Publications

2026

  1. What Information Buys in Active Inference
    M. Kandemir and M.M. Çelikok
    arXiv Preprint, 2026
  3. Rethinking Least-Core Computation in Contextual-Distractor Games
    H. Kera, T. Yamauchi, and S.G. Nagarajan
    arXiv Preprint, 2026
  4. Let CSP Be Your ANCHOR: Adaptive Crystal Search over Frozen Structure Priors
    E.L. Hovmand, J. Elsborg, M. Kandemir, and A. Bhowmik
    arXiv Preprint, 2026
  6. Hitting Time Isomorphism for Multi-Stage Planning with Foundation Policies
    M.V. Boock, A. Akgül, M.M. Çelikok, and M. Kandemir
    In Neural Information Processing Systems, 2026
  7. Fitted Q-Iteration with Continuous Actions and Adaptive Data: Smoothed Coverage and Minimax Rates
    M. Haussmann, M.M. Çelikok, and M. Kandemir
    arXiv Preprint, 2026
  8. The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment
    F. Tonini, F. Torrielli, A.D. Lautrup, P. Schneider-Kamp, M.M. Çelikok, and L.G. Poech
    arXiv Preprint, 2026
  9. Uncertainty in Physics and AI: Taxonomy, Quantification, and Validation
    M. Haußmann, R. Winterhalder, and M. Ubiali
    arXiv Preprint, 2026
  10. Transition analysis 3: Skeletal age estimation program
    J.L. Boldsen, T.W. Heissel, S.M. Getz, S. Weise, M.V. Boock, L. Cruz-Filipe, S.D. Ousley, and G.R. Milner
    In Forensic Science International, 112909, 2026
  11. Policy-based Tuning of Autoregressive Image Models with Instance- and Distribution-Level Rewards
    O.B Baran, M. Kandemir, and R.G. Cinbis
    In European Conference on Computer Vision, 2026
  12. Distributional Active Inference
    A. Akgül, G. Baykal, M. Haußmann, M. M. Çelikok, and M. Kandemir
    In International Conference on Machine Learning, 2026
  13. Bridging the performance-gap between target-free and target-based reinforcement learning
    T. Vincent, Y. Tripathi, T. Faust, A. Akgül, Y. Oren, M. Kandemir, P. Peters, and C. D’Eramo
    In International Conference on Learning Representations, 2026
  14. Weighted Sequential Bayesian Inference for Non-Stationary Linear Contextual Bandits
    N. Werge, Y.S. Wu, A. Akgul, and M. Kandemir
    In International Conference on Uncertainty in Artificial Intelligence, 2026

