Thilo Spinner

en | de
M.Sc.
Computer and
Information Science

About me

I am a Research Engineer in Prof. Dr. Mennatallah El-Assady's research group for Interactive Visualization & Intelligence Augmentation (IVIA) at ETH Zurich. Here, I am responsible for building a microservice-based infrastructure for research, education, and industry projects. This includes DevOps, developing full-stack applications for the visualization and interactive analysis of AI algorithms, as well as project planning and execution. My research focus and the topic of my doctoral thesis are in the area of visualization for the explainability of AI algorithms and the debugging of neural networks. During my studies, I specialized in computer graphics and image processing, and privately, I like to implement small projects in the maker area. I am interested in the natural sciences in general and love to immerse myself in new subject areas. I particularly value working in a team to solve complex problems together and master challenging projects.

Curriculum vitae

since
2024
Jan
Research Engineer ETH Zurich
2018
Feb
–
2023
Dez
Academic Employee University of Konstanz
2016
Oct
–
2018
Jan
Master of Science University of Konstanz
2014
Sep
–
2017
Dec
Student Employee Siemens Postal, Parcel & Airport Logistics
2014
Mar
–
2014
Aug
Internship Semester Siemens
2011
Oct
–
2016
Sep
Bachelor of Science University of Konstanz
2003
Sep
–
2011
May
Abitur Okengymnasium Offenburg

Publications

[1] Thilo Spinner, Jonas Körner, Jochen Görtler, and Oliver Deussen. "Towards an Interpretable Latent Space – An Intuitive Comparison of Autoencoders with Variational Autoencoders". IEEE VIS Workshop on Visualization for AI explainability (VISxAI), 2018.
[2] Mennatallah El-Assady, Wolfgang Jentner, Rebecca Kehlbeck, Udo Schlegel, Rita Sevastjanova, Fabian Sperrle, Thilo Spinner, and Daniel Keim. "Towards XAI: Structuring the Processes of Explanations". ACM CHI Workshop on Human–Centered Machine Learning Perspectives, 2019.
[3] Jochen Görtler, Thilo Spinner, Dirk Streeb, Daniel Weiskopf, and Oliver Deussen. "Uncertainty-Aware Principal Component Analysis". IEEE Transactions on Visualization and Computer Graphics, vol. 26, no. 1, 2020.
[4] Thilo Spinner, Udo Schlegel, Hanna Schäfer, and Mennatallah El-Assady. "explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learning". IEEE Transactions on Visualization and Computer Graphics, vol. 26, no. 1, 2020.
[5] Rebecca Kehlbeck, Rita Sevastjanova, Thilo Spinner, Tobias Stähle, and Mennatallah El-Assady. "Demystifying the Embedding Space of Language Models". IEEE VIS Workshop on Visualization for AI explainability (VISxAI), 2021.
[6] Thilo Spinner, Udo Schlegel, Martin Schall, Fabian Sperrle, Rita Sevastjanova, Beatrice Gobbo, Julius Rauscher, Mennatallah El-Assady, and Daniel A Keim. "Speculative Execution of Similarity Queries: Real-Time Parameter Optimization through Visual Exploration". EDBT Workshop on Data Analytics and Machine Learning Made Simple (SIMPLIFY), 2021.
[7] Mennatallah El-Assady, Rebecca Kehlbeck, Yannick Metz, Udo Schlegel, Rita Sevastjanova, Fabian Sperrle, and Thilo Spinner. "Semantic Color Mapping: A Pipeline for Assigning Meaningful Colors to Text". IEEE VIS Workshop on Visualization Guidelines in Research, Design, and Education (VisGuides), 2022.
[8] Wolfgang Jentner, Fabian Sperrle, Daniel Seebacher, Matthias Kraus, Rita Sevastjanova, Maximilian T. Fischer, Udo Schlegel, Dirk Streeb, Matthias Miller, Thilo Spinner, Eren Cakmak, Matthew Sharinghousen, Philipp Meschenmoser, Jochen Görtler, Oliver Deussen, Florian Stoffel, Hans-Joachim Kabitz, Daniel A. Keim, Mennatallah El-Assady, and Juri F. Buchmüller. "Visualisierung der COVID-19-Inzidenzen und Behandlungskapazitäten mit CoronaVis". Resilienz und Pandemie: Handlungsempfehlungen anhand von Erfahrungen mit COVID-19, 2022.
[9] Thilo Spinner, Rebecca Kehlbeck, Rita Sevastjanova, Tobias Stähle, Daniel A. Keim, Oliver Deussen, Andreas Spitz, and Mennatallah El-Assady. "Revealing the Unwritten: Visual Investigation of Beam Search Trees to Address Language Model Prompting Challenges". arXiv, 2023.
[10] Thilo Spinner, Rebecca Kehlbeck, Rita Sevastjanova, Tobias Stähle, Daniel A. Keim, Oliver Deussen, and Mennatallah El-Assady. "generAItor: Tree-in-the-Loop Text Generation for Language Model Explainability and Adaptation". ACM Transactions on Interactive Intelligent Systems, 2024.