Related papers: Reliably Detecting Model Failures in Deployment Wi…

Autonomous vehicles drive millions of miles on the road each year. Under such circumstances, deployed machine learning models are prone to failure both in seemingly normal situations and in the presence of outliers. However, in the training…

Training deep neural networks(DNN) with noisy labels is challenging since DNN can easily memorize inaccurate labels, leading to poor generalization ability. Recently, the meta-learning based label correction strategy is widely adopted to…

Model-based optimization (MBO) is increasingly applied to design problems in science and engineering. A common scenario involves using a fixed training set to train models, with the goal of designing new samples that outperform those…

We might hope that when faced with unexpected inputs, well-designed software systems would fire off warnings. Machine learning (ML) systems, however, which depend strongly on properties of their inputs (e.g. the i.i.d. assumption), tend to…

In this paper, we consider a deep learning approach to the limited aperture inverse obstacle scattering problem. It is well known that traditional deep learning relies solely on data, which may limit its performance for the inverse problem…

Dynamic Mode Decomposition (DMD) is a powerful tool for extracting spatial and temporal patterns from multi-dimensional time series, and it has been used successfully in a wide range of fields, including fluid mechanics, robotics, and…

Partially-supervised learning can be challenging for segmentation due to the lack of supervision for unlabeled structures, and the methods directly applying fully-supervised learning could lead to incompatibility, meaning ground truth is…

Assessing model generalization under distribution shift is essential for real-world deployment, particularly when labeled test data is unavailable. This paper presents a unified and practical framework for unsupervised model evaluation and…

Denoising Probabilistic Models (DPMs) represent an emerging domain of generative models that excel in generating diverse and high-quality images. However, most current training methods for DPMs often neglect the correlation between…

Due to the large number of parameters, the inference phase of Large Language Models (LLMs) is resource-intensive. Unlike traditional model compression, which needs retraining, recent dynamic computation methods show that not all components…

Industry 4.0 aims to optimize the manufacturing environment by leveraging new technological advances, such as new sensing capabilities and artificial intelligence. The DRAEM technique has shown state-of-the-art performance for unsupervised…

Failure of mission-critical equipment interrupts production and results in monetary loss. The risk of unplanned equipment downtime can be minimized through Predictive Maintenance of revenue generating assets to ensure optimal performance…

Data-driven fault detection has been regarded as a 3D image segmentation task. The models trained from synthetic data are difficult to generalize in some surveys. Recently, training 3D fault segmentation using sparse manual 2D slices is…

We propose probe-based data attribution, a method that traces behavioral changes in post-trained language models to responsible training datapoints. By computing activation-difference vectors for both test prompts and preference pairs and…

In recent years, machine learning has witnessed extensive adoption across various sectors, yet its application in medical image-based disease detection and diagnosis remains challenging due to distribution shifts in real-world data. In…

Supervised 3D Object Detection models have been displaying increasingly better performance in single-domain cases where the training data comes from the same environment and sensor as the testing data. However, in real-world scenarios data…

Unsupervised domain adaptation (UDA) involves adapting a model trained on a label-rich source domain to an unlabeled target domain. However, in real-world scenarios, the absence of target-domain labels makes it challenging to evaluate the…

Delays frequently occur in real-world environments, yet standard reinforcement learning (RL) algorithms often assume instantaneous perception of the environment. We study random sensor delays in POMDPs, where observations may arrive…

Gradient-based attacks are important methods for evaluating model robustness. However, since the proposal of APGD, it has been difficult for such methods to achieve significant breakthroughs. To achieve such an effect, we first analyze the…

Predictive maintenance (PdM) is a concept, which is implemented to effectively manage maintenance plans of the assets by predicting their failures with data driven techniques. In these scenarios, data is collected over a certain period of…