collaborators

6 papers

cs.AI2025

Promoting Sustainable Web Agents: Benchmarking and Estimating Energy Consumption through Empirical and Theoretical Analysis

Lars Krupp, Daniel Geißler, Vishal Banwari +2

Web agents, like OpenAI's Operator and Google's Project Mariner, are powerful agentic systems pushing the boundaries of Large Language Models (LLM). They can autonomously interact…

cs.LG2025

Human in the Latent Loop (HILL): Interactively Guiding Model Training Through Human Intuition

Daniel Geissler, Lars Krupp, Vishal Banwari +4

Latent space representations are critical for understanding and improving the behavior of machine learning models, yet they often remain obscure and intricate. Understanding and ex…

cs.AI2025

TxP: Reciprocal Generation of Ground Pressure Dynamics and Activity Descriptions for Improving Human Activity Recognition

Lala Shakti Swarup Ray, Lars Krupp, Vitor Fortes Rey +3

Sensor-based human activity recognition (HAR) has predominantly focused on Inertial Measurement Units and vision data, often overlooking the capabilities unique to pressure sensors…

physics.ed-ph2025

Visualization enhances Problem Solving in multi-Qubit Systems

Jonas Bley, Eva Rexigel, Alda Arias +7

Quantum Information Science (QIS) is a vast, diverse, and abstract field. In consequence, learners face many challenges. Science, Technology, Engineering, and Mathematics (STEM) ed…

cs.AI2025

Talk2X -- An Open-Source Toolkit Facilitating Deployment of LLM-Powered Chatbots on the Web

Lars Krupp, Daniel Geißler, Peter Hevesi +3

Integrated into websites, LLM-powered chatbots offer alternative means of navigation and information retrieval, leading to a shift in how users access information on the web. Yet,…

cs.AI2025

Towards Sustainable Web Agents: A Plea for Transparency and Dedicated Metrics for Energy Consumption

Lars Krupp, Daniel Geißler, Paul Lukowicz +1

Improvements in the area of large language models have shifted towards the construction of models capable of using external tools and interpreting their outputs. These so-called we…