Recent Publications of Group Members
Note: Only publications since 2015 from the Visual Computing group at JGU Mainz are listed. For earlier / other work, see the individual home pages of the group members.
J.P. Filling, F. Post, M. Wand, D. Andrienko
Direct Molecular Polarizability Prediction with SO (3) Equivariant Local Frame GNNs
Machine Learning and the Physical Sciences Workshop at NeurIPS 2025
C.H.X. Ali Mehmeti-Göpel, M. Wand
ResNets Are Deeper Than You Think
arXiv preprint arXiv:2506.14386, 2025
C.H.X. Ali Mehmeti-Göpel, M. Wand
On the Weight Dynamics of Deep Normalized Networks.
In: International Conference on Machine Learning (ICML), 2024.
K. H.M. Klos, J. Disselhoff, K. Everschor-Sitte, F. Schmid
Reconstructing micro-magnetic vector fields based on topological charge distributions via generative neural network systems
Machine Learning and the Physical Sciences Workshop at NeurIPS 2024
J. Disselhoff, M. Wand
Probing the Inductive Bias of Neural Networks through Learning Random Cellular Automata
Manuscript, https://openreview.net/pdf?id=QWHArest6b, 2025
D. Franzen, J. Disselhoff, D. Hartmann
Product of Experts with LLMs: Boosting Performance on ARC Is a Matter of Perspective
ICML 2025
D. Franzen, J. Disselhoff, D. Hartmann
The LLM ARChitect: Solving ARC-AGI Is A Matter of Perspective
Technical Report for ARC Prize 2024
https://da-fr.github.io/arc-prize-2024/the_architects.pdf
S. Lemcke, J.H. Appeldorn, M. Wand, T. Speck
Toward a structural identification of metastable molecular conformations
The Journal of Chemical Physics 159 (11), 2023
C.H.X. Ali Mehmeti-Göpel, M. Wand
On the weight dynamics of deep normalized networks
arXiv preprint arXiv:2306.00700, 2023
A.C. Woerl, J. Disselhoff, M. Wand
Initialization noise in image gradients and saliency maps
IEEE CVPR 2023
C.H.X. Ali Mehmeti-Göpel, J. Disselhoff
Nonlinear Advantage: Trained Networks Might Not Be As Complex as You Think
International Conference on Machine Learning, 529-546, 2023.
J. Disselhoff, M. Wand
Relating Generalization in Deep Neural Networks to Sensitivity of Discrete Dynamical Systems
Machine Learning and the Physical Sciences Workshop at NeurIPS 2025
S. Brodehl, R. Müller, E. Schömer, P. Spichtinger, M. Wand
End-to-end prediction of lightning events from geostationary satellite images
Remote Sensing 14 (15), 3760, 2022, 2022
D. Franzen, M. Wand
General nonlinearities in so (2)-equivariant cnns
Advances in neural information processing systems 34, 9086-9098, 2021
D. Franzen, M. Wand
Nonlinearities in steerable so (2)-equivariant cnns
arXiv preprint arXiv:2109.06861, 2021
L. Grulich, R. Weigel, A. Hildebrandt, M. Wand, P. Spichtinger
Automatic shape detection of ice crystals
Journal of Computational Science 54, 101429, 2021
M. Stieffenhofer, T. Bereau, M. Wand
Adversarial reverse mapping of condensed-phase molecular structures: Chemical transferability
APL Materials 9 (3), 2021
D. Hartmann, S. Brodehl, M. Wand
ActCooLR–High-Level Learning Rate Schedules using Activation Pattern Temperature
Manuscript, https://openreview.net/pdf?id=yqj6q_eNTJd
M. Stieffenhofer, M. Wand, T. Bereau
Adversarial reverse mapping of equilibrated condensed-phase molecular structures
Machine Learning: Science and Technology 1 (4), 045014, 2021
T. Dratsch, M. Korenkov, D. Zopfs, S. Brodehl, B. Baessler, D. Giese, S. Brinkmann, D. Maintz, D. Pinto dos Santos
