Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Prenner, Julian Aron"'
Autor:
Prenner, Julian Aron, Robbes, Romain
Deep learning source code models have been applied very successfully to the problem of automated program repair. One of the standing issues is the small input window of current models which often cannot fully fit the context code required for a bug f
Externí odkaz:
http://arxiv.org/abs/2312.04986
Autor:
Prenner, Julian Aron, Robbes, Romain
Recently, we can notice a transition to data-driven techniques in Automated Program Repair (APR), in particular towards deep neural networks. This entails training on hundreds of thousands or even millions of non-executable code fragments. We would l
Externí odkaz:
http://arxiv.org/abs/2304.01102
The Codex model has demonstrated extraordinary competence in synthesizing code from natural language problem descriptions. However, in order to reveal unknown failure modes and hidden biases, such large-scale models must be systematically subjected t
Externí odkaz:
http://arxiv.org/abs/2212.02684
Autor:
Prenner, Julian Aron, Robbes, Romain
OpenAI's Codex, a GPT-3 like model trained on a large code corpus, has made headlines in and outside of academia. Given a short user-provided description, it is capable of synthesizing code snippets that are syntactically and semantically valid in mo
Externí odkaz:
http://arxiv.org/abs/2111.03922
Autor:
Prenner, Julian Aron, Robbes, Romain
This paper provides a starting point for Software Engineering (SE) researchers and practitioners faced with the problem of training machine learning models on small datasets. Due to the high costs associated with labeling data, in Software Engineerin
Externí odkaz:
http://arxiv.org/abs/2106.15209
Autor:
Babii, Hlib, Prenner, Julian Aron, Stricker, Laurin, Karmakar, Anjan, Janes, Andrea, Robbes, Romain
Many software engineering studies or tasks rely on categorizing software engineering artifacts. In practice, this is done either by defining simple but often imprecise heuristics, or by manual labelling of the artifacts. Unfortunately, errors in thes
Externí odkaz:
http://arxiv.org/abs/2103.01722
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.