Hendrik Strobelt
Senior Research Scientist at IBM Research and MIT-IBM lab explainability lead; co-creator of GLTR
- Senior Research Scientist; Explainability Lead, MIT-IBM Watson AI Lab, IBM Research1
Hendrik Strobelt is a Senior Research Scientist at IBM Research and the Explainability Lead at the MIT-IBM Watson AI Lab, working on visualization for and human collaboration with AI models. Strobelt joined IBM in 2017 after postdoctoral positions at Harvard SEAS and NYU Tandon. With Sebastian Gehrmann and Alexander M. Rush, Strobelt created GLTR (Giant Language Model Test Room), an Apache-2.0 open-source tool that helps people judge whether a text was generated by a language model, built as a collaboration of the MIT-IBM Watson AI Lab and HarvardNLP. Strobelt also co-authored LSTMVis, a tool for visual analysis of hidden-state dynamics in recurrent neural networks.1234
Work
GLTR (Giant Language Model Test Room) (external site: github.com)Open-source code
Co-author of "GLTR: Statistical Detection and Visualization of Generated Text" (2019); the Apache-2.0 repository describes GLTR as a project by Hendrik Strobelt, Sebastian Gehrmann, and Alexander M. Rush, built as a collaboration of the MIT-IBM Watson AI Lab and HarvardNLP.23
LSTMVis (external site: arxiv.org)Published research
First author of "LSTMVis: A Tool for Visual Analysis of Hidden State Dynamics in Recurrent Neural Networks" (2016), with Sebastian Gehrmann, Hanspeter Pfister, and Alexander M. Rush.4
Other documented roles
Roles the sources document but that are not confirmed as current.
- Postdoctoral position at Harvard SEAS (before joining IBM in 2017), Harvard University (SEAS)1
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.