Practical applications of deep learning: classifying the most common categories of plain radiographs in a PACS using a neural network
European radiology 31 (4), 1812-1818, 2021
D. Hartmann, D. Franzen, S. Brodehl
Studying the evolution of neural activation patterns during training of feed-forward relu networks
Frontiers in artificial intelligence 4, 642374, 2021
A.-C. Woerl, M. Eckstein, J. Geiger, D. C. Wagner, T. Daher, P. Stenzel, A. Fernandez, A. Hartmann, M. Wand, W. Roth, S. Foersch
Deep learning predicts molecular subtype of muscle-invasive bladder cancer from conventional histopathological slides
European urology 78 (2), 256-264, 2020
C.H.X.A. Ali Mehmeti-Göpel, D. Hartmann, M. Wand
Ringing relus: Harmonic distortion analysis of nonlinear feedforward networks
International Conference on Learning Representations, 2020
J. Grau Chopite, M.B. Hullin, M. Wand, J. Iseringhausen
Deep non-line-of-sight reconstruction
IEEE CVPR 2020
A. Mähringer‐Kunz, F. Wagner, F. Hahn, A. Weinmann, S. Brodehl, S. Schotten, J. B. Hinrichs, C. Düber, P. R. Galle, D. Pinto dos Santos, R. Kloeckner
Predicting survival after transarterial chemoembolization for hepatocellular carcinoma using a neural network: A Pilot Study
Liver International 40 (3), 694-703, 2020
F. Jungmann, S. Brodehl, R. Buhl, P. Mildenberger, E. Schömer, C. Düber, D. Pinto Dos Santos
Workflow-centred open-source fully automated lung volumetry in chest CT
Clinical Radiology 75 (1), 78. e1-78. e7, 2020
D. Hartmann, M. Wand
Progressive Stochastic Binarization of Deep Networks
Fifth Workshop on Energy Efficient Machine Learning and Cognitive Computing-NeurIPS Edition (EMC2-NIPS), 2019
D. Pinto dos Santos, S. Brodehl, B. Baeßler, G. Arnhold, T. Dratsch, S.-H. Chon, P. Mildenberger, F. Jungmann
Structured report data can be used to develop deep learning algorithms: a proof of concept in ankle radiographs
Insights into imaging 10 (1), 93, 2019
D. Pinto dos Santos, D. Giese, S. Brodehl, S.H. Chon, W. Staab, R. Kleinert, D. Maintz, B. Baeßler
Medical students' attitude towards artificial intelligence: a multicentre survey
European Radiology, 1-7, 2018
C. Li, M. Wand
Precomputed real-time texture synthesis with markovian generative adversarial networks
European conference on computer vision, 702-716, 2016
D.G. Aliaga, İ. Demir, B. Benes, M. Wand
Inverse procedural modeling of 3d models for virtual worlds (Siggraph '16 Course)
ACM SIGGRAPH 2016 Courses
J. Kalojanov, M. Wand, P. Slusallek
Building construction sets by tiling grammar simplification
Computer Graphics Forum 35 (2), 13-25, 2016
C. Li, M. Wand
Combining markov random fields and convolutional neural networks for image synthesis
IEEE CVPR 2016
C. Li, M. Wand
Approximate translational building blocks for image decomposition and synthesis
ACM Transactions on Graphics (TOG) 34 (5), 1-16, 2015
C. Li, M. Wand, X. Wu, H.-P. Seidel
Approximate 3d partial symmetry detection using co-occurrence analysis
International Conference on 3D Vision, 425-433, 2015.
R. Herzog, D. Mewes, M. Wand, L. Guibas, H.-P. Seidel
LeSSS: Learned Shared Semantic Spaces for Relating Multi‐Modal Representations of 3D Shapes
Computer Graphics Forum 34(5), 141-151, 2015
H. Liu, U. Vimont, M. Wand, M.P. Cani, S. Hahmann, D. Rohmer, N.J. Mitra
Replaceable substructures for efficient part‐based modeling
Computer Graphics Forum 34 (2), 503-513, 2015