 3D generative adversarial networks (GANs), and user feedback in image generation via Latent Diffusion Models (LDM). This retrofitting can be done after training, or dynamically at inference time by taking into account the user feedback. The advantages of AfterLearnER are its versatility, the possibility to use non-differentiable feedback, including human evaluations (i.e., no gradient is needed), the limited overfitting supported by a theoretical study, and its anytime behavior. Last but not least, AfterLearnER requires only a small amount of feedback, i.e., a few dozen to a few hundred scalars, compared to the tens of thousands needed in most related published works.

The modeling and simulation of high-dimensional multiscale systems is a critical challenge across all areas of science and engineering. It is broadly believed that even with today's computer advances resolving all spatiotemporal scales described by the governing equations remains a remote target. This realization has prompted intense efforts to develop model order reduction techniques. In recent years, techniques based on deep recurrent neural networks have produced promising results for the modeling and simulation of complex spatiotemporal systems and offer large flexibility in model development as they can incorporate experimental and computational data. However, neural networks lack interpretability, which limits their utility and generalizability across complex systems. Here we propose a novel framework of Interpretable Learning Effective Dynamics (iLED) that offers comparable accuracy to state-of-the-art recurrent neural network-based approaches while providing the added benefit of interpretability. The iLED framework is motivated by Mori-Zwanzig and Koopman operator theory, which justifies the choice of the specific architecture. We demonstrate the effectiveness of the proposed framework in simulations of three benchmark multiscale systems. Our results show that the iLED framework can generate accurate predictions and obtain interpretable dynamics, making it a promising approach for solving high-dimensional multiscale systems.

This paper introduces Interactive Latent Diffusion Model (IELDM), an encapsulation of a popular text-to-image diffusion model into an Evolutionary framework, allowing the users to steer the design of images toward their goals, alleviating the tedious trial-and-error process that such tools frequently require. The users can not only designate their favourite images, allowing the system to build a surrogate model based on their goals and move in the same directions, but also click on some specific parts of the images to either locally refine the image through dedicated mutation, or recombine images by choosing on each one some regions they like. Experiments validate the benefits of IELDM, especially in a situation where Latent Diffusion Model is challenged by complex input prompts.

Model order reduction through the POD-Galerkin method can lead to dramatic gains in terms of computational efficiency in solving physical problems. However, the applicability of the method to non linear high-dimensional dynamical systems such as the Navier-Stokes equations has been shown to be limited, producing inaccurate and sometimes unstable models. This paper proposes a deep learning based closure modeling approach for classical POD-Galerkin reduced order models (ROM). The proposed approach is theoretically grounded, using neural networks to approximate well studied operators. In contrast with most previous works, the present CD-ROM approach is based on an interpretable continuous memory formulation, derived from simple hypotheses on the behavior of partially observed dynamical systems. The final corrected models can hence be simulated using most classical time stepping schemes. The capabilities of the CD-ROM approach are demonstrated on two classical examples from Computational Fluid Dynamics, as well as a parametric case, the Kuramoto-Sivashinsky equation.