Robin Schmucker



8227 Gates Hillman Center

4902 Forbes Ave

Pittsburgh, PA 15213

I am a PhD candidate in the Machine Learning Department at Carnegie Mellon University (CMU), where I am fortunate to be advised by Prof. Tom Mitchell.

My research focuses on machine learning for education, particularly in the context of large-scale online education. I aim to develop technologies that automatically refine their ability to teach as they support individual students and that generate insights that enhance our understanding of human learning. Some questions I am actively pursuing:

  • What can we learn about student knowledge acquistion using modern machine learning and robust statistical methods? [1, 2, 3, 4]

  • How can reinforcement learning help us understand the effects of instructional materials and refine the abilities of learning systems? [1, 2]

  • How can generative-AI facilitate structured conversational learning activities and foster new types of content authoring tools? [1, 2]

We are grateful to collaborate with the CK-12 Foundation, where our algorithms for student knowledge modeling and content selection benefit millions of learners worldwide.

Previously, I studied computer science at KIT in Germany. I was a research assistant at TECO with Prof. Michael Beigl. Supported by the CLICS fellowship, I worked on human-robot interaction advised by Prof. Manuela Veloso. In the industry, I was a research intern at AWS where I designed new algorithms and contributed to AutoGluon.

Research opportunities: I am happy to collaborate, discuss research and answer questions about CMU’s academic programs. If you are interested, please feel free to send me an email.

I am on the academic job market for positions in machine learning, education and related disciplines.


May 15, 2024 Our two papers (Differential Course Difficulty, KC Generation+Tagging) were accepted at L@S. We will also organize an interactive demonstration of Ruffle&Riley.
Mar 21, 2024 Come visit our LAK presentation on measuring temporal difficulty variations in university courses! We are honored to have received a best-paper nomination.
Mar 15, 2024 Our work our LLM-based conversational tutoring system was accepted to AIED! You can find the open-source implementation of Ruffle&Riley in our public GitHub repository.
Nov 02, 2023 Honored to give a talk about LLM-based conversational tutoring at the ALTTAI Seminar.
Sep 05, 2023 Come listen to our ECTEL presentation on how data-driven content evaluation and reinforcement learning can enhance student learning outcomes inside a large-scale online tutoring system.

selected publications

  1. AIED
    Ruffle&Riley: Insights from Designing and Evaluating a Large Language Model-Based Conversational Tutoring System
    Robin Schmucker, Meng Xia, Amos Azaria, and Tom Mitchell
    In Proceedings of the 25th International Conference on Artificial Intelligence in Education (to appear) , 2024
  2. L@S
    Gaining Insights into Group-Level Course Difficulty via Differential Course Functioning
    Frederik Baucks*Robin Schmucker*, Conrad Borchers, Zachary A. Pardos, and Laurenz Wiskott
    In Proceedings of the 11th ACM Conference on Learning @ Scale (to appear) , 2024
  3. LAK
    Gaining Insights into Course Difficulty Variations Using Item Response Theory
    Frederik Baucks*Robin Schmucker*, and Laurenz Wiskott
    In Proceedings of the 14th Learning Analytics and Knowledge Conference , 2024
  4. ECTEL
    Learning to Give Useful Hints: Assistance Action Evaluation and Policy Improvements
    Robin Schmucker, Nimish Pachapurkar, Shanmuga Bala, Miral Shah, and Tom Mitchell
    In Proceedings of the 18th European Conference on Technology Enhanced Learning , 2023
  5. ICCE
    Transferable Student Performance Modeling for Intelligent Tutoring Systems
    Robin Schmucker, and Tom M Mitchell
    In Proceedings of the 30th International Conference on Computers in Education , 2022
  6. JEDM
    Assessing the Knowledge State of Online Students-New Data, New Approaches, Improved Accuracy
    Robin Schmucker, Jingbo Wang, Shijia Hu, Tom Mitchell, and  others
    Journal of Educational Data Mining, 2022