|
/research/2025-12-09-flowm/
|
H. Lillemark, B. Huang, F. Zhan, Y. Du, and <strong>T. A. Keller</strong> (2026). <i>Flow Equivariant World Modeling for Partially Observed Dynamic Environments</i>. In: International Conference on Machine Learning (ICML).
|
|
|
/research/2025-12-08-fernn/
|
<strong>T. A. Keller</strong> (2025). <i>Flow Equivariant Recurrent Neural Networks</i>. In: Advances in Neural Information Processing Systems (NeurIPS). <strong>Spotlight, Top 13% accepted.</strong>
|
|
|
/research/2025-12-07-kuramoto-diffusion/
|
Y. Song, <strong>T. A. Keller</strong>, S. Brodjian, T. Miyato, Y. Yue, P. Perona, and M. Welling (2025). <i>Kuramoto Orientation Diffusion Models</i>. In: Advances in Neural Information Processing Systems (NeurIPS).
|
|
|
/research/2025-12-06-aussm/
|
A. Karuvally, F. Nowak, <strong>T. A. Keller</strong>, C. A. Alonso, T. Sejnowski, and H. T. Siegelmann (2025). <i>Bridging Expressivity and Scalability with Adaptive Unitary SSMs</i>. Advances in Neural Information Processing Systems (NeurIPS).
|
|
|
/research/2025-12-03-diffusion-generalization/
|
S. Bharthulwar, <strong>T. A. Keller</strong>, M. Theodosis, and D. E. Ba (2025). <i>From Extrapolation to Generalization: How Conditioning Transforms Symmetry Learning in Diffusion Models</i>. In: NeurIPS 2025 Workshop on Symmetry and Geometry in Neural Representations.
|
|
|
/research/2025-12-02-fnn/
|
J. Bertram, L. Dyballa, <strong>T. A. Keller</strong>, S. Kinger, and S. W. Zucker (2026). <i>How Neural is a Neural Foundation Model?</i> In: International Conference on Machine Learning. Under review. Accepted at Data on Brain & Mind Workshop @ NeurIPS 2025.
|
|
|
/research/2025-12-02-raptor/
|
M. Jacobs, T. Fel, R. Hakim, A. Brondetta, D. E. Ba, and <strong>T. A. Keller</strong> (2026). <i>Block Recurrent Dynamics in Vision Transformers</i>. In: International Conference on Learning Representations (ICLR).
|
|
|
/research/2025-10-02-wavelet-score/
|
E. L. Byrnes Finn, B. Wang, <strong>T. A. Keller</strong>, and D. E. Ba (2026). <i>Where the Score Lives: A Wavelet View of Diffusion</i>. In: Proceedings of the 29th International Conference on Artificial Intelligence and Statistics (AISTATS). Also accepted at SPIGM Workshop @ NeurIPS 2025.
|
|
|
/research/2025-08-15-waves-integrate/
|
M. Jacobs, R. C. Budzinski, L. Muller, D. E. Ba, and <strong>T. A. Keller</strong> (2025). <i>Traveling Waves Integrate Spatial Information Through Time</i>. In: Conference on Cognitive Computational Neuroscience (CCN). Oral presentation, Top 7%.
|
|
|
/research/2025-06-20-structure-rep-book/
|
Y. Song, <strong>T. A. Keller</strong>, N. Sebe, and M. Welling (May 2025). <i>Structured Representation Learning</i>. Synthesis Lectures on Computer Vision. Cham, Switzerland: Springer International Publishing.
|
|
|
/research/2025-06-15-langevinflow/
|
Y. Song, <strong>T. A. Keller</strong>, Y. Yue, P. Perona, and M. Welling (2025). <i>Langevin Flows for Modeling Neural Latent Dynamics</i>. In: Conference on Cognitive Computational Neuroscience (CCN). arXiv: 2507.11531 [cs.LG].
|
|
|
/research/2025-06-09-creativity/
|
E. L. B. Finn, <strong>T. A. Keller</strong>, M. Theodosis, and D. E. Ba (2025). <i>Origins of Creativity in Attention Based Diffusion Models</i>. In: High-dimensional Learning Dynamics 2025 @ ICML ’25.
|
|
|
/research/2025-03-22-nu-wave-ssms/
|
<strong>T. A. Keller</strong> (2025). <i>Nu-Wave State Space Models: Traveling Waves as a Biologically Plausible Context</i>. In: Science Communications Worldwide. doi: 10.57736/b30b-8eed.
|
|
|
/research/2025-01-03-cvrnn/
|
L. H. B. Liboni, R. C. Budzinski, A. N. Busch, S. Löwe, <strong>T. A. Keller</strong>, M. Welling, and L. E. Muller (2025). <i>Image segmentation with traveling waves in an exactly solvable recurrent neural network</i>. In: Proceedings of the National Academy of Sciences (PNAS) 122.1, e2321319121. doi: 10.1073/pnas.2321319121.
|
|
|
/research/2024-12-05-artistic-signatures/
|
E. Finn, <strong>T. A. Keller</strong>, E. Theodosis, and D. E. Ba (2024). <i>Learning Artistic Signatures: Symmetry Discovery and Style Transfer</i>. arXiv: 2412.04441 [cs.CV].
|
|
|
/research/2024-09-24-spacetime-perspective/
|
<strong>T. A. Keller</strong>, L. Muller, T. J. Sejnowski, and M. Welling (2026). <i>A Spacetime Perspective on Dynamical Computation in Neural Information Processing Systems</i>. arXiv: 2409.13669 [q-bio.NC].
|
|
|
/research/2024-08-25-sta/
|
Y. Song, <strong>T. A. Keller</strong>, Y. Yue, P. Perona, and M. Welling (2024). <i>Unsupervised Representation Learning from Sparse Transformation Analysis</i>. In: IEEE Transactions on Pattern Analysis and Machine Intelligence. arXiv: 2410.05564 [cs.LG].