2025

  1. In the picture: Medical imaging datasets, artifacts, and their living review
    A. Jiménez-Sánchez, N. Avlona, S.D. Boer, V.M. Campello, A. Feragen, E. Ferrante, M. Ganz, J.W. Gichoya, C. Gonzalez, S. Groefsema, A. Hering, A. Hulman, L. Joskowicz, D. Juodelyte, M. Kandemir, T. Kooi, J.d.P. Lérida, L.Y. Li, A. Pacheco, T. Rädsch, M. Reyes, T. Sourget, B.V. Ginneken, D. Wen, N. Weng, J.J. Xu, H.D. Zajaç, M.A. Zuluaga, and V. Cheplygina
    In Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency, 2025
  2. Towards an Experimentation Platform for Hybrid Human-AI Sequential Decision-Making
    H. Aydin, K. Godin-Dubois, L. Goncalvez Braz, F. Hengst, K. Baraka, M.M. Çelikok, A. Sauter, S. Wang, and F.A. Oliehoek
    In HHAI 2025: Proceedings of the 4th International Conference on Hybrid Human-Artificial Intelligence, 2025
  3. The Good, the Bad and the Ugly: Meta-Analysis of Watermarks, Transferable Attacks and Adversarial Defenses
    G. Gluch, B. Turan, S.G. Nagarajan, and S. Pokutta
    In Neural Information Processing Systems, 2025
  4. Directional Ensemble Aggregation for Actor-Critics
    N. Werge, Y.S. Wu, B. Tasdighi, and M. Kandemir
    arXiv Preprint, 2025
  5. Accurate Surrogate Amplitudes with Calibrated Uncertainties
    H. Bahl, E. Nina, L. Favaro, M. Haussmann, T. Plehn, and R. Winterhalder
    SciPost Physics Core, 2025
  6. ObjectRL: An Object-Oriented Reinforcement Learning Codebase
    G. Baykal, A. Akgül, M. Haussmann, B. Tasdighi, N. Werge, Y.S. Wu, and M. Kandemir
    arXiv Preprint, 2025
  7. Deep Actor-Critics with Tight Risk Certificates
    B. Tasdighi, M. Haußmann, Y.S. Wu, Masegosa. A.R., and M. Kandemir
    arXiv Preprint, 2025
  8. Latent mixed-effect models for high-dimensional longitudinal data
    Priscilla Ong, Manuel Haußmann, Otto Lönnroth, and Harri Lähdesmäki
    Transactions on Machine Learning Research, 2025
  9. On Adaptive Stochastic Optimization for Streaming Data: A Newton’s Method with O (dN) Operations
    Antoine Godichon-Baggioni and Nicklas Werge
    Journal of Machine Learning Research, 2025
  10. Overcoming Non-stationary Dynamics with Evidential Proximal Policy Optimization
    A. Akgül, G. Baykal, M. Haußmann, and M. Kandemir
    Transactions on Machine Learning Research, 2025
  11. Disentanglement with Factor Quantized Variational Autoencoders
    G. Baykal, M. Kandemir, and G. Unal
    Neurocomputing, 2025
  12. High-Dimensional Bayesian Optimisation with Gaussian Process Prior Variational Autoencoders
    S. Ramchandran, M. Haussmann, and H. Lähdesmäki
    In International Conference on Learning Representations, 2025
  13. Deep Exploration with PAC-Bayes
    B. Tasdighi, M. Haussmann, N. Werge, Y. Wu, and M. Kandemir
    In European Conference on Artificial Intelligence, 2025
  14. Improving Actor-Critic Training with Steerable Action-Value Approximation Errors
    B. Tasdighi, N. Werge, Y.S. Wu, and M. Kandemir
    In European Conference on Artificial Intelligence, 2025

2024

  1. A comparative study of clinical trial and real-world data in patients with diabetic kidney disease
    S. Kurki, V. Halla-Aho, M. Haussmann, H. Lähdesmäki, J.V. Leinonen, and M. Koskinen
    Scientific Reports, 2024
  2. Estimating treatment effects from single-arm trials via latent-variable modeling
    M. Haußmann, T.M.S. Le, V. Halla-Aho, S. Kurki, J. Leinonen, M. Koskinen, S. Kaski, and H. Lähdesmäki
    In International Conference on Artificial Intelligence and Statistics, 2024
  3. Deterministic Uncertainty Propagation for Improved Model-Based Offline Reinforcement Learning
    A. Akgül, M. Haussmann, and M. Kandemir
    In Neural Information Processing Systems, 2024
  4. Recursive PAC-Bayes: A Frequentist Approach to Sequential Prior Updates with No Information Loss
    Y. Wu, Y. Zhang, B. Chérief-Abdellatif, and Y. Seldin
    In Neural Information Processing Systems, 2024
  5. Latent variable model for high-dimensional point process with structured missingness
    M. Sinelnikov, M. Haussmann, and H. Lähdesmäki
    In International Conference on Machine Learning, 2024
  6. Learning high-dimensional mixed models via amortized variational inference
    P. Ong, M. Haussmann, and H. Lähdesmäki
    In Structured Probabilistic Inference & Generative Modeling, 2024
  7. PAC-Bayesian Soft Actor-Critic Learning
    B. Tasdighi, A. Akgül, M. Haussmann, K.K. Brink, and M. Kandemir
    In Advances in Approximate Bayesian Inference Symposium, 2024
  8. Continual Learning of Multi-modal Dynamics with External Memory
    A. Akgül, G. Unal, and M. Kandemir
    In Learning for Dynamics and Control, 2024
  9. EdVAE: Mitigating codebook collapse with evidential discrete variational autoencoders
    G. Baykal, M. Kandemir, and G. Unal
    In Pattern Recognition, 2024
  10. The Cold Posterior Effect Indicates Underfitting, and Cold Posteriors Represent a Fully Bayesian Method to Mitigate It
    Y. Zhang, Y. Wu, L.A. Ortega, and A.R. Masegosa
    Transactions on Machine Learning Research, 2024
  11. Calibrating Bayesian UNet++ for Sub-Seasonal Forecasting
    B. Asan, A. Akgül, A. Unal, M. Kandemir, and G. Unal
    In Tackling Climate Change with Machine Learning at ICLR 2024, 2024

