International Conference Contributions
On this page, you will find the latest contributions from Computational Health Center researchers at international AI conferences:
ICML 2025
ICML 2025
Henrik von Kleist, Joshua Wendland, Ilya Shpitser, Carsten Marr
Feature Importance Metrics in the Presence of Missing Data
Lukas Thede, Karsten Roth, Matthias Bethge, Zeynep Akata, Thomas Hartvigsen
Understanding the Limits of Lifelong Knowledge Editing in LLMs. arXiv
Arik Reuter, Tim G. J. Rudner, Vincent Fortuin, David Rügamer
Can Transformers Learn Full Bayesian Inference in Context? arXiv
Nora Schneider, Lars Lorch, Niki Kilbertus, Bernhard Schölkopf, Andreas Krause
Generative Intervention Models for Causal Perturbation Modeling. arXiv
Jonas Schweisthal, Dennis Frauen, Maresa Schröder, Konstantin Hess, Niki Kilbertus, Stefan Feuerriegel
Learning Representations of Instruments for Partial Identification of Treatment Effects. arXiv
Alessandro Palma, Sergei Rybakov, Leon Hetzel, Stephan Günnemann, Fabian J Theis
Enforcing Latent Euclidean Geometry in Single-Cell VAEs for Manifold Interpolation. OpenReview
Corinna Coupette, Jeremy Wayland, Emily Simons, Bastian Rieck
No Metric to Rule Them All: Toward Principled Evaluations of Graph-Learning Datasets. arXiv
MICCAI 2025
MICCAI 2025
Muhammed Furkan Dasdelen, Hyesu Lim, Michele Buck, Katharina S. Götze,
Carsten Marr, Steffen Schneider
CytoSAE: Interpretable Cell Embeddings for Hematology
Daniel Lang, Richard Osuala, Veronika Spieker, Karim Lekadir, Rickmer Braren, Julia Schnabel
Temporal Neural Cellular Automata: Application to modeling of contrast enhancement in breast MRI. arXiv
Chun Kit Wong, Anders Christensen, Cosmin Bercea, Julia Schnabel, Martin Tolsgaard, Aasa Feragen
Influence of Classification Task and Distribution Shift Type on OOD Detection in Fetal Ultrasound.
Tomáš Chobola, Julia Schnabel, Tingying Peng
Lightweight Data-Free Denoising for Detail-Preserving Biomedical Image Restoration.
ICLR 2025
ICLR 2025
Hyesu Lim, Jinho Choi, Jaegul Choo, Steffen Schneider
Sparse autoencoders reveal selective remapping of visual concepts during adaptation. arXiv
Rodrigo González Laiz, Tobias Schmidt, Steffen Schneider
Self-supervised contrastive learning performs non-linear system identification. arXiv
Massimo Bini, Leander Girrbach, Zeynep Akata
Decoupling Angles and Strength in Low-rank Adaptation. arXiv
Théo Uscidda, Luca Eyring, Karsten Roth, Fabian J Theis, Zeynep Akata, Marco Cuturi
Disentangled Representation Learning with the Gromov-Monge Gap. arXiv
Shuchen Wu, Mirko Thalmann, Peter Dayan, Zeynep Akata, Eric Schulz
Building, Reusing, and Generalizing Abstract Representations from Concrete Sequences. arXiv
Can Demircan, Tankred Saanum, Akshay K. Jagadish, Marcel Binz, Eric Schulz
Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models. arXiv
Alex Kipnis, Konstantinos Voudouris, Luca M. Schulze Buschoff, Eric Schulz
metabench -- A Sparse Benchmark to Measure General Ability in Large Language Models. arXiv
Georg Manten, Cecilia Casolo, Emilio Ferrucci, Søren Wengel Mogensen, Cristopher Salvi, Niki Kilbertus
Signature Kernel Conditional Independence Tests in Causal Discovery for Stochastic Processes. arXiv
Tristan Cinquin, Stanley Lo, Felix Strieth-Kalthoff , Alan Aspuru-Guzik, Geoff Pleiss, Robert Bamler, Tim G. J. Rudner, Vincent Fortuin, Agustinus Kristiadi
What Actually Matters for Materials Discovery: Pitfalls and Recommendations in Bayesian Optimization. OpenReview
Yasin Esfandiari, Stefan Bauer, Sebastian Stich, Andrea Dittadi
Sample Quality-Likelihood trade-off in Diffusion Models. OpenReview
Amir Mohammad Karimi Mamaghan, Samuele Papa, Karl H. Johansson, Stefan Bauer, Andrea Dittadi
Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Models. arXiv
Alessandro Palma, Till Richter, Hanyi Zhang, Manuel Lubetzki, Alexander Tong, Andrea Dittadi, Fabian Theis
