Publications

These publications will be moved to the publication list as they are added to our repository

2026

• Y. Bai, G. Eskandar, Z. Liu, G. Kutyniok. Physics-informed video diffusion for shallow water equations. IEEE ICASSP 2026 (arXiv:2603.15627)
• Y. Bai, L. Yang, G. Eskandar, F. Shen, M. Altillawi, Z. Liu, G. Kutyniok. DRAW2ACT: Turning Depth-Encoded Trajectories into Robotic Demonstration Videos. ICRA 2026 (arXiv:2512.14217)
• L. Yang, Y. Bai, G. Eskandar, F. Shen, M. Altillawi,D. Chen, Z. Liu, Abhinav Valada. CoVAR: Co-generation of Video and Action for Robotic Manipulation via Multi-Modal Diffusion. ICRA 2026 (arXiv:2512.16023)
• J. von Berg, A. Fono, M. Datres, S. Maskey, G. Kutyniok. The Price of Robustness: Stable Classifiers Need Overparameterization. The Fourteenth International Conference on Learning representations (ICLR 2026) (Link)
• D. A. Nguyen, M. Datres, E. Araya, G. Kutyniok. Expressive Power of Recurrent Spiking Neural Networks for Sequence Modeling. In 1st ICLR Workshop on Time Series in the Age of Large Models (Link)
• E. Araya, M. Datres, G. Kutyniok. Random Spiking Neural Networks are Stable and Spectrally Simple. The Fourteenth International Conference on learning Representations (ICLR 2026) (Link)
• L. Yang, Y. Bai, Y. Wang, I. Alsarraj, G. Kutyniok, Z. Wang, K. Wu. Lightweight Learning from Actuation-Space Demonstrations via Flow Matching for Whole-Body Soft Robotic Grasping. IEEE Robotics and Automation Letters, 2026 (ieeexplore)
• G. Eskandar, F. Shen, M. Altillawi, D. Chen, Y. Bai, L. Yang, Z. Liu. VideoWeaver: Multimodal Multi-View Video-to-Video Transfer for Embodied Agents. IEEE/CVF Conference on Computer Vision and Pattern Recognition. Colorado Convention Center. (arXiv:2603.25420)
• H. Boche, A. Fono, G. Kutyniok. Computability of Matrix Functions and Compiling of Matrix Problems on Quantum Computers. 2026 IEEE International Symposium on Information Theory (ISIT) (pdf (PDF, 224 KB))
• A. Fono, N. Wedlich, H. Boche, G. Kutyniok. Complexity Theory meets Ordinary Differential Equations. 50-th anniversary of the Woudschoten Conference. Lecture Notes in Computational Science and Engineering (LNCSE) of Springer (arXiv:2604.09790)
• M. Matveev, V. Fojtik, H. Chou, G. Kutyniok, J. Maly. Conflicting Biases at the Edge of Stability: Norm versus Sharpness Regularization. (arXiv:2505.21423) ICML 2026
• Eichin, Florian; Du, Yupei; Mondorf, Philipp; Matveev, Maria; Plank, Barbara; Hedderich, Michael A.
  ExPLAIND: Unifying Model, Data, and Training Attribution to Study Model Behavior ICML 2026
• M. Seleznova, H. Chou, M. Verdun, G. Kutyniok. GradPCA: Leveraging NTK Alignment for Reliable Out-of-Distribution Detection. ICLR 2026 (arXiv:2505.16017)
• H. Andrade-Loarca, J. Hege, D. Cremers, G. Kutyniok. Neural Poisson Surface Reconstruction: Resolution-Agnostic Shape Reconstruction via Fourier Neural Operators, CVPR 2026 Workshop on 3D Geometry Generation for Scientific Computing (arXiv:2308.01766)
• S. Maskey, R. Paolino, F. Jogl, G. Kutyniok, J. F. Lutzeyer. Graph Representational Learning: When Does More Expressivity Hurt Generalization? ICLR 2026 (arXiv:2505.11298)
• P. Scholl, A. Bacho, H. Boche, G. Kutyniok. Symbolic Recovery of Differential Equations: The Identifiability Problem. Machine Learning Springer Nature (arXiv:2210.08342)
• H.–H. Chou, J. Maly, and D. Stöger: “How to induce regularization in generalized linear models: A guide to reparametrizing gradient flow”, Advances in Computational Mathematics, 2026 (arXiv:2308.04921)
• F. Körner, M. Matveev, F. Eichin, G. Kutyniok, B. Plank, M. A. Hedderich. Copy First, Translate Later: Interpreting Translation Dynamics in Multilingual Pretraining. EMNLP 2026 (arXiv:2604.17633)
• K. Kepesidis, N. Leopold-Kerschbaumer, T. Halenke, S. Süzeroğlu, M. Jung, M. Seleznova, N. Thorisch, J. Lorenz, T. Bocklitz, B. Eskofier, G. Kutyniok, F. Krausz. Conditional deep generative modeling of blood-based infrared spectra enables controlled in-silico phenotyping studies. npj Digital Medicine (8540695)
• M. Matveev, P. Esser, A. Bharadwaj, L. Bushnaq, G. Kutyniok. Functional Degeneracy in Neural Networks: Measurement and Pruning. AXIOM: Foundations of Efficient Deep Learning Workshop, NeurIPS 2026 (arXiv: 2608.30741)
• S. Rezwan, C. Li, J. Li, J. A. Cabrera, M. Reisslein, S. Speidel, G. Kutyniok, F. H. P. Fitzek. AIcXR+: Spiking Neural Network (SNN) Semantic Compression for 3D Point Clouds. IEEE Access, 2026
• E. Araya, M. Datres, G. Kutyniok, V. Pohl, H. Boche, C. de Boer, S. Speidel, S. Rezwan, J. A. Cabrera, F. H. P. Fitzek. Nachhaltige KI: energieeffiziente neuronale Netze für Chirurgie und Kommunikation. In: A. Gillhuber, G. Kauermann, W. Hauner (eds.), Künstliche Intelligenz und Data Science in Theorie und Praxis, 2nd ed., Springer Spektrum, 2026, pp. 131–152 (Springer)

