Institution profile

CentraleSupélec

Academic institutioneurope · fr
Official website
Research library308linked papers
Opportunities0open roles
Selected work

Representative Papers

ViDoRe V3: A Comprehensive Evaluation of Retrieval Augmented Generation in Complex Real-World Scenarios

Jan 13, 2026

Existing retrieval-augmented generation (RAG) evaluation benchmarks struggle to address real-world challenges such as multi-document synthesis, visual understanding, and fine-grained source attribution. To bridge this gap, this work introduces the first comprehensive multimodal RAG benchmark that integrates visual content, cross-document reasoning, and multilingual support. The benchmark comprises 26,000 visually rich document pages spanning ten specialized domains and 3,099 human-verified queries, accompanied by high-quality annotations for retrieval relevance, bounding box localization, and reference answers. Systematic evaluation reveals that vision-aware retrievers significantly outperform purely text-based approaches, and late interaction with re-ranking further enhances performance. Nevertheless, current models still exhibit notable deficiencies in interpreting non-textual elements, answering open-ended questions, and achieving fine-grained visual grounding.

3 citations1 influentialRead paper

El0ps: An Exact L0-regularized Problems Solver

Jun 04, 2025

L₀-regularized optimization remains computationally challenging for efficient solving and practical deployment in machine learning, statistical modeling, and signal processing. To address this, we propose the first customizable L₀ modeling framework, integrating high-performance exact solvers based on branch-and-bound, dynamic programming, and sparse optimization. Implemented as a modular Python toolbox, it enables flexible user specification of objective functions and constraints, and provides out-of-the-box machine learning pipelines. Empirical evaluation demonstrates substantial improvements in feature selection accuracy and model interpretability across diverse sparse modeling tasks, achieving state-of-the-art solution quality and runtime efficiency. The framework is open-source, designed for extensibility, and supports seamless integration into industrial-scale machine learning systems.

1 citationsRead paper

Optimal Data Splitting for Holdout Cross-Validation in Large Covariance Matrix Estimation

Mar 19, 2025

Cross-validation data splitting in high-dimensional covariance matrix estimation lacks rigorous finite-sample theoretical foundations, particularly under hold-out validation. Method: We derive the first closed-form analytical expression for the estimation error under the white inverse Wishart population model, integrating high-dimensional statistics, random matrix theory, and asymptotic spectral analysis. Contribution/Results: We establish that the optimal train-test ratio scales as $Theta(sqrt{p})$, where $p$ is the dimension; this scaling holds exactly for finite samples and unifies hold-out and $k$-fold cross-validation in the high-dimensional asymptotic limit—both converge to the optimal error bound of the nonlinear shrinkage estimator. Our work provides the first analytically tractable and empirically verifiable theoretical framework for cross-validation data partitioning in covariance estimation, resolving the longstanding gap in finite-sample performance characterization of cross-validation for this fundamental problem.

1 citationsRead paper

Downlink Multiuser Communications Relying on Flexible Intelligent Metasurfaces

Feb 23, 2025

This work addresses the power minimization problem in a multi-user MIMO downlink system employing a flexible intelligent metasurface (FIM) at the base station. We propose a joint optimization framework that simultaneously designs the transmit beamformer and the three-dimensional surface deformation of the FIM, subject to per-user SINR constraints and physical deformation limits of the FIM. To the best of our knowledge, this is the first study to introduce deformable metasurfaces into multi-user downlink communications; by dynamically reshaping the radiating surface geometry, it enhances channel spatial degrees of freedom and overcomes the inherent limitations of conventional rigid antenna arrays. A computationally efficient alternating optimization algorithm is developed to tackle the non-convex joint design problem, integrated with electromagnetic radiation modeling to ensure physical realizability. Simulation results demonstrate that, for identical data rates, the proposed method reduces total transmit power by approximately 3 dB compared to a two-dimensional rigid array, thereby significantly improving energy efficiency.

1 citationsRead paper

Are foundation models for computer vision good conformal predictors?

Dec 08, 2024arXiv.org

This study systematically evaluates the uncertainty calibration capabilities of vision and multimodal foundation models within the conformal prediction (CP) framework, with emphasis on risk-sensitive applications. We examine prevalent Vision Transformer (ViT) architectures, three canonical CP methods—Adaptive Prediction Sets (APS), Split CP, and Adaptive CP—and multiple image classification benchmarks. Our key contributions are: (i) ViT-based models exhibit inherent compatibility with CP, achieving well-calibrated uncertainty estimates without retraining; (ii) adapter-based fine-tuning substantially outperforms prompt learning for CP adaptation; (iii) APS achieves the optimal trade-off between theoretical guarantees and empirical performance—strictly maintaining marginal coverage while yielding more compact prediction sets; and (iv) post-hoc confidence calibration degrades Adaptive CP’s efficacy. Collectively, these findings demonstrate that modern foundation models possess strong inherent conformalizability, offering a robust pathway for uncertainty quantification in high-stakes visual recognition tasks.

1 citationsRead paper
Recent publications

Latest Papers