Télécom Paris

In the context of the Classification and Regression Trees (CART) algorithm, the efficient splitting of categorical features using standard criteria like GINI and Entropy is well-established. However, using the Mean Absolute Error (MAE) criterion for categorical features has traditionally relied on various numerical encoding methods. This paper demonstrates that unsupervised numerical encoding methods are not viable for MAE criteria. Furthermore, we present a novel and efficient splitting algorithm that addresses the challenges of handling categorical features with the MAE criterion. Our findings underscore the limitations of existing approaches and offer a promising solution to enhance the handling of categorical data in CART algorithms.

Implicit Neural Representations (INRs) have revolutionized signal processing and computer vision by modeling signals as continuous, differentiable functions parameterized by neural networks. However, INRs are prone to the spectral bias problem, limiting their ability to retain high-frequency information, and often struggle with noise robustness. Motivated by recent trends in iterative refinement processes, we propose Iterative Implicit Neural Representations (I-INRs). This novel plug-and-play framework iteratively refines signal reconstructions to restore high-frequency details, improve noise robustness, and enhance generalization, ultimately delivering superior reconstruction quality. I-INRs integrate seamlessly into existing INR architectures with only a 0.5–2% increase in parameters. During reconstruction, the iterative refinement adds just 0.8–1.6% additional FLOPs over the baseline while delivering a substantial performance boost of up to +2.0 PSNR. Extensive experiments demonstrate that I-INRs consistently outperform WIRE, SIREN, and Gauss across various computer vision tasks, including image fitting, image denoising, and object occupancy prediction.

International audience

Trusting software systems, particularly autonomous ones, is challenging. To address this, formal verification techniques can ensure these systems behave as expected. Runtime Verification (RV) is a leading, lightweight method for verifying system behaviour during execution. However, traditional RV assumes perfect information, meaning the monitoring component perceives everything accurately. This assumption often fails, especially with autonomous systems operating in real-world environments where sensors might be faulty. Additionally, traditional RV considers the monitor to be passive, lacking the capability to interpret the system’s information and thus unable to address incomplete data. In this work, we extend standard RV of Linear Temporal Logic properties to accommodate scenarios where the monitor has imperfect information and behaves rationally. We outline the necessary engineering steps to update the verification pipeline and demonstrate our implementation in a case study involving robotic systems.

Deep neural networks frequently encode and propagate biases arising from data, model design, and deployment contexts, posing significant challenges for reliable and lawful AI systems. This presentation surveys debiasing techniques for deep neural networks, situating them within the regulatory constraints introduced by the AI Act. We compare supervised and unsupervised debiasing methods, emphasizing their underlying assumptions, optimization objectives, and practical trade-offs. The talk then addresses bias discovery and bias naming as foundational problems for systematic bias mitigation. Finally, we discuss emerging research directions, including privacy-aware debiasing, fairness certification, and machine unlearning, highlighting open technical challenges and unresolved tensions between fairness, robustness, and compliance.

• An end-to-end optimized pipeline for classifying mental states. • Tailed to various mainstream ML algorithms. • Achieve SOTA across different classification paradigms. • Demonstrating exceptional generalizability across subjects. Mental states, a complex union of cognitive, emotional, and perceptual conditions, fundamentally shape how individuals perceive and interact with their surroundings. Detecting these states is vital, as it reveals the underlying processes that govern behaviour and enables targeted interventions across diverse fields such as mental health, education, and human-computer interaction. Generalisability across subjects and trials is essential to ensure that these interventions are effective and reliable in varied real-world settings, thereby enhancing their practical applicability. In this paper, we introduce an end-to-end optimised pipeline for classifying mental states from electroencephalography (EEG) signals. Through quantitative studies of data preprocessing and feature enhancement of continuous data collected under less stringent conditions, our pipeline utilises specially designed, cutting-edge, lightweight classifiers and achieves new state-of-the-art performance. Specifically addressing the challenge of generalisability in EEG signal research, our pipeline demonstrates robust performance, achieving a peak accuracy of 79.1% and an average of 71.9% in cross-subject scenarios, and a high of 89.3% with an average of 85.4% in cross-trial evaluations.