Related papers: A Semantic-Based Approach for Detecting and Decomp…
Novelty Detection methods identify samples that are not representative of a model's training set thereby flagging misleading predictions and bringing a greater flexibility and transparency at deployment time. However, research in this area…
Software is among the most complex endeavors of the human mind; large scale systems can have tens of millions of lines of source code. However, seldom is complexity measured above the lowest level of code, and sometimes source code files or…
We devise a new accelerated gradient-based estimating sequence technique for solving large-scale optimization problems with composite structure. More specifically, we introduce a new class of estimating functions, which are obtained by…
Empirical results in software engineering have long started to show that findings are unlikely to be applicable to all software systems, or any domain: results need to be evaluated in specified contexts, and limited to the type of systems…
Attempts of learning from hierarchical taxonomies in computer vision have been mostly focusing on image classification. Though ways of best harvesting learning improvements from hierarchies in classification are far from being solved, there…
Introduction: Taxonomies capture knowledge about a particular domain in a succinct manner and establish a common understanding among peers. Researchers use taxonomies to convey information about a particular knowledge area or to support…
Maintaining software artifacts is among the hardest tasks an engineer faces. Like any other piece of code, model transformations developed by engineers are also subject to maintenance. To facilitate the comprehension of programs, software…
Compositionality in language refers to how much the meaning of some phrase can be decomposed into the meaning of its constituents and the way these constituents are combined. Based on the premise that substitution by synonyms is…
Learning classifiers using skewed or imbalanced datasets can occasionally lead to classification issues; this is a serious issue. In some cases, one class contains the majority of examples while the other, which is frequently the more…
While technical debt grows in absolute numbers as software systems evolve over time, the density of technical debt (technical debt divided by lines of code) is reduced in some cases. This can be explained by either the application of…
One-class learning is the classic problem of fitting a model to the data for which annotations are available only for a single class. In this paper, we explore novel objectives for one-class learning, which we collectively refer to as…
Post-hoc unlearning has emerged as a practical mechanism for removing undesirable concepts from large text-to-image diffusion models. However, prior work primarily evaluates unlearning through erasure success; its impact on broader…
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…
We give a pedagogical introduction to the process of decoherence - the irreversible emergence of classical properties through interaction with the environment. After discussing the general concepts, we present the following examples:…
Component-based software development (CBSD) is an alternative approach to constructing software systems that offers numerous benefits, particularly in decreasing the complexity of system design. However, deploying components into a system…
Performance is a critical quality attribute in software development, yet the impact of method-level code changes on performance evolution remains poorly understood. While developers often make intuitive assumptions about which types of…
This paper focuses on Code Generation task that aims at generating relevant code fragments according to given natural language descriptions. In the process of software development, developers often encounter two scenarios. One is requested…
One of the most pressing threats to computing systems is software vulnerabilities, which can compromise both hardware and software components. Existing methods for vulnerability detection remain suboptimal. Traditional techniques are both…
This paper proposes a structure-aware decoding method based on large language models to address the difficulty of traditional approaches in maintaining both semantic integrity and structural consistency in nested and overlapping entity…
Deep neural networks have achieved impressive success in large-scale visual object recognition tasks with a predefined set of classes. However, recognizing objects of novel classes unseen during training still remains challenging. The…