Related papers: LUCID: A Framework for Reducing False Positives an…
We propose the Uncertainty Contrastive Framework (UCF), a Positive-Unlabeled (PU) representation learning framework that integrates uncertainty-aware contrastive loss, adaptive temperature scaling, and a self-attention-guided LSTM encoder…
Deepfake detection faces a critical generalization hurdle, with performance deteriorating when there is a mismatch between the distributions of training and testing data. A broadly received explanation is the tendency of these detectors to…
Modern software deployment process produces software that is uniform, and hence vulnerable to large-scale code-reuse attacks. Compiler-based diversification improves the resilience and security of software systems by automatically…
Despite advances in machine learning-based medical image classifiers, the safety and reliability of these systems remain major concerns in practical settings. Existing auditing approaches mainly rely on unimodal features or metadata-based…
Large language models (LLMs) are increasingly deployed under diverse numerical precision configurations, including standard floating-point formats (e.g., bfloat16 and float16) and quantized integer formats (e.g., int16 and int8), to meet…
A primary challenge in semi-supervised learning (SSL) for segmentation is the confirmation bias from noisy pseudo-labels, which destabilizes training and degrades performance. We propose Inconsistency Masks (IM), a framework that reframes…
The computational fabrication pipeline for 3D printing is much like a compiler - users design models in Computer Aided Design (CAD) tools that are lowered to polygon meshes to be ultimately compiled to machine code by 3D slicers. For…
Clustering is an unsupervised technique of Data Mining. It means grouping similar objects together and separating the dissimilar ones. Each object in the data set is assigned a class label in the clustering process using a distance measure.…
Quantum programs exhibit inherent non-deterministic behavior, which poses more significant challenges for error discovery compared to classical programs. While several testing methods have been proposed for quantum programs, they often…
Software containers are widely adopted for developing and deploying software applications. Despite their popularity, major security concerns arise during container development and deployment. Software Engineering (SE) research literature…
Real-world datasets inevitably contain biases that arise from different sources or conditions during data collection. Consequently, such inconsistency itself acts as a confounding factor that disturbs the cluster analysis. Existing methods…
Modern deep neural networks can achieve high accuracy when the training distribution and test distribution are identically distributed, but this assumption is frequently violated in practice. When the train and test distributions are…
Containers improve the efficiency in application deployment and thus have been widely utilised on Cloud and lately in High Performance Computing (HPC) environments. Containers encapsulate complex programs with their dependencies in isolated…
Self-consistency decoding enhances LLMs' performance on reasoning tasks by sampling diverse reasoning paths and selecting the most frequent answer. However, it is computationally expensive, as sampling many of these (lengthy) paths is…
This work presents a framework for control theory based on constructive analysis to account for discrepancy between mathematical results and their implementation in a computer, also referred to as computational uncertainty. In control…
Unit tests are critical in the hardware design lifecycle to ensure that component design modules are functionally correct and conform to the specification before they are integrated at the system level. Thus developing unit tests targeting…
Large language models (LLMs) are increasingly deployed across diverse domains, yet they are prone to generating factually incorrect outputs - commonly known as "hallucinations." Among existing mitigation strategies, uncertainty-based…
LiDAR point clouds are fundamental to various applications, yet the extreme sparsity of high-precision geometric details hinders efficient context modeling, thereby limiting the compression speed and performance of existing methods. To…
Learning exists in the context of data, yet notions of confidence typically focus on model predictions, not label quality. Confident learning (CL) is an alternative approach which focuses instead on label quality by characterizing and…
Nowadays, locating software components responsible for observed failures is one of the most expensive and error-prone tasks in the software development process. To improve the debugging process efficiency, some effort was already made to…