Related papers: Generating Software for Well-Understood Domains
Within the agile paradigm, many software product companies create cross-functional product development teams that own their product or a defined set of product features. In contrast to development teams operating within a…
Nowadays, many individuals and teams involved on projects are already using agile development techniques as part of their daily work. However, we have much less experience in how to scale and manage agile practices in distributed software…
Large language models (LLMs) have shown impressive promise in code generation, yet their progress remains limited by the shortage of large-scale datasets that are both diverse and well-aligned with human reasoning. Most existing resources…
Software is the key crosscutting technology that enables advances in mathematics, computer science, and domain-specific science and engineering to achieve robust simulations and analysis for science, engineering, and other research fields.…
Domain generalization (DG) aims to generalize a model trained on multiple source (i.e., training) domains to a distributionally different target (i.e., test) domain. In contrast to the conventional DG that strictly requires the availability…
The size and complexity of software applications is increasing at an accelerating pace. Source code repositories (along with their dependencies) require vast amounts of labor to keep them tested, maintained, and up to date. As the…
We systematically study how three large language models with code capabilities - CodeT5, Codex, and ChatGPT - generalize to out-of-domain data. We consider two fundamental applications - code summarization, and code generation. We split…
We survey Natural Language Processing (NLP) approaches to summarizing, simplifying, and generating patents' text. While solving these tasks has important practical applications - given patents' centrality in the R&D process - patents'…
Data-driven systems depend on task-relevant data, yet data collection pipelines remain passive and indiscriminate. Continuous logging of multimodal sensor streams incurs high storage costs and captures irrelevant data. This paper proposes a…
Contributions of different experts to innovation projects improve enterprise value, captured in documents. A subset of them is the centre of expert constraint convergence. Their production needs to be tailored case by case. Documents are…
We propose and explore a new paradigm called Code Drones in which every software artifact such as a class is an intelligent and socially active entity. In this paradigm, humanized artifacts take the lead and choreograph (socially, in…
Software documentation is essential for program comprehension, developer onboarding, code review, and long-term maintenance. Yet producing quality documentation manually is time-consuming and frequently yields incomplete or inconsistent…
Domain specific languages (DSLs) are increasingly used today. Coping with complex language definitions, evolving them in a structured way, and ensuring their error freeness are the main challenges of DSL design and implementation. The use…
Domain Generalization techniques aim to enhance model robustness by simulating novel data distributions during training, typically through various augmentation or stylization strategies. However, these methods frequently suffer from limited…
The automatic generation of computer programs is one of the main applications with practical relevance in the field of evolutionary computation. With program synthesis techniques not only software developers could be supported in their…
Agile software development methods have been suggested as useful in many situations and contexts. However, only few (if any) experiences are available regarding the use of agile methods in embedded domain where the hardware sets tight…
Large language models show strong potential for automated code generation, but lack guarantees for correctness, quality, safety, and domain-specific constraints. For instance in robotics, where code generation is increasingly being used for…
Prompt learning has become an efficient paradigm for adapting CLIP to downstream tasks. Compared with traditional fine-tuning, prompt learning optimizes a few parameters yet yields highly competitive results, especially appealing in…
Designing domain models and software architectures represents a significant challenge in software development, as the resulting architectures play a vital role in fulfilling the system's quality of service. Due to time pressure, architects…
Generating high-quality stories spanning thousands of tokens requires competency across a variety of skills, from tracking plot and character arcs to keeping a consistent and engaging style. Due to the difficulty of sourcing labeled…