2025

• H. Boche, A. Fono, and G. Kutyniok. “Turing meets Moore-Penrose: Computing the Pseudoinversen on Turing Machines”. In: IWOTA 2024 Conference Proceedings. Ed. by M. Iliopoulou, B. Lemmens, A. Loureiro, M. Marletta, and I. Wood. to appear. 2025.
• C. Bülte, Y. Sale, T. Löhr, P. Hofman, G. Kutyniok, E. Hüllermeier. A Formal Assessment of Uncertainty Measures in Regression. EIML@EurIPS 2025 Workshop Epistemic Intelligence in Machine Learning
• W.Samek, U. Schmid, J. Hoffart, D. Keim, G. Kutyniok, P. Schlunder, Whitepaper “Nach vollziehbare KI. Erklären, für wen, was und wofür“, Plattform Lernende Systeme, 2025.
• H. Boche, A. Fono, and G. Kutyniok. “HPC und KI - Wie erzielen wir Vertrauenswürdigkeit und reduzieren den Energieverbrauch?” In: Physik: Erkenntnisse und Perspektiven. Deutsche Physikalische Gesellschaft e.V., 2025
• G. Kutyniok. The Mathematics of Reliable Artificial Intelligence. SIAM News 57 (2025)

2026

• H. Boche, P. Hofmann, G. Kutyniok. Das menschliche Gehirn als Vorbild für künftige
  Computing-Generationen (pdf (PDF, 286 KB))
• J. Li, S. Huang, H. Feng, D. Zhou, G. Kutyniok. Sparse-Aware Neural Networks for Nonlinear Functionals: Mitigating the Exponential Dependence on Dimension.(arXiv:2604.06774)
• J. Maly, K. Neuner, and S. Vadia: “Efficient computation of the singular value decomposition with linear photonic circuits”, 2026 (arXiv:2602.18950)
• J. Maly and A. Veselovska: “Reliable one-bit quantization of bandlimited graph data via single-shot noise shaping”, 2026 (arXiv:2602.08669)
• M. Kranzlmüller, L. Koller, T. Ladner, M. Althoff. Set-Based Training of Neural Barrier Certificates for Safety Verification of Dynamical Systems. (arXiv:2605.02526)
• M.Seleznova. How Long Does Infinite Width Last? Signal Propagation in Long-Range Linear Recurrences (arXiv:2605.05113)
• H. Gottschalk, E. Partow, T. J. Riedlinger. Consistency of Learned Sparse Grid Quadrature Rules using NeuralODEs. (arXiv:2507.01533v2)
• S. Das, R. Bilas, P. Esser, S. Mukherjee. Beyond Linear and Overcomplete Regimes: A Mean-Field Analysis of Bottleneck Autoencoders. (arXiv:2606.07120)
• L. Mazza, M. Datres, A. Rodriguez, S. Bodenstedt, G. Kutyniok, S. Speidel. Understanding Multimodal Failure in Action-Chunking Behavioral Cloning (arXiv:2605.22493)
• H.--H. Chou, J. Maly, and H. Rauhut: "Compressive Sensing - Introduction and Relations to Deep Learning", 2026, (arXiv:2608.24211)