Multi-Modal and Multi-Attribute Generation of Single Cells with CFGen. arXiv
Jonas Schweisthal, Dennis Frauen, Maresa Schröder , Konstantin Hess, Niki Kilbertus, Stefan Feuerriegel
Learning Representations of Instruments for Partial Identification of Treatment Effects. arXiv
Ferdinand Kapl, Amir Mohammad Karimi Mamaghan, Max Horn, Carsten Marr, Stefan Bauer, Andrea Dittadi
Object-Centric Representations Generalize Better Compositionally with Less Compute. OpenReview
Kristina Ulicna, Rebecca Boiarsky, Eeshaan Jain, Till Richter, Giovanni Palla, Jason Hartford, Oren Kraus, Aleksandrina Goeva, Charlotte Bunne, Fabian Theis
Learning Meaningful Representations of Life (LMRL) Workshop @ ICLR 2025. OpenReview
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2025
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2025
Sanghwan Kim, Rui Xiao, Iuliana Georgescu, Stephan Alaniz, Zeynep Akata
COSMOS: Cross-Modality Self-Distillation for Vision Language Pretraining. arXiv
Rui Xiao, Sanghwan Kim, Iuliana Georgescu, Zeynep Akata, Stephan Alaniz
FLAIR: VLM with Fine-grained Language-informed Image Representations. arXiv
Sebastian Dziadzio, Vishaal Udandarao, Karsten Roth, Ameya Prabhu, Zeynep Akata, Samuel Albanie, Matthias Bethge
How to Merge Your Multimodal Models Over Time? arXiv
Karsten Roth, Zeynep Akata, Dima Damen, Ivana Balazevic, Olivier J Henaff
Context-Aware Multimodal Pretraining. arXiv
AISTATS 2025
AISTATS 2025
Steffen Schneider, Rodrigo González Laiz, Anastasiia Filippova, Markus Frey, Mackenzie W Mathis
Time-series attribution maps with regularized contrastive learning. arXiv
Xudong Sun, Nutan Chen, Alexej Gossmann, Yu Xing, Matteo Wohlrapp, Emilio Dorigatti, Carla Feistner, Felix Drost, Daniele Scarcella, Lisa Helen Beer, Carsten Marr
Multi-objective Hierarchical Feedback Optimization of Penalty Multiplier for Domain Invariant Auto-encoding. arXiv
Małgorzata Łazęcka, Ewa Szczurek
Factor Analysis with Correlated Topic Model for Multi-Modal Data. OpenReview
NeurIPS 2025
NeurIPS 2025
Jinho Choi, Hyesu Lim, Steffen Schneider, Jaegul Choo.
ConceptScope: Characterizing Dataset Bias via Disentangled Visual Concepts.
Tobias Schmidt, Steffen Schneider, Matthias Bethge.
Equivariance by Contrast: Identifiable Equivariant Embeddings from Unlabeled Finite Group Actions.
Michal Kmicikiewicz, Vincent Fortuin, Ewa Szczurek
ProSpero: Active Learning for Robust Protein Design Beyond Wild-Type Neighborhoods. arXiv
Szymon Płotka, Maciej Chrabaszcz, Gizem Mert, Ewa Szczurek, Arkadiusz Sitek
Mamba Goes HoME: Hierarchical Soft Mixture-of-Experts for 3D Medical Image Segmentation. arXiv
Luca Eyring, Shyamgopal Karthik, Alexey Dosovitskiy, Nataniel Ruiz, Zeynep Akata
Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models. arXiv
Shuchen Wu, Stephan Alaniz, Shyamgopal Karthik, Peter Dayan, Eric Schulz, Zeynep Akata
Concept-Guided Interpretability via Neural Chunking. arXiv
Jitin Jami, Thomas Altstidl, Jonas Leon Müller, Jindong Li, Dario Zanca, Björn Eskofier, Heike Leutheuser
Mateusz Pach, Shyamgopal Karthik, Quentin Bouniot, Serge Belongie, Zeynep Akata
Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models. arXiv
Joel Valdivia Ortega, Lorenz Lamm, Franziska Eckardt, Benedikt Schworm, Marion Jasnin, Tingying Peng
Randomized-MLP Regularization Improves Domain Adaptation and Interpretability in DINOv2.
Milena Rmus, Akshay Jagadish, Marvin Mathony, Tobias Ludwig, Eric Schulz
Generating computational cognitive models using large language models. arXiv
B Cosmin I. Bercea, Jun Li, Philipp Raffler, Evamaria Olga Riedel, Lena Schmitzer, Angela Kurz, Felix Bitzer, Paula Roßmüller, Julian Canisius, Mirjam L. Beyrle, Che Liu, Wenjia Bai, Bernhard Kainz, Julia A. Schnabel, Benedikt Wiestler
NOVA: A Benchmark for Anomaly Localization and Clinical Reasoning in Brain MRI.
ICCV 2025
