Hi, I'm Matt Groh.

Bio - Publications - Recorded Talks - Podcasts - Essays - Art

I am an assistant professor at Northwestern University in the Management and Organizations department at the Kellogg School of Management and by courtesy in the Computer Science department at the McCormick School of Engineering. I am also the principal investigator of the Human-AI Collaboration Lab.

My research examines the dynamics of human-AI collaboration with a focus on synthetic media, medical diagnosis, and empathic communication. Bridging methods from social science and machine learning, I build large-scale digital experiments to study questions around when, where, why, and how the combination of human problem solving and AI systems leads to hybrid systems that surpass (or fail to surpass) the performance of either humans or the machine alone.

You can find my CV here, research on Google Scholar and latest thoughts on Twitter.



I am taking new PhD students; please apply to Northwestern in Fall 2024 and mention my name in your application if you are interested in working with me. I advise students in both the Computer Science and Management and Organizations departments.


2024 Papers

Human Detection of Political Speech Deepfakes across Transcripts, Audio, and Video
Matt Groh, Aruna Sankaranarayana, Nikhil Singh, Dong Young Kim, Andy Lippman, Rosalind Picard
Nature Communications
[pdf] [replication code + data] [stimuli]
Deep Learning-aided Decision Support for Diagnosis of Skin Disease across Skin Tones
Matt Groh, Omar Badri, Roxana Daneshjou, Arash Koochek, Caleb Harris, Luis Soenksen, P. Murali Doraiswamy, Rosalind Picard
Nature Medicine
[ pdf ] [ research briefing]
Intrinsic Self-Supervision for Data Quality Audits
Fabian Gröger, Simone Lionetti, Philippe Gottfrois, Alvaro Gonzalez-Jimenez, Ludovic Amruthalingam, Labelling Consortium, Matt Groh, Alexander Navarini, Marc Pouly
NeurIPS
[pdf]
Deepfake Detection in Super-Recognizers and Police Officers
Meike Ramon, Matthew Vowels, Matthew Groh
IEEE Security & Privacy
[ pdf ]
How to Distinguish AI-generated Images from Authentic Photographs
Negar Kamali, Karyn Nakamura, Angelos Chatzimparmpas, Jessica Hullman, Matthew Groh
arXiv
[ pdf ] [experiment]

2023 Papers

Art and the Science of Generative AI
Ziv Epstein, Aaron Hertzmann, Investigators of Human Creativity, Memo Akten, Hany Farid, Jessica Fjeld, Morgan R Frank, Matt Groh, Laura Herman, Neil Leach, Robert Mahari, Alex Pentland, Olga Russakovsky, Hope Schroeder, Amy Smith
Science (2023)
[pdf with additional details]
Augmenting Medical Image Classifiers with Synthetic Data from Latent Diffusion Models
Luke Sagers, James Diao, Luke Melas-Kyriazi, Matt Groh, Pranav Rajpurkar, Adewole Adamson, Veronica Rotemberg, Roxana Daneshjou, Arjun Manrai
preprint (under submission)
[pdf]
Towards Reliable Dermatology Evaluation Benchmarks
Fabian Gröger, Simone Lionetti, Philippe Gottfrois, Alvaro Gonzalez-Jimenez, Matt Groh, Roxana Daneshjou, Labelling Consortium, Alexander Navarini, Marc Pouly
Proceedings of Machine Learning Research - ML4Health Symposium (2023)
[pdf]

2022 Papers

Deepfake Detection by Human Crowds, Machines, and Machine-informed Crowds
Matt Groh, Ziv Epstein, Chaz Firestone, and Rosalind Picard
Proceedings of the National Academy of Science (2022)
[pdf] [experiment] [replication code and data]
Computational Empathy Counteracts the Effects of Anger on Human Creative Problem Solving
Matt Groh, Craig Ferguson, Rob Lewis, Rosalind Picard
10th International Conference on Affective Computing and Intelligent Interaction (ACII) (2022)
[pdf] [experiment] [replication code and data]
Towards Transparency in Dermatology Image Datasets with Experts, Crowds, and an Algorithm
Matt Groh, Caleb Harris, Roxana Daneshjou, Omar Badri, Arash Koochek
Proceedings of the ACM on Human-Computer Interaction (CSCW) (2022)
[pdf] [replication code and data]
Context Shift from Test Benchmarks to Real-World Production Performance
Matt Groh
ICML Workshop on Principles of Distribution Shift (2022)
[pdf]
Improving Dermatology Classifiers across Populations using Images Generated by Large Diffusion Models
Luke Sagers, James Diao, Matt Groh, Pranav Rajpurkar, Adewole Adamson, Arjun Manrai
NeurIPS Workshop Synthetic Data for Machine Learning (2022)
[pdf]

2021 Papers

Context in Automated Affect Recognition
Matt Groh, Rosalind Picard
NeurIPS Workshop Meaning in Context (2021) (and in progress)
[pdf]
Evaluating Deep Neural Networks Trained on Clinical Images in Dermatology with the Fitzpatrick 17k Dataset
Matt Groh, Caleb Harris, Luis Soenksen, Felix Lau, Rachel Han, Aerin Kim, Arash Koochek, and Omar Badri
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2021)
[pdf] [replication code and data]
Human detection of machine-manipulated media
Matt Groh, Ziv Epstein, Nick Obradovich, Manuel Cebrian, Iyad Rahwan
Communications of the ACM (2021)
[pdf] [replication code and data]
Social influence leads to the formation of diverse local trends
Ziv Epstein, Matt Groh, Abhimanyu Dubey, Alex 'Sandy' Pentland
Proceedings of the ACM on Human-Computer Interaction (CSCW) (2021)
[pdf]