Andreas Stöckl
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Andreas Stöckl has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Oliver Krauss
University of Applied Sciences Upper Austria
6 shared publications - Simone Sandler
University of Applied Sciences Upper Austria
3 shared publications - David C. Schedl
University of Applied Sciences Upper Austria, Hagenberg, Austria
2 shared publications Ulrich Bodenhofer
School of Informatics, Communications and Media, University of Applied Sciences Upper Austria
2 shared publications- Andreas Pointner
University of Applied Sciences Upper Austria
1 shared publication - Andreas Riegler
Digital Media Lab, University of Applied Sciences Upper Austria, Hagenberg, Austria
1 shared publication
Latest Publications
- Open Access
- 16 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Hearing Heat and Cold: Auditory Cues Shape Subjective Thermal Perception in Virtual Reality
- 16 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessHearing Heat and Cold: Auditory Cues Shape Subjective Thermal Perception in Virtual Reality
- Open Access
- 7 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-5
When AI Lies with Charts: Misleading Infographics in Text-to-Image Generation
- 7 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Open AccessWhen AI Lies with Charts: Misleading Infographics in Text-to-Image Generation
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Waiting for GPT: Probing Interaction Patterns in High-Latency RAG Chatbots
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Open AccessWaiting for GPT: Probing Interaction Patterns in High-Latency RAG Chatbots
- Open Access
Detection and Measurement of Hailstones with Multimodal Large Language Models
This study examines the use of social media and news images to detect and measure hailstones, utilizing pre-trained multimodal large language models. The dataset for this study comprises 474 crowdsourced images of hailstones from documented hail events in Austria, which occurred between January 2022 and September 2024. These hailstones have maximum diameters ranging from 2 to 11cm. We estimate the hail diameters and compare four different models utilizing one-stage and two-stage prompting strategies. The latter utilizes additional size cues from reference objects, such as human hands, within the image. Our results show that pretrained models already have the potential to measure hailstone diameters from images with an average mean absolute error of 1.12cm for the best model. In comparison to a single-stage prompt, two-stage prompting improves the reliability of most models. Our study suggests that these off-the-shelf models, even without fine-tuning, can complement traditional hail sensors by extracting meaningful and spatially dense information from social media imagery, enabling faster and more detailed assessments of severe weather events. The automated real-time image harvesting from social media and other sources remains an open task, but it will make our approach directly applicable to future hail events.
Open AccessDetection and Measurement of Hailstones with Multimodal Large Language Models
This study examines the use of social media and news images to detect and measure hailstones, utilizing pre-trained multimodal large language models. The dataset for this study comprises 474 crowdsourced images of hailstones from documented hail events in Austria, which occurred between January 2022 and September 2024. These hailstones have maximum diameters ranging from 2 to 11cm. We estimate the hail diameters and compare four different models utilizing one-stage and two-stage prompting strategies. The latter utilizes additional size cues from reference objects, such as human hands, within the image. Our results show that pretrained models already have the potential to measure hailstone diameters from images with an average mean absolute error of 1.12cm for the best model. In comparison to a single-stage prompt, two-stage prompting improves the reliability of most models. Our study suggests that these off-the-shelf models, even without fine-tuning, can complement traditional hail sensors by extracting meaningful and spatially dense information from social media imagery, enabling faster and more detailed assessments of severe weather events. The automated real-time image harvesting from social media and other sources remains an open task, but it will make our approach directly applicable to future hail events.
- 22 August 2025
- Published by Springer Nature
- p. 100-114
Extraction of Entities from Stock Analyst Reports via Language Models
- 22 August 2025
- Published by Springer Nature
- p. 100-114
Extraction of Entities from Stock Analyst Reports via Language Models
- 24 April 2025
- Published by Springer Nature
- p. 43-53
Modeling Wildlife Accident Risk with Gaussian Mixture Models
- 24 April 2025
- Published by Springer Nature
- p. 43-53
Modeling Wildlife Accident Risk with Gaussian Mixture Models
- 24 April 2025
- Published by Springer Nature
- p. 326-332
Using LLMs and Websearch in Order to Perform Fact Checking on Texts Generated by LLMs
- 24 April 2025
- Published by Springer Nature
- p. 326-332
Using LLMs and Websearch in Order to Perform Fact Checking on Texts Generated by LLMs
- 24 April 2025
- Published by Springer Nature
- p. 311-325
The Human-Centered AI-DATA Model for Onsite Customer Journeys in E-Commerce
- 24 April 2025
- Published by Springer Nature
- p. 311-325
The Human-Centered AI-DATA Model for Onsite Customer Journeys in E-Commerce
- 30 January 2024
- Published by Springer Nature
- p. 807-821
Application of Language Models for the Segmentation of Website Visitors
- 30 January 2024
- Published by Springer Nature
- p. 807-821
Application of Language Models for the Segmentation of Website Visitors