Search our Publications
Latest Publications
Ebubechukwu Ike, Johane Takeuchi, Antonello Ceravola, Frank Joublin , "Automating Dialogue Evaluation: Large Language Mode versus Human Judgement", HCI International 2025, 2025.
AbstractAs dialogue systems and chatbots become more common in daily life, efficient and accurate evaluation methods are crucial. This study compares human and AI assessments across various dialogue scenarios, focusing on seven key performance indicators (KPIs): Coherence, Innovation, Concreteness, Goal Contribution, Commonsense Contradiction, Incorrect Fact, and Redundancy. Using the GPT-4o API, we generated diverse conversation datasets and conducted a...
Download Bibtex file
Tobias Rodemann and Christiane Attig , "Real Application Challenges in Evolutionary Optimization? People!", EvoApplications2025, pp. 469-481, 2025.
AbstractThe application of evolutionary optimization methods for real world problems is often far less straight-forward than expected. One of the main challenges are the involved people in real businesses that decide on whether optimization projects are successful or not. In this work we present a few insights from 20+ years of applying EAs (mostly multi- and many-objective) with in-house customers and point to some key psychological insights that can ex...
Download Bibtex file
Ahmed Sadik, Muhammad Ashfaq, Niko Mäkitalo, Tommi Mikkonen , "Human-LLM Synergy in Context-Aware Adaptive Architecture for Scalable Drone Swarm Operation", arXiv, 2025.
AbstractThe deployment of autonomous drone swarms in disaster response missions necessitates the development of flexible, scalable, and robust coordination systems. Traditional fixed architectures struggle to cope with dynamic and unpredictable environments, leading to inefficiencies in energy consumption and connectivity. This paper addresses this gap by proposing an adaptive architecture for drone swarms, leveraging a Large Language Model (LLM) to dyna...
Download Bibtex file Per Mail Request
Ahmed Sadik and Mariusz Bujny , "Human-in-the-Loop: Quantitative Evaluation of 3D Models Generation by Large Language Models", arXiv, 2025.
AbstractRecent advancements in Large Language Models (LLMs) have demonstrated their potential in generating 3D shapes, yet the evaluation of these outputs remains a critical challenge. In this study, we propose a quantitative evaluation framework that integrates human-in-the-loop feedback to iteratively refine 3D shape generation. Our approach employs a set of complexity and similarity metrics to assess the generated models against ground truth (GT) coun...
Download Bibtex file Per Mail Request
Felix Ocker , "LLM-based agents in robotics", Ringvorlesung an der TUM "Digitaler Zwilling im Engineering und Design", 2025.
AbstractLLM-based agents in robotics...
Download Bibtex file Per Mail Request
Kyle Poland , "A Measure-Theoretic Perspective on Multivariate Information with Applications to Data Science", Georg-August-Universität Göttingen, 2024.
AbstractDescribing statistical dependencies is foundational to empirical scientific research. For uncovering intricate and possibly nonlinear dependencies between a single target variable and several source variables within a system, a principled and versatile framework can be found in the theory of partial information decomposition (PID). Despite PID conceptually being defined for any type of random variables, so far, PID could only be quantified for ...
Download Bibtex file Per Mail Request
Kaosisochukwu Egbuonu , "Bayesian Network-based Intention Estimation of Traffic Participants ", Technical University of Darmstadt, 2024.
AbstractAutonomous vehicles are seen as a great source of hope when it comes to improving general road traffic safety. In order to achieve this and prevent potential accidents, they are required to predict the motion of surrounding traffic participants. Generally speaking, the movement of traffic participants is driven by hidden intentions such as taking a left turn or going straight at an intersection. Therefore, this work aims to develop an approach to...
Download Bibtex file Per Mail Request
Ahmed Sadik, Sebastian Brulin, Markus Olhofer, Antonello Ceravola, Frank Joublin , "LLM as a code generator in Agile Model Driven Development", Springer , 2024.
AbstractLeveraging Large Language Models (LLM) like GPT-4 in the auto-generation of code represents a signifi cant advancement, yet it is not without its challenges. The ambiguity inherent in natural language descriptions of software poses substantial obstacles to generating deployable, structured artifacts. This research champions Model-Driven Development (MDD) as a viable strategy to overcome these challenges, proposing an Agile Model-Driven Developmen...
Download Bibtex file Per Mail Request
Frank Joublin, Antonello Ceravola, Pavel Smirnov, Felix Ocker, Jörg Deigmöller, Anna Belardinelli, Chao Wang, Daniel Tanneberg, Stephan Hasler, Michael Gienger , "CoPAL: Corrective Planning of Robot Actions with Large Language Models", International Conference on Robotics and Automation (ICRA), 2024.
AbstractRecent advances in the field of pretrained Large Language Models (LLM) made commonsense knowledge available "out of the box" for a vast range of scenarios including content generation, customer service, and voice assistants. The release of GPT-3.5 (known as ChatGPT) opened prospectives for building highly contextualizable conversational agents, capable to hold a dialog and reflect about various situations as well as on behalf of different ...
Download Bibtex file
Sebastian Schmitt , "Quantum multi-objective optimization ", QC Workshop 2024: GI Quantum Computing Workshop 2024, 2024.
AbstractSolving combinatorial optimization problems using variational quantum algorithms to be executed on near-term quantum devices has gained a lot of attraction in recent years. Currently, most works have focused on single-objective problems. In contrast, many real-world problems need to consider multiple conflicting objectives simultaneously, which is not well studied using variation quantum algorithms. In multi-objective optimization, one seeks the ...
Download Bibtex file Per Mail Request
1 ... 18 19 20 21 22 23 ... 183
Follow us
