Related papers: Co-Change Graph Entropy: A New Process Metric for …
We present Entropy Adaptive Decoding (EAD), a novel approach for efficient language model inference that dynamically switches between different-sized models based on prediction uncertainty. By monitoring rolling entropy in model logit…
Data stream mining problem has caused widely concerns in the area of machine learning and data mining. In some recent studies, ensemble classification has been widely used in concept drift detection, however, most of them regard…
Software defect prediction models can assist software testing initiatives by prioritizing testing error-prone modules. In recent years, in addition to the traditional defect prediction model approach of predicting defects from class,…
In this paper, we propose a novel method, aggregation cross-entropy (ACE), for sequence recognition from a brand new perspective. The ACE loss function exhibits competitive performance to CTC and the attention mechanism, with much quicker…
Subset repair is an important data cleaning technique that enforces integrity constraints by deleting a minimal number of conflicting tuples, yet multiple minimal repairs often exist. Density-based methods address this ambiguity by favoring…
We find that LoRA fine-tuning exhibits un-learning on contested examples: items with high annotator disagreement show increasing loss during training, a qualitatively distinct pattern largely absent under full fine-tuning and consistent…
Fault-proneness is a measure that indicates the possibility of programming errors occurring within a software system. On the other hand, change-proneness refers to the potential for modifications to be made to the software. Both of these…
Optical Character Recognition (OCR) is fundamental to Vision-Language Models (VLMs) and high-quality data generation for LLM training. Yet, despite progress in average OCR accuracy, state-of-the-art VLMs still struggle with detecting…
With the sharp rise in software dependability and failure cost, high quality has been in great demand. However, guaranteeing high quality in software systems which have grown in size and complexity coupled with the constraints imposed on…
Just-in-time defect prediction assigns a defect risk to each new change to a software repository in order to prioritize review and testing efforts. Over the last decades different approaches were proposed in literature to craft more…
Software engineering activities in the Industry has come a long way with various improve- ments brought in various stages of the software development life cycle. The complexity of modern software, the commercial constraints and the…
This paper presents a command-line tool, called Entropia, that implements a family of conformance checking measures for process mining founded on the notion of entropy from information theory. The measures allow quantifying classical…
We present two novel models of document coherence and their application to information retrieval (IR). Both models approximate document coherence using discourse entities, e.g. the subject or object of a sentence. Our first model views text…
End-to-end image/video codecs are getting competitive compared to traditional compression techniques that have been developed through decades of manual engineering efforts. These trainable codecs have many advantages over traditional…
Recent vision language models (VLMs) like CLIP have demonstrated impressive anomaly detection performance under significant distribution shift by utilizing high-level semantic information through text prompts. However, these models often…
Zero-shot image anomaly classification (AC) and segmentation (AS) are vital for industrial quality control, detecting defects without prior training data. Existing representation-based methods compare patch features with nearest neighbors…
Mapping complex input data into suitable lower dimensional manifolds is a common procedure in machine learning. This step is beneficial mainly for two reasons: (1) it reduces the data dimensionality and (2) it provides a new data…
Many multivariate time series anomaly detection frameworks have been proposed and widely applied. However, most of these frameworks do not consider intrinsic relationships between variables in multivariate time series data, thus ignoring…
Methods such as non-intrusive polynomial chaos (NIPC), and stochastic collocation are frequently used for uncertainty propagation problems. Particularly for low-dimensional problems, these methods often use a tensor-product grid for…
Code smells represent sub-optimal implementation choices applied by developers when evolving software systems. The negative impact of code smells has been widely investigated in the past: besides developers' productivity and ability to…