Related papers: RobustA: Robust Anomaly Detection in Multimodal Da…

In multimedia understanding tasks, corrupted samples pose a critical challenge, because when fed to machine learning models they lead to performance degradation. In the past, three groups of approaches have been proposed to handle noisy…

3D object detection is an important task in autonomous driving to perceive the surroundings. Despite the excellent performance, the existing 3D detectors lack the robustness to real-world corruptions caused by adverse weathers, sensor…

Multimodal learning, which integrates data from diverse sensory modes, plays a pivotal role in artificial intelligence. However, existing multimodal learning methods often struggle with challenges where some modalities appear more dominant…

We initiate the study of multi-stage episodic reinforcement learning under adversarial corruptions in both the rewards and the transition probabilities of the underlying system extending recent results for the special case of stochastic…

Recently, multimodal prompting, which introduces learnable missing-aware prompts for all missing modality cases, has exhibited impressive performance. However, it encounters two critical issues: 1) The number of prompts grows exponentially…

A range of applications of multi-modal music information retrieval is centred around the problem of connecting large collections of sheet music (images) to corresponding audio recordings, that is, identifying pairs of audio and score…

We study episodic reinforcement learning under unknown adversarial corruptions in both the rewards and the transition probabilities of the underlying system. We propose new algorithms which, compared to the existing results in (Lykouris et…

This paper presents a methodology to detect robust zero dynamics anomaly behavior and mitigate the impacts in general multi-input multi-output (MIMO) nonlinear systems. The proposed method guarantees the resiliency and stability of the…

Multimodal Large Language Models demonstrate strong performance on multimodal benchmarks, yet often exhibit poor robustness when exposed to spurious modality interference, such as irrelevant text in vision understanding, or irrelevant…

Simultaneously using multimodal inputs from multiple sensors to train segmentors is intuitively advantageous but practically challenging. A key challenge is unimodal bias, where multimodal segmentors over rely on certain modalities, causing…

We introduce the initial release of our software Robustar, which aims to improve the robustness of vision classification machine learning models through a data-driven perspective. Building upon the recent understanding that the lack of…

Multimodal sentiment analysis is a core research area that studies speaker sentiment expressed from the language, visual, and acoustic modalities. The central challenge in multimodal learning involves inferring joint representations that…

Multivariate time series (MTS) anomaly detection is essential for maintaining the reliability of industrial systems, yet real-world deployment is hindered by two critical challenges: training data contamination (noises and hidden anomalies)…

With the rapid growth of information, recommender systems have become integral for providing personalized suggestions and overcoming information overload. However, their practical deployment often encounters ``dirty'' data, where noise or…

Despite their strong performance in embodied tasks, recent Vision-Language-Action (VLA) models remain highly fragile under multimodal perturbations, where visual corruption and linguistic noise jointly induce distribution shifts that…

We introduce the MNIST-C dataset, a comprehensive suite of 15 corruptions applied to the MNIST test set, for benchmarking out-of-distribution robustness in computer vision. Through several experiments and visualizations we demonstrate that…

To generate accurate and reliable predictions, modern AI systems need to combine data from multiple modalities, such as text, images, audio, spreadsheets, and time series. Multi-modal data introduces new opportunities and challenges for…

Modern multimodal systems deployed in industrial and safety-critical environments must remain reliable under partial sensor failures, signal degradation, or cross-modal inconsistencies. This work introduces a mathematically grounded…

Robust anomaly detection is a requirement for monitoring complex modern systems with applications such as cyber-security, fraud prevention, and maintenance. These systems generate multiple correlated time series that are highly seasonal and…

The presence of data corruption in user-generated streaming data, such as social media, motivates a new fundamental problem that learns reliable regression coefficient when features are not accessible entirely at one time. Until now,…