doi.bio/hendrik_strobelt

Hendrik Strobelt

Early Life and Education

Hendrik Strobelt was born in former East Germany. He completed his Abitur (A levels) at Käthe Kollwitz Gymnasium Zwickau. He then went on to study Computer Science, obtaining a Dipl.-Inf. (MA) from TU Dresden in 2007, and a Dr. rer. nat. (PhD) from Uni Konstanz in 2012.

Career

Strobelt has held various academic and research positions throughout his career. From 2013 to 2014, he was a PostDoc in Computer Science at NYU Tandon, New York. This was followed by a PostDoc position at Harvard University's School of Engineering and Applied Sciences (SEAS) from 2014 to 2016.

Since 2017, Strobelt has been a Senior Research Scientist at IBM Research in Cambridge, MA, where he also serves as the Explainability Lead for the MIT-IBM Watson AI Lab. Additionally, he has held visiting researcher and adjunct faculty positions at MIT and CMU, respectively. In 2022, he became a Professor of Computer Science at Uni Konstanz, Germany.

Strobelt has a strong interest in the visualization of large data sets, particularly unstructured or semi-structured data, biological data, and neural network models. He has published extensively in this field, with notable works including:

• Visual Analysis of Hidden State Dynamics in Recurrent Neural Networks
• Ontologies in Biological Data Visualization
• RELIC: Investigating Large Language Model Responses using Self-Consistency
• Empirical Evidence on Conversational Control of GUI in Semantic Automation
• Memory in Plain Sight: A Survey of the Uncanny Resemblances between Diffusion Models and Associative Memories
• GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
• CogMol: Target-Specific and Selective Drug Design for COVID-19 Using Deep Generative Models

Service to the Community

Strobelt is actively involved in the research community, regularly reviewing for conferences and participating in program committees. He has also served as a general or hybrid chair for various conferences, including IEEE VIS 2022 and NeurIPS (2020-23).