David Exler
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
David Exler has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Joaquin Eduardo Urrutia Gomez
Institute for Automation and Applied Informatics (IAI) Karlsruher Institute of Technology (KIT) Eggenstein‐Leopoldshafen Baden‐Württemberg Germany
3 shared publications - Mario Vitacolonna
CeMOS, Mannheim University of Applied Sciences, Mannheim, Germany
2 shared publications - Markus Reischl
Institute for Automation and Applied Informatics (IAI), Karlsruhe Institute of Technology (KIT), Eggenstein-Leopoldshafen, Germany
2 shared publications - Martin Krüger
Institute for Automation and Applied Informatics (IAI), Karlsruhe Institute of Technology (KIT), Eggenstein-Leopoldshafen, Germany
2 shared publications - Rüdiger Rudolf
Institute of Molecular and Cell Biology, Mannheim University of Applied Sciences, Mannheim, Germany
2 shared publications - Christof M. Niemeyer
Karlsruhe Institute of Technology
1 shared publication
Latest Publications
- Open Access
- 9 October 2026
- Published by Elsevier in SLAS Technology
- Vol. 43
Bayesian optimization for design parameters of 3D image data analysis
- 9 October 2026
- Published by Elsevier in SLAS Technology
- Vol. 43
Open AccessBayesian optimization for design parameters of 3D image data analysis
- Open Access
- 21 April 2026
- Published by Wiley in Advanced Intelligent Discovery
LLM‐Based Scientific Assistants for Knowledge Extraction: Which Design Choices Matter?
Large Language Model chatbots have gained significant popularity, offering knowledge to support specialists in diverse fields. However, adapting models to specific use cases and specialized domains presents considerable challenges. Hence, we introduce the LLM Playground, a comprehensive approach to optimizing LLMs for specialist applications with respect to their accuracy in answering domain‐specific questions, addressing the limitations of unmodified models. The utilized optimization techniques begin with Prompt Engineering, advance to the integration of external knowledge, and culminate in complex reasoning strategies or self‐feedback loops. This paper introduces various architectures for scientific assistants, comprising individual enhancement techniques, both in isolation and in combination with others, designed to facilitate comparisons. To demonstrate the efficacy of the LLM Playground, a chemical chatbot is set up as a case study, and the optimization techniques are compared using ChemBench, an independent question–answer benchmark for the chemical domain, to measure its performance. By providing tested, ready‐to‐deploy architectures and clear use‐case guidance, this work helps researchers and practitioners leverage LLMs in domain‐specific applications. The insights and methodologies presented in this paper contribute to the growing body of knowledge on tailoring LLMs to meet the unique demands of specialized fields.
- 21 April 2026
- Published by Wiley in Advanced Intelligent Discovery
Open AccessLLM‐Based Scientific Assistants for Knowledge Extraction: Which Design Choices Matter?
Large Language Model chatbots have gained significant popularity, offering knowledge to support specialists in diverse fields. However, adapting models to specific use cases and specialized domains presents considerable challenges. Hence, we introduce the LLM Playground, a comprehensive approach to optimizing LLMs for specialist applications with respect to their accuracy in answering domain‐specific questions, addressing the limitations of unmodified models. The utilized optimization techniques begin with Prompt Engineering, advance to the integration of external knowledge, and culminate in complex reasoning strategies or self‐feedback loops. This paper introduces various architectures for scientific assistants, comprising individual enhancement techniques, both in isolation and in combination with others, designed to facilitate comparisons. To demonstrate the efficacy of the LLM Playground, a chemical chatbot is set up as a case study, and the optimization techniques are compared using ChemBench, an independent question–answer benchmark for the chemical domain, to measure its performance. By providing tested, ready‐to‐deploy architectures and clear use‐case guidance, this work helps researchers and practitioners leverage LLMs in domain‐specific applications. The insights and methodologies presented in this paper contribute to the growing body of knowledge on tailoring LLMs to meet the unique demands of specialized fields.
- Open Access
Bayesian Optimization for Design Parameters of 3D Image Data Analysis
Deep learning-based segmentation and classification are crucial to large-scale biomedical imaging, particularly for 3D data, where manual analysis is impractical. Although many methods exist, selecting suitable models and tuning parameters remains a major bottleneck in practice. Hence, we introduce the 3D data Analysis Optimization Pipeline, a method designed to facilitate the design and parameterization of segmentation and classification using two Bayesian Optimization stages. First, the pipeline selects a segmentation model and optimizes postprocessing parameters using a domain-adapted syntactic benchmark dataset. To ensure a concise evaluation of segmentation performance, we introduce a segmentation quality metric that serves as the objective function. Second, the pipeline optimizes design choices of a classifier, such as encoder and classifier head architectures, incorporation of prior knowledge, and pretraining strategies. To reduce manual annotation effort, this stage includes an assisted class-annotation workflow that extracts predicted instances from the segmentation results and sequentially presents them to the operator, eliminating the need for manual tracking. In four case studies, the 3D data Analysis Optimization Pipeline efficiently identifies effective model and parameter configurations for individual datasets.
Open AccessBayesian Optimization for Design Parameters of 3D Image Data Analysis
Deep learning-based segmentation and classification are crucial to large-scale biomedical imaging, particularly for 3D data, where manual analysis is impractical. Although many methods exist, selecting suitable models and tuning parameters remains a major bottleneck in practice. Hence, we introduce the 3D data Analysis Optimization Pipeline, a method designed to facilitate the design and parameterization of segmentation and classification using two Bayesian Optimization stages. First, the pipeline selects a segmentation model and optimizes postprocessing parameters using a domain-adapted syntactic benchmark dataset. To ensure a concise evaluation of segmentation performance, we introduce a segmentation quality metric that serves as the objective function. Second, the pipeline optimizes design choices of a classifier, such as encoder and classifier head architectures, incorporation of prior knowledge, and pretraining strategies. To reduce manual annotation effort, this stage includes an assisted class-annotation workflow that extracts predicted instances from the segmentation results and sequentially presents them to the operator, eliminating the need for manual tracking. In four case studies, the 3D data Analysis Optimization Pipeline efficiently identifies effective model and parameter configurations for individual datasets.