Related papers: Upgrading EasyTime: from a textual to a visual lan…
This work-in-progress paper presents our work with a domain specific language (DSL) for tackling the issue of programming robots for small-sized batch production. We observe that as the complexity of assembly increases so does the…
EasyMath is a compact benchmark for practical math reasoning in small language models. It covers thirteen categories, from basic arithmetic and order of operations to word problems, algebraic expressions, edge cases, and omits specialist…
Domain-specific modelling languages (DSMLs) help practitioners solve modelling challenges specific to various domains. As domains grow more complex and heterogeneous in nature, industrial practitioners often face challenges in the usability…
The escalating data scale in High-Energy Physics (HEP) fuels a growing aspiration for higher analytical efficiency. While Large Language Models (LLMs) offer a path toward automation via agentic AI, they struggle with complex scientific…
Model-driven engineering (MDE) simplifies software development through abstraction, yet challenges such as time constraints, incomplete domain understanding, and adherence to syntactic constraints hinder the design process. This paper…
Labeling training datasets has become a key barrier to building medical machine learning models. One strategy is to generate training labels programmatically, for example by applying natural language processing pipelines to text reports…
This works aims to design a statistical machine translation from English text to American Sign Language (ASL). The system is based on Moses tool with some modifications and the results are synthesized through a 3D avatar for interpretation.…
Many scientific-software projects test their codes inadequately, or not at all. Despite its well-known benefits, adopting routine testing is often not easy. Development teams may have doubts about establishing effective test procedures,…
Large language models (LLMs) have ushered in a new era for processing complex information in various fields, including science. The increasing amount of scientific literature allows these models to acquire and understand scientific…
There is currently a large amount of robotics software using the component-oriented programming paradigm. However, the rapid growth in number and complexity of components may compromise the scalability and the whole lifecycle of robotics…
Softmax Loss (SL) is being increasingly adopted for recommender systems (RS) as it has demonstrated better performance, robustness and fairness. Yet in implicit-feedback, a single global temperature and equal treatment of uniformly sampled…
Large pre-trained vision-language models, such as CLIP, have shown remarkable generalization capabilities across various tasks when appropriate text prompts are provided. However, adapting these models to specific domains, like remote…
Machine learning (ML) applications become increasingly common in many domains. ML systems to execute these workloads include numerical computing frameworks and libraries, ML algorithm libraries, and specialized systems for deep neural…
This paper introduces a new fundamental characteristic, \ie, the dynamic range, from real-world metric tools to deep visual recognition. In metrology, the dynamic range is a basic quality of a metric tool, indicating its flexibility to…
As the integration of web services into web applications becomes more and more common, it is necessary to find a solution for low-code or no-code environments. This thesis is the first attempt to allow for the easy integration of web…
Encoding time-series with Linear Dynamical Systems (LDSs) leads to rich models with applications ranging from dynamical texture recognition to video segmentation to name a few. In this paper, we propose to represent LDSs with…
Service robots act in open-ended, natural environments. Therefore, due to combinatorial explosion of potential situations, it is not possible to foresee all eventualities in advance during robot design. In addition, due to limited resources…
Large language models (LLMs) enable strong text generation, and in general there is a practical tradeoff between fine-tuning and prompt engineering. We introduce Simplify-This, a comparative study evaluating both paradigms for text…
How to best use Large Language Models (LLMs) for software engineering is covered in many publications in recent years. However, most of this work focuses on widely-used general purpose programming languages. The utility of LLMs for software…
Formal languages are an integral part of modeling and simulation. They allow the distillation of knowledge into concise simulation models amenable to automatic execution, interpretation, and analysis. However, the arguably most humanly…