|
|
|
/research/2024-04-19-relative-rsa/
|
<strong>T. A. Keller</strong>, T. Konkle, and C. Conwell (2024). <i>Towards the Use of Relative Representations for Lower-Dimensional, Interpretable Model-to-Brain Mappings</i>. In: Conference on Cognitive Computational Neuroscience (CCN).
|
|
|
/research/2024-01-16-wrnn/
|
<strong>T. A. Keller</strong>, L. Muller, T. Sejnowski, and M. Welling (2024). <i>Traveling Waves Encode the Recent Past and Enhance Sequence Learning</i>. In: International Conference on Learning Representations (ICLR).
|
|
|
/research/2023-11-07-thesis/
|
<strong>T. A. Keller</strong>. (2023) <i>Natural Inductive Biases for Artificial Intelligence</i>. PhD Thesis. University of Amsterdam
|
|
|
/research/2023-10-27-hssl/
|
<strong>T. A. Keller</strong>, X. Suau, and L. Zappella (2023). <i>Homomorphic Self-Supervised Learning</i>. In: Transactions on Machine Learning Research. issn: 2835-8856.
|
|
|
/research/2023-10-05-music-expect/
|
N. L. Masclef and <strong>T. A. Keller</strong> (2023). <i>Deep Generative Models of Music Expectation</i>. arXiv: 2310.03500 [cs.SD].
|
|
|
/research/2023-09-22-ffrl/
|
Y. Song, <strong>T. A. Keller</strong>, N. Sebe, and M. Welling (2023). <i>Flow Factorized Representation Learning</i>. In: Advances in Neural Information Processing Systems (NeurIPS). vol. 36. Curran Associates, Inc., pp. 49761–49782.
|
|
|
/research/2023-07-28-duet-ssl/
|
X. Suau, F. Danieli, <strong>T. A. Keller</strong>, A. Blaas, C. Huang, J. Ramapuram, D. Busbridge, and L. Zappella (2023). <i>DUET: 2D Structured and Approximately Equivariant Representations</i>. In: Proceedings of the 40th International Conference on Machine Learning. Vol. 202. Proceedings of Machine Learning Research. PMLR, pp. 32749–32769.
|
|
|
/research/2023-07-23-poflow/
|
Y. Song, <strong>T. A. Keller</strong>, N. Sebe, and M. Welling (2023). <i>Latent traversals in generative models as potential flows</i>. In: Proceedings of the 40th International Conference on Machine Learning. ICML’23. Honolulu, Hawaii, USA: JMLR.org.
|
|
|
/research/2023-06-23-waves/
|
<strong>T. A. Keller</strong> and M. Welling (2023). <i>Neural Wave Machines: Learning Spatiotemporally Structured Representations with Locally Coupled Oscillatory Recurrent Neural Networks</i>. In: Proceedings of the 40th International Conference on Machine Learning (ICML). vol. 202. Proceedings of Machine Learning Research, pp. 16168–16189.
|
|
|
/research/2022-12-20-locornn/
|
<strong>T. A. Keller</strong> and M. Welling (2022). <i>Locally Coupled Oscillator Networks Learn Traveling Waves and Topographic Organization</i>.
|
|
|
/research/2021-10-23-class-cluster-modeling/
|
<strong>T. A. Keller</strong>, Q. Gao, and M. Welling (2021). <i>Modeling Category-Selective Cortical Regions with Topographic Variational Autoencoders</i>. In: Shared Visual Representations in Humans and Machines (SVRHM) Workshop @ NeurIPS. <strong>Best Paper Award</strong>.
|
|
|
/research/2021-10-11-pctvae/
|
<strong>T. A. Keller</strong> and M. Welling (2021). <i>Predictive Coding with Topographic Variational Autoencoders</i>. In: IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). <strong>Oral presentation</strong>, pp. 1086–1091. doi: 10.1109/ICCVW54120.2021.00127.
|
|
|
/research/2021-09-03-tvae/
|
<strong>T. A. Keller</strong> and M. Welling (2021). <i>Topographic VAEs Learn Equivariant Capsules</i>. In: Advances in Neural Information Processing Systems (NeurIPS). vol. 34. Curran Associates, Inc., pp. 28585–28597.
|
|
|
/research/2021-07-29-apc/
|
F. Wever, <strong>T. A. Keller</strong>, L. Symul, and V. Garcia Satorras (2021). <i>As Easy as APC</i>. In: Self-Supervised Learning Workshop @ NeurIPS.
|
|
|
/research/2020-10-21-self-normalizing-flows/
|
<strong>T. A. Keller</strong>, J. W. T. Peters, P. Jaini, E. Hoogeboom, P. Forré, and M. Welling (July 2021). <i>Self Normalizing Flows</i>. In: Proceedings of the 38th International Conference on Machine Learning (ICML). vol. 139. Proceedings of Machine Learning Research. PMLR, pp. 5378–5387.
|
|
|
/research/2018-04-18-fwlstm/
|
<strong>T. A. Keller</strong>, S. N. Sridhar, and X. Wang (2018). <i>Fast Weight Long Short-Term Memory</i>. In: arXiv preprint. doi: 10.48550/ARXIV.1804.06511.
|
|
|
/LICENSE/
|
LICENSE
|
|
|
/NOTICE/
|
NOTICE
|
|
|
/
|
<h2 class="h1">T. Anderson Keller</h2>
|
|
|
/about/
|
About Me
|
|
|
/talks/
|
Invited Talks
|
|
|
/publications/
|
Publication List
|
|
|
/assets/img/about_me/cv.pdf
|
CV
|
|
|
/
|
Пустой анкор
|
|