Related papers: McUDI: Model-Centric Unsupervised Degradation Indi…

Missing instances in time series data impose a significant challenge to deep learning models, particularly in regression tasks. In the Earth Observation field, satellite failure or cloud occlusion frequently results in missing time-steps,…

Model predictive control (MPC) has been applied to many platforms in robotics and autonomous systems for its capability to predict a system's future behavior while incorporating constraints that a system may have. To enhance the performance…

Industrial prognostics focuses on utilizing degradation signals to forecast and continually update the residual useful life of complex engineering systems. However, existing prognostic models for systems with multiple failure modes face…

The reliability of machine learning (ML) software systems is heavily influenced by changes in data over time. For that reason, ML systems require regular maintenance, typically based on model retraining. However, retraining requires…

Ocean exploration places high demands on autonomous underwater vehicles, especially when there's observation delay. We propose age of information optimized Markov decision process (AoI-MDP) to enhance underwater tasks by modeling…

Computer-aided diagnosis systems must make critical decisions from medical images that are often noisy, ambiguous, or conflicting, yet today's models are trained on overly simplistic labels that ignore diagnostic uncertainty. One-hot labels…

Bayesian finite mixture models can identify discrete risk clusters (low-risk vs. high-risk equipment), but face three critical bottlenecks: (1) insufficient degradation signals from coarse state discretization, (2) unstable cluster…

Mechanistic dynamic models allow for a quantitative and systematic interpretation of data and the generation of testable hypotheses. However, these models are often over-parameterized, leading to non-identifiability and non-observability,…

A significant challenge in maintaining real-world machine learning models is responding to the continuous and unpredictable evolution of data. Most practitioners are faced with the difficult question: when should I retrain or update my…

Masked Autoencoders (MAEs) learn rich low-level representations from unlabeled data but require substantial labeled data to effectively adapt to downstream tasks. Conversely, Instance Discrimination (ID) emphasizes high-level semantics,…

Anomaly detection is fundamental for ensuring quality control and operational efficiency in industrial environments, yet conventional approaches face significant challenges when training data contains mislabeled samples-a common occurrence…

Language models often struggle with temporal misalignment, performance degradation caused by shifts in the temporal distribution of data. Continuously updating models to avoid degradation is expensive. Can models be adapted without updating…

Automatic medical image segmentation plays a critical role in scientific research and medical care. Existing high-performance deep learning methods typically rely on large training datasets with high-quality manual annotations, which are…

Safety goes first. Meeting and maintaining industry safety standards for robustness of artificial intelligence (AI) and machine learning (ML) models require continuous monitoring for faults and performance drops. Deep learning models are…

To train the change detector, bi-temporal images taken at different times in the same area are used. However, collecting labeled bi-temporal images is expensive and time consuming. To solve this problem, various unsupervised change…

Road infrastructure maintenance inspection is typically a labour-intensive and critical task to ensure the safety of all the road users. In this work, we propose a detailed methodology to use state-of-the-art techniques in artificial…

We present a data-driven optimization approach for robotic controlled deposition with a degradable tool. Existing methods make the assumption that the tool tip is not changing or is replaced frequently. Errors can accumulate over time as…

Pre-trained foundation models, due to their enormous capacity and exposure to vast amounts of data during pre-training, are known to have learned plenty of real-world concepts. An important step in making these pre-trained models effective…

Health indicators (HIs) are central to diagnosing and prognosing the condition of aerospace composite structures, enabling efficient maintenance and operational safety. However, extracting reliable HIs remains challenging due to variability…

Recursive learning -- where models are trained on data generated by previous versions of themselves -- is increasingly common in large language models, autonomous agents, and self-supervised systems. However, standard performance metrics…