2023

  1. Sampling-Free Probabilistic Deep State-Space Models
    A. Look, M. Kandemir, B. Rakitsch, and J. Peters
    arXiv Preprint, 2023
  2. Practical equivariances via relational conditional neural processes
    D. Huang, M. Haussmann, U. Remes, S. John, G. Clarté, K. Luck, S. Kaski, and L. Acerbi
    In Neural Information Processing Systems, 2023
  3. Demystifying the Myths and Legends of Nonconvex Convergence of SGD
    A. Dutta, E.H. Bergou, S. Boucherouite, N. Werge, M. Kandemir, and X. Li
    arXiv Preprint, 2023
  4. If there is no underfitting, there is no Cold Posterior Effect
    Y. Zhang, Y. Wu, L.A. Ortega, and A.R. Masegosa
    arXiv Preprint, 2023
  5. Improved Algorithms for Stochastic Linear Bandits Using Tail Bounds for Martingale Mixtures
    H. Flynn, D. Reeb, M. Kandemir, and J. Peters
    In Neural Information Processing Systems, 2023
  6. Estimation of Counterfactual Interventions under Uncertainties
    J. Weilbach, S. Gerwinn, M. Kandemir, and M. Fraenzle
    In Asian Conference on Machine Learning, 2023
  7. PAC-Bayes Bounds for Bandit Problems: A Survey and Experimental Comparison
    H. Flynn, D. Reeb, M. Kandemir, and J. Peters
    IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
  8. ALReg: Registration of 3D Point Clouds Using Active Learning
    Y.H. Sahin, O. Karabacak, M. Kandemir, and G. Unal
    MDPI Applied Sciences, 2023
  9. Cheap and Deterministic Inference for Deep State-Space Models of Interacting Dynamical Systems
    A. Look, B. Rakitsch, M. Kandemir, and J. Peters
    Transactions on Machine Learning Research, 2023
  10. Meta Continual Learning on Graphs with Experience Replay
    A. Unal, A. Akgül, M. Kandemir, and G. Unal
    Transactions on Machine Learning Research, 2023

2022

  1. Understanding Event-Generation Networks via Uncertainties
    M. Bellagente, M. Haussmann, M. Luchmann, and T. Plehn
    SciPost Physics, 2022
  2. Learning Interacting Dynamical Systems with Latent Gaussian Process ODEs
    C. Yildiz, M. Kandemir, and B. Rakitsch
    In Neural Information Processing Systems, 2022
  3. Evidential Turing Processes
    M. Kandemir, A. Akgül, M. Haussmann, and G. Unal
    In International Conference on Learning Representations, 2022
  4. A Deterministic Approximation to Neural SDEs
    A. Look, M. Kandemir, B. Rakitsch, and J. Peters
    IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
  5. Traversing Time with Multi-Resolution Gaussian Process State-Space Models
    K. Longi, J. Lindinger, O. Duennbier, M. Kandemir, A. Klami, and B Rakitsch
    In Learning for Dynamics and Control, 2022
  6. PAC-Bayesian lifelong learning for multi-armed bandits
    H. Flynn, D. Reeb, M. Kandemir, and J. Peters
    Data Mining and Knowledge Discovery, 2022

2021

  1. Learning Partially Known Stochastic Dynamics with Empirical PAC Bayes
    M. Haussmann, S. Gerwinn, A. Look, B. Rakitsch, and M. Kandemir
    In International Conference on Artificial Intelligence and Statistics, 2021
  2. Inferring the Structure of Ordinary Differential Equations
    J. Weilbach, S. Gerwinn, C. Weilbach, and M. Kandemir
    In International Conference on Machine Learning, 2021