Related papers: Eigen-Value: Efficient Domain-Robust Data Valuatio…

Recent advancements in IoT technologies have underscored the importance of using sensor data to understand environmental contexts effectively. This paper introduces a novel embedded system designed to autonomously label sensor data directly…

Usually considered as a classification problem, entity resolution (ER) can be very challenging on real data due to the prevalence of dirty values. The state-of-the-art solutions for ER were built on a variety of learning models (most…

In autonomous driving and robotics, ensuring road safety and reliable decision-making critically depends on out-of-distribution (OOD) segmentation. While numerous methods have been proposed to detect anomalous objects on the road,…

High-quality data is crucial for accurate machine learning and actionable analytics, however, mislabeled or noisy data is a common problem in many domains. Distinguishing low- from high-quality data can be challenging, often requiring…

Assessing the safety of autonomous driving policy is of great importance, and reinforcement learning (RL) has emerged as a powerful method for discovering critical vulnerabilities in driving policies. However, existing RL-based approaches…

Unsupervised domain adaptation (UDA) aims to mitigate the domain shift issue, where the distribution of training (source) data differs from that of testing (target) data. Many models have been developed to tackle this problem, and recently…

Out-of-distribution (OOD) generalization remains a fundamental challenge in real-world classification, where test distributions often differ substantially from training data. Most existing approaches pursue domain-invariant representations,…

Deep neural networks (DNNs) have become the de facto learning mechanism in different domains. Their tendency to perform unreliably on out-of-distribution (OOD) inputs hinders their adoption in critical domains. Several approaches have been…

Embedding is a useful technique to project a high-dimensional feature into a low-dimensional space, and it has many successful applications including link prediction, node classification and natural language processing. Current approaches…

Variational autoencoders (VAEs) are influential generative models with rich representation capabilities from the deep neural network architecture and Bayesian method. However, VAE models have a weakness that assign a higher likelihood to…

Egocentric video action recognition under domain shifts remains challenging due to large intra-class spatio-temporal variability, long-tailed feature distributions, and strong correlations between actions and environments. Existing…

Assessing the importance of individual training samples is a key challenge in machine learning. Traditional approaches retrain models with and without specific samples, which is computationally expensive and ignores dependencies between…

These notes are based on lectures delivered by G. Schehr at the XVIth School on Fundamental Problems in Statistical Physics (FPSP), held in Oropa (Italy) from 30 June to 11 July 2025. After a brief introduction to extreme value statistics…

Reliable evaluation of AI systems remains a fundamental challenge when ground truth labels are unavailable, particularly for systems generating natural language outputs like AI chat and agent systems. Many of these AI agents and systems…

Neuromorphic hardware equipped with learning capabilities can adapt to new, real-time data. While models of Spiking Neural Networks (SNNs) can now be trained using gradient descent to reach an accuracy comparable to equivalent conventional…

End-to-end differentiable learning for autonomous driving (AD) has recently become a prominent paradigm. One main bottleneck lies in its voracious appetite for high-quality labeled data e.g. 3D bounding boxes and semantic segmentation,…

We propose a new representation learning solution for the classification of cognitive load based on Electroencephalogram (EEG). Our method integrates both time and frequency domains by first passing the raw EEG signals through the…

Power systems are developing very fast nowadays, both in size and in complexity; this situation is a challenge for Early Event Detection (EED). This paper proposes a data- driven unsupervised learning method to handle this challenge.…

Reinforcement Learning (RL) has significantly advanced Large Language Models (LLMs) in verifiable domains, but aligning models for open-ended generation remains profoundly challenging due to the lack of definitive rewards. Current…

Generative modeling has recently shown remarkable promise for visuomotor policy learning, enabling flexible and expressive control across diverse embodied AI tasks. However, existing generative policies often struggle with data…