Searched for: contributor%3A%22Izadi%2C+M.+%28mentor%29%22
(1 - 18 of 18)
document
Mekkes, Erik (author)
Large Language Models of code have seen significant jumps in performance recently. However, these jumps tend to accompany a notable and perhaps concerning increase in scale and costs. We contribute an evaluation of prediction performance with respect to model size by assessing the layer-wise progression for language and user-defined elements in...
bachelor thesis 2023
document
Keeler, Miranda (author)
We present an investigation into the relationship between the average depth of the first correct prediction and the performance of CodeGen. This was done on a dataset comprised of code files comprised of C++, Go, Java, Julia, Kotlin, and Python. The analysis involved investigating the model's predictions at different layers using a Tuned Lens,...
bachelor thesis 2023
document
Kuo, Nadine (author)
The development of contemporary source code auto-completion tools have significantly boosted productivity and efficiency of developers. In 2021, the GPT-2-based Transformer CodeGPT was developed to support code completion and text-to-code generation. Similarly to most code models however, CodeGPT was trained on a limited set of widely-used...
bachelor thesis 2023
document
Malmsten, Emil (author)
The application of large language models (LLMs) for programming tasks, such as automatic code completion, has seen a significant upswing in recent years. However, due to their computational demands, they have to operate on servers. This both requires users to have a steady internet connection and raises potential privacy concerns. Therefore,...
bachelor thesis 2023
document
Sochirca, Dan (author)
Code generation models have become more popular recently, due to the fact that they assist developers in writing code in a more productive manner. While these large models deliver impressive performance, they require significant computational resources and memory, making them difficult to deploy and expensive to train. Additionally, their large...
bachelor thesis 2023
document
Storti, Mauro (author)
The significant advancements in large language models have enabled their use in various applications, such as in code auto-completion. However, the deployment of such models often encounters challenges due to their large size and prohibitive running costs. In this research, we investigate the effectiveness of post-training quantization...
bachelor thesis 2023
document
de Moor, Aral (author)
Large language models are powerful because of their state-of-the-art language processing abilities. But, they come at the cost of being extremely resource-intensive, and are steadily growing in size. As a result, compressing such models for resource- constrained devices is an active and promising re- search area. In spite of their current...
bachelor thesis 2023
document
Popescu, Popescu (author)
In recent years, deep learning techniques, particularly transformer models, have demonstrated remarkable advancements in the accuracy and efficiency of language models. These models provide the foundation for many natural language processing tasks, including code completion. The effectiveness of code completion models has been the subject of a...
bachelor thesis 2023
document
Al-Kaswan, Ali (author)
Reverse engineering binaries is required to understand and analyse programs for which the source code is unavailable. Decompilers can transform the largely unreadable binaries into a more readable source code-like representation. However, many aspects of source code, such as variable names and comments, are lost during the compilation and...
master thesis 2022
document
Otten, Marc (author)
A lot of models have been proposed to automatically complete code with promising evaluation results when tested in isolation on testing sets. This research aims to evaluate the performance of these models when used by developers when programming. Are these models still useful for actual programming and do developers even want this functionality?...
bachelor thesis 2022
document
de Weerdt, Jorit (author)
State-of-the-art machine learning-based models provide automatic intelligent code completion based on large pre-trained language models. The theoretical accuracy of these models reaches 70%. However, the research on the practicality of these models is limited. Our paper will discuss the usefulness of UniXcoder, a machine learning-based cross...
bachelor thesis 2022
document
Turk, Mika (author)
Code Completion is advancing constantly, with new research coming out all the time. One such advancement is CodeFill, which converts source files into token sequences for type prediction. To train the CodeFill model, a lot of source files are needed which take a long time to convert before training can begin. Converting the file the end-user is...
bachelor thesis 2022
document
van der Heijden, Frank (author)
Automatic code completions are a widely used feature when programming code efficiently. These completions can be made by various code language models, and these can be differentiated in three categories: single token completion, statement (line) completion and block completions. These completions, and in particular statement predictions are...
bachelor thesis 2022
document
van Dam, Tim (author)
Numerous papers have empirically studied the performance of deep learning based code completion models. However, none of these papers considered nor investigated whether good performance on statically typed languages translates to good performance on dynamically typed languages. A lack of available type information can make code completion more...
bachelor thesis 2022
document
Ionescu, Andrei (author)
Developers do not want to reinvent the wheel when developing software systems. Open-source software repositories are packed with resources that may assist developers with their work. Since Github enabled repository tagging, a new opportunity arose to help developers find the needed resources tailored to their needs. The current work proposes two...
bachelor thesis 2022
document
van der Rande, Arend (author)
Programmers and software engineers often share code and one of the largest platforms on which this happens is GitHub, with an 87,58\% market share in the Source Code Management Category. One important part of sharing code is making sure that others who might be interested in it are also able to find it. One way to do that is by adding tags to a...
bachelor thesis 2022
document
Roozendaal, Philip (author)
Software Question & Answer platforms such as Stack Overflow allow users to annotate their posts with tags in order to help organize them and aid in their discoverability. This work sets out to study the machine learning techniques used to determine these tags automatically, and see how, and to what extent, these determinations could be...
bachelor thesis 2022
document
Botocan, Cristian (author)
The users of the most widespread Software Engineering dedicated forum, Stack Overflow (SO), are confronted by the issue of posting duplicate questions and spending time waiting for an answer. Currently, only the SO users with a high reputation and the moderators manually determine this type of post. Hence, an automatic solution can save...
bachelor thesis 2022
Searched for: contributor%3A%22Izadi%2C+M.+%28mentor%29%22
(1 - 18 of 18)