Related papers: SynSpill: Improved Industrial Spill Detection With…

In recent years, the emergence of models capable of generating images from text has attracted considerable interest, offering the possibility of creating realistic images from text descriptions. Yet these advances have also raised concerns…

The advancement of large language models (LLMs) is critically dependent on the availability of high-quality datasets for Supervised Fine-Tuning (SFT), alignment tasks like Direct Preference Optimization (DPO), etc. In this work, we present…

Recent advancements in Large Vision-Language Models (LVLMs) have demonstrated impressive capabilities across various multimodal tasks. They continue, however, to struggle with trivial scenarios such as reading values from Digital…

One way to mitigate risks in vision-language models (VLMs) is to remove dangerous samples in their training data. However, such data moderation can be easily bypassed when harmful images are split into small, benign-looking patches,…

Large-scale pre-trained Vision & Language (VL) models have shown remarkable performance in many applications, enabling replacing a fixed set of supported classes with zero-shot open vocabulary reasoning over (almost arbitrary) natural…

Laboratories are prone to severe injuries from minor unsafe actions, yet continuous safety monitoring -- beyond mandatory pre-lab safety training -- is limited by human availability. Vision language models (VLMs) offer promise for…

Deep Learning has seen an unprecedented increase in vision applications since the publication of large-scale object recognition datasets and introduction of scalable compute hardware. State-of-the-art methods for most vision tasks for…

We propose a deep learning framework to detect and categorize oil spills in synthetic aperture radar (SAR) images at a large scale. By means of a carefully designed neural network model for image segmentation trained on an extensive…

Recent advances in image generation have led to the widespread availability of highly realistic synthetic media, increasing the difficulty of reliable deepfake detection. A key challenge is generalization, as detectors trained on a narrow…

Small language models (SLMs) are promising for real-world deployment due to their efficiency and low operational cost. However, their limited capacity struggles with high-stakes legal reasoning tasks that require coherent statute…

Dataset distillation (DD) condenses large datasets into compact yet informative substitutes, preserving performance comparable to the original dataset while reducing storage, transmission costs, and computational consumption. However,…

Machine learning (ML) models frequently rely on training data that may include sensitive or personal information, raising substantial privacy concerns. Legislative frameworks such as the General Data Protection Regulation (GDPR) and the…

Vision-language models (VLMs) still struggle with visual perception tasks such as spatial understanding and viewpoint recognition. One plausible contributing factor is that natural image datasets provide limited supervision for low-level…

Adequate bridge inspection is increasingly challenging in many countries due to growing ailing stocks, compounded with a lack of staff and financial resources. Automating the key task of visual bridge inspection, classification of defects…

Zero-shot 3D object classification is crucial for real-world applications like autonomous driving, however it is often hindered by a significant domain gap between the synthetic data used for training and the sparse, noisy LiDAR scans…

The in-context learning ability of large language models (LLMs) enables them to generalize to novel downstream tasks with relatively few labeled examples. However, they require enormous computational resources to be deployed. Alternatively,…

Industrial accidents, particularly in high-risk domains such as surface and underground mining, are frequently caused by unsafe worker behaviors. Traditional manual inspection remains labor-intensive, error-prone, and insufficient for…

Database research and the development of learned query optimisers rely heavily on realistic SQL workloads. Acquiring real-world queries is increasingly difficult, however, due to strict privacy regulations, and publicly released anonymised…

Behavioural differences across organisms, whether healthy or pathological, are closely tied to the structure of their neural circuits. Yet, the fine-scale synaptic changes that give rise to these variations remain poorly understood, in part…

The increasing complexity of modern software systems exacerbates the prevalence of security vulnerabilities, posing risks of severe breaches and substantial economic loss. Consequently, robust code vulnerability detection is essential for…