Related papers: PIE: A Domain-Specific Language for Interactive So…
Foundation models, such as GPT-4, DALL-E have brought unprecedented AI "operating system" effect and new forms of human-AI interaction, sparking a wave of innovation in AI-native services, where natural language prompts serve as executable…
Question Answering (QA) is a growing area of research, often used to facilitate the extraction of information from within documents. State-of-the-art QA models are usually pre-trained on domain-general corpora like Wikipedia and thus tend…
Multi-stage ML inference pipelines are difficult to autoscale due to heterogeneous resources, cross-stage coupling, and dynamic bottleneck migration. We present SAIR, an autoscaling framework that uses an LLM as an in-context reinforcement…
We present DAPIP, a Programming-By-Example system that learns to program with APIs to perform data transformation tasks. We design a domain-specific language (DSL) that allows for arbitrary concatenations of API outputs and constant…
Understanding complex parameter dependencies is critical for effective configuration and maintenance of software systems across diverse domains - from Computer-Aided Engineering (CAE) to cloud infrastructure and database management.…
Developers of Molecular Dynamics (MD) codes face significant challenges when adapting existing simulation packages to new hardware. In a continuously diversifying hardware landscape it becomes increasingly difficult for scientists to be…
The demand for rapid software delivery in the Information Technology (IT) industry has significantly intensified, emphasising the need for faster software products and service releases with enhanced features to meet customer expectations.…
We present a Parallel Iterative Edit (PIE) model for the problem of local sequence transduction arising in tasks like Grammatical error correction (GEC). Recent approaches are based on the popular encoder-decoder (ED) model for sequence to…
ost recent popular Role-Playing Games (RPGs) allow players to create in-game characters with hundreds of adjustable parameters, including bone positions and various makeup options. Although text-driven auto-customization systems have been…
The computer programs most users interact with daily are driven by a graphical user interface (GUI). However, many scientific applications are used with a command line interface (CLI) for the ease of development and increased flexibility…
Several approaches have been presented, which aim to extract models from natural language specifications. These approaches have inherent weaknesses for they assume an initial problem understanding that is perfect, and they leave no room for…
Data scientists develop ML pipelines in an iterative manner: they repeatedly screen a pipeline for potential issues, debug it, and then revise and improve its code according to their findings. However, this manual process is tedious and…
The process of engineering and deploying applications in the edge/embedded space is massively complicated by the non-homogeneous nature of the software stack and the complexity of diagnostics & debugging. Often different languages and…
This article introduces a model-driven engineering (MDE) integrated development environment (IDE) for Data-Intensive Cloud Applications (DIA) with iterative quality enhancements. As part of the H2020 DICE project (ICT-9-2014, id 644869), a…
Traditional Digital Signal Processing ( DSP ) compilers work at low level ( C-level / assembly level ) and hence lose much of the optimization opportunities present at high-level ( domain-level ). The emerging multi-level compiler…
This paper introduces CAAI, a novel cognitive architecture for artificial intelligence in cyber-physical production systems. The goal of the architecture is to reduce the implementation effort for the usage of artificial intelligence…
Advancements in large language models (LLMs) have led to a surge of prompt engineering (PE) techniques that can enhance various requirements engineering (RE) tasks. However, current LLMs are often characterized by significant uncertainty…
Layered software architecture contains several intra-layer and inter-layer dependencies. Each layer depends on shared components making it difficult to release a code change, bug fix or feature without exhaustive testing and having to build…
Recent advances in large language models (LLMs) have demonstrated the effectiveness of Iterative Self-Improvement (ISI) techniques. However, continuous training on self-generated data leads to reduced output diversity, a limitation…
Different organisations often run similar digitised business processes to achieve their business goals. However, organisations often need to slightly adapt the business processes implemented in an information system in order to adopt them.…