CAIN 2024
Sun 14 - Mon 15 April 2024 Lisbon, Portugal
co-located with ICSE 2024

The recent release of large language model (LLM) based chatbots, such as ChatGPT, has attracted huge interest on foundation models. It is widely believed that foundation models will serve as the fundamental building blocks for future AI systems. As foundation models are in their early stages, the design of foundation model based systems has not yet been systematically explored. There is limited understanding about the impact of introducing foundation models in software architecture. Therefore, in this paper, we propose a taxonomy of foundation model based systems, which classifies and compares the characteristics of foundation models and design options of foundation model based systems. Our taxonomy comprises three categories: the pretraining and adaptation of foundation models, the architecture design of foundation model based systems, and responsible-AI-by-design. This taxonomy can serve as concrete guidance for making major architectural design decisions when designing foundation model based systems and highlights trade-offs arising from design decisions.

Sun 14 Apr

Displayed time zone: Lisbon change

11:00 - 12:30
Architecting, Designing, Managing, and Modeling AI-Enabled SystemsIndustry Talks / Research and Experience Papers at Pequeno Auditório
Chair(s): Nicolás Cardozo Universidad de los Andes
11:00
10m
Talk
A Taxonomy of Foundation Model based Systems through the Lens of Software Architecture
Research and Experience Papers
Qinghua Lu Data61, CSIRO, Liming Zhu CSIRO’s Data61, Xiwei (Sherry) Xu Data61, CSIRO, Yue Liu CSIRO's Data61 & University of New South Wales, Zhenchang Xing CSIRO's Data61, Jon Whittle CSIRO's Data61 and Monash University
11:10
15m
Talk
Investigating the Impact of Solid Design Principles on Machine Learning Code UnderstandingDistinguished paper AwardDistinguished paper Award Candidate
Research and Experience Papers
Raphael Cabral Pontifical Catholic University of Rio de Janeiro (PUC-Rio), Marcos Kalinowski Pontifical Catholic University of Rio de Janeiro (PUC-Rio), Maria Teresa Baldassarre Department of Computer Science, University of Bari , Hugo Villamizar Pontifical Catholic University of Rio de Janeiro (PUC-Rio), Tatiana Escovedo Pontifical Catholic University of Rio de Janeiro, Helio Côrtes Vieira Lopes PUC-Rio
Pre-print
11:25
10m
Industry talk
KnowING Intelligent Document Classification: A Deep Dive into Microservices and Efficient Models at ING
Industry Talks
A: Andrew Rutherfoord CWI; University of Groningen, A: Gert Vermeer , Andrea Capiluppi Brunel University
11:35
15m
Talk
An Exploratory Study of V-Model in Building ML-Enabled Software: A Systems Engineering PerspectiveDistinguished paper Award Candidate
Research and Experience Papers
Jie JW Wu University of British Columbia (UBC)
Pre-print
11:50
10m
Industry talk
Engineering Challenges in Industrial AI
Industry Talks
12:00
10m
Talk
Approach for Argumenting Safety on Basis of an Operational Design Domain
Research and Experience Papers
Gereon Weiss Fraunhofer IKS, Marc Zeller Siemens AG, Hannes Schoenhaar Siemens Corporate Technology, Christian Drabek Fraunhofer Institute for Cognitive Systems IKS, Andreas Kreutz Fraunhofer Institute for Cognitive Systems IKS
12:10
15m
Talk
The Impact of Knowledge Distillation on the Performance and Energy Consumption of NLP Models
Research and Experience Papers
Ye Yuan Vrije Universiteit Amsterdam, Jiacheng Shi Vrije Universiteit Amsterdam, Zongyao Zhang Vrije Universiteit Amsterdam, Kaiwei Chen Vrije Universiteit Amsterdam, Eloise Zhang Vrije Universiteit Amsterdam, Vincenzo Stoico Vrije Universiteit Amsterdam, Ivano Malavolta Vrije Universiteit Amsterdam