• M. Kranzlmüller, P. Esser, G. Kutyniok. Towards an Expressivity-Normalized Energy-Demand Comparison of ANNs and SNNs. (arXiv:2608.29869)
• M. Singh, G. Montúfar, G. Kutyniok. Polyhedral Geometry of Time-to-First-Spike Neural Networks. (arXiv: 2609.11227v1)
• C. Bülte, E. Partow, A. Gupta, P. Esser, G. Kutyniok. SCORE: Spectral Correlation Estimation for Multivariate Gaussians (arXiv:2610.12096)
• M. Štefánik, P. Mondorf, A. Waldis, M. Spiegel, R. Belanec, C. Yang, M. Matveev, J. Mazak, Q. Liu, M. Schepers, J. Kuchař, M. Kadlčík, A. Vawda-Oomerjee, C. Liu, S. Frieder, B. Plank, F. Barez, P. Stenetorp. AIMO Interpretability Challenge. (arXiv: 2607.13899)
• E. Araya, G. Kutyniok, W. Li, J. Maly, M. Singh. Formalizing the Intrinsic Dimension of Objective Landscapes by a Generalized Notion of Co-dimension. (arXiv:2610.39674)

2025

• J. Li and G. Kutyniok. Expressivity of Deep Neural Networks. (pdf (PDF, 1,450 KB))
• Sustainable AI: Mathematical Foundations of Spiking Neural Networks. A. Fono, M. Singh, E. Araya, P. Petersen, H. Boche, G. Kutyniok. (arXiv:2503.02013v1)
• C. Bülte, Y. Sale, T. Löhr, P. Hofman, G. Kutyniok, E. Hüllermeier. An Axiomatic Assessment of Entropy- and Variance-based Uncertainty Quantification in Regression. (arXiv:2504.18433)
• P. Scholl, A. Dietrich, S. Wolf, J. Lee, A. Schäffer, G. Kutyniok, M. Iskandar. Interpretable Robotic Friction Learning via Symbolic Regression. (arXiv:2505.13186)
• Z. Shumaylov, P. Zaika, P. Scholl, G. Kutyniok, L. Horesh, C. Schönlieb. When is a System Discoverable from Data? Discovery Requires Chaos. (https://arxiv.org abs/2511.08860)
• C. Kneissl, C. Bülte, P. Scholl, G. Kutyniok. Improved probabilistic regression using diffusion models.(arXiv:2510.04583)
• J. Suarez Cardona, H. Boche, G. Kutyniok. A Variational Framework for the Algorithmic Complexity of PDE Solutions. (arXiv:2510.21290)
• C. Bülte, Y. Sale, G. Kutyniok, E. Hüllermeier. Uncertainty Quantification for Regression: A Unified Framework based on kernel scores (arXiv:2510.25599)
• J. Li, I. Rosellon-Inclan, G. Kutyniok, J. Starck. CHEM: Estimating and Understanding Hallucinations in Deep Learning for Image Processing (arXiv:2512.09806)

2023

• M. Singh, A. Fono, G. Kutyniok. Expressivity of Spiking Neural Networks (arXiv:2308.08218)
• A. Bacho, H. Boche, G. Kutyniok. Reliable AI: Does the Next Generation Require
  Quantum Computing? (arXiv:2307.01301v1)