Related papers: KARMA Approach supporting Development Process Reco…

Flexible neural sequence models outperform grammar- and automaton-based counterparts on a variety of tasks. However, neural models perform poorly in settings requiring compositional generalization beyond the training data -- particularly to…

This paper demonstrates that language models are strong structure-based protein designers. We present LM-Design, a generic approach to reprogramming sequence-based protein language models (pLMs), that have learned massive sequential…

This paper presents prompt design techniques for software engineering, in the form of patterns, to solve common problems when using large language models (LLMs), such as ChatGPT to automate common software engineering activities, such as…

The thesis discusses topics related to the development of business process management systems. Business process management systems have evolved on the basis of workflow management systems through incremental inclusion of standard…

Autoregressive generative models are commonly used, especially for those tasks involving sequential data. They have, however, been plagued by a slew of inherent flaws due to the intrinsic characteristics of chain-style conditional modeling…

Large Language Models (LLMs) have demonstrated impressive capabilities in a wide range of code generation tasks. However, generating code for certain domains remains challenging. One such domain is Computer-Aided Design (CAD) program, where…

Fine-tuning pre-trained vision models for specific tasks is a common practice in computer vision. However, this process becomes more expensive as models grow larger. Recently, parameter-efficient fine-tuning (PEFT) methods have emerged as a…

Like software, requirements evolve and change frequently during the development process. Refactoring is the process of reorganising software without changing its behaviour, to make it easier to understand and modify. We propose refactoring…

The class framework developed for vertex reconstruction in CMS is described. We emphasize how we proceed to develop a flexible, efficient and reliable piece of reconstruction software. We describe the decomposition of the algorithms into…

While overparameterization in machine learning models offers great benefits in terms of optimization and generalization, it also leads to increased computational requirements as model sizes grow. In this work, we show that by leveraging the…

Safety critical software assessment requires robust assessment against complex regulatory frameworks, a process traditionally limited by manual evaluation. This paper presents Document Retrieval-Augmented Fine-Tuning (DRAFT), a novel…

As retrieval-augmented generation prevails in large language models, embedding models are becoming increasingly crucial. Despite the growing number of general embedding models, prior work often overlooks the critical role of training data…

The most important way to achieve higher performance in computer systems is through heterogeneous computing, i.e., by adopting hardware platforms containing more than one type of processor, such as CPUs, GPUs, and FPGAs. Several types of…

Many engineering processes exist in the industry, text books and international standards. However, in practice rarely any of the processes are followed consistently and literally. It is observed across industries the processes are altered…

As large language models (LLMs) continue to advance, improving them solely through human supervision is becoming increasingly costly and limited in scalability. As models approach human-level capabilities in certain domains, human feedback…

Classical and new numerical schemes are generated using evolutionary computing. Differential Evolution is used to find the coefficients of finite difference approximations of function derivatives, and of single and multi-step integration…

In systems engineering, accurately decomposing requirements is crucial for creating well-defined and manageable system components, particularly in safety-critical domains. Despite the critical need, rigorous, top-down methodologies for…

Analysing the development process for an ERP solution, in our case SAP, is one of the most critical processes in implementing standard software packages. Modelling of the proposed system can facilitate the development of enterprise systems…

Reinforcement learning-based policies for continuous control robotic navigation tasks often fail to adapt to changes in the environment during real-time deployment, which may result in catastrophic failures. To address this limitation, we…

COnstraint-Based Reconstruction and Analysis (COBRA) provides a molecular mechanistic framework for integrative analysis of experimental data and quantitative prediction of physicochemically and biochemically feasible phenotypic states. The…