publications

publications by categories in reversed chronological order.

2026

  1. Causal foundation models with observational data and partial graph information
    Use What You Know: Causal Foundation Models with Partial Graphs
    Arik Reuter, Anish Dhir, Cristiana Diaconu, Jake Robertson, Ole Ossen, Frank Hutter, Adrian Weller, Mark van der Wilk, and Bernhard Schölkopf
    In Forty-third International Conference on Machine Learning, 2026
    PDF Code
  2. Numerical and categorical feature encoding in the tabular transformer
    Beyond Black-Box Predictions: Identifying Marginal Feature Effects in Tabular Transformer Networks
    Anton Thielmann, Arik Reuter, and Benjamin Säfken
    In Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, 2026
    PDF Code

2025

  1. Do-PFN pre-training on causal graphs and observational and interventional data
    Do-PFN: In-Context Learning for Causal Effect Estimation
    Jake Robertson*, Arik Reuter*, Siyuan Guo, Noah Hollmann, Frank Hutter, and Bernhard Schölkopf
    In Advances in Neural Information Processing Systems, 2025
    Spotlight. * Shared first authors.
    PDF Code
  2. In-context text generation compared with sampling a Bayesian posterior
    Can Transformers Learn Full Bayesian Inference in Context?
    Arik Reuter, Tim G. J. Rudner, Vincent Fortuin, and David Rügamer
    In Proceedings of the 42nd International Conference on Machine Learning, 2025
    PDF Code
  3. Prior-fitted learning from synthetic datasets and prediction on new data
    Position: The Future of Bayesian Prediction Is Prior-Fitted
    Samuel Müller, Arik Reuter, Noah Hollmann, David Rügamer, and Frank Hutter
    In Proceedings of the 42nd International Conference on Machine Learning, 2025
    PDF
  4. Probabilistic Topic Modeling With Transformer Representations
    Arik Reuter, Anton Thielmann, Christoph Weisser, Benjamin Säfken, and Thomas Kneib
    IEEE Transactions on Neural Networks and Learning Systems, 2025
    PDF (arXiv) Code

2024

  1. STREAM: Simplified Topic Retrieval, Exploration, and Analysis Module
    Anton Thielmann, Arik Reuter, Benjamin Säfken, Christoph Weisser, Manish Kumar, and Gillian Kant
    In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 2024
    PDF Code
  2. Interpretable Additive Tabular Transformer Networks
    Anton Thielmann, Arik Reuter, Thomas Kneib, David Rügamer, and Benjamin Säfken
    Transactions on Machine Learning Research, 2024
    PDF Code
  3. Topics in the Haystack: Enhancing Topic Quality through Corpus Expansion
    Anton Thielmann, Arik Reuter, Quentin Seifert, Elisabeth Bergherr, and Benjamin Säfken
    Computational Linguistics, 2024
    PDF Code
  4. Mambular: A Sequential Model for Tabular Deep Learning
    Anton Thielmann, Manish Kumar, Christoph Weisser, Arik Reuter, Benjamin Säfken, and Soheila Samiee
    arXiv preprint arXiv:2408.06291, 2024
    PDF Code
  5. GPTopic: Dynamic and Interactive Topic Representations
    Arik Reuter, Bishnu Khadka, Anton Thielmann, Christoph Weisser, Sebastian Fischer, and Benjamin Säfken
    arXiv preprint arXiv:2403.03628, 2024
    PDF Code
  6. Neural Additive Image Model: Interpretation through Interpolation
    Arik Reuter, Anton Thielmann, and Benjamin Saefken
    arXiv preprint arXiv:2405.02295, 2024
    PDF Code

2023

  1. Pseudo-document simulation for comparing LDA, GSDMM and GPM topic models on short and sparse text using Twitter data
    Christoph Weisser, Christoph Gerloff, Anton Thielmann, Andre Python, Arik Reuter, Thomas Kneib, and Benjamin Säfken
    Computational Statistics, 2023
    PDF