Tom Sühr

I am on the job market for postdoc, faculty and industry positions starting in 2027.

I am a doctoral candidate at the Max Planck Institute for Intelligent Systems, advised by Samira Samadi, Chiara Farronato (Harvard Business School) and Moritz Hardt. I completed my MSc in Information Systems Management at TU Berlin while being a research assistant at Harvard Business School. During my undergraduate studies I was a research intern at the Max Planck Institute for Software Systems advised by Krishna Gummadi and Asia Biega, as well as a student researcher at the chair of complex distributed systems (CIT) advised by Meike Zehlike and Carlos Castillo. I am broadly interested in machine learning, AI evaluation and human-AI interaction.

Currently thinking about

• Benchmarking and evaluation of AI
• Measurement theory for AI
• Latent traits of large language models
• Human-AI collaboration

News

• Thank you to all users of Comparity.ai for your participation. Our two-month study was a great success.
• Our paper “AI Construct Lexis: An Ontology of the Hidden Assumptions in AI Evaluation” got accepted at NeurIPS 2026 in the Evaluations and Datasets Track.
• Our paper “Position: Stop Evaluating AI with Human Tests, Develop Principled, AI-specific Tests instead” got accepted at ICML 2026 in the position paper track.
• I TA'ed for the course “The Science of Machine Learning Benchmarks and Evaluation” (ML4331) instructed by Moritz Hardt at the University of Tübingen in WS 2025 and 2026.

Info for Undergrad / MA students

If you would like to write a thesis or student paper with me, please send an email to tom.suehr@tuebingen.mpg.de with some information about your areas of interest and the rough time you would like to work on the project (e.g. July–November).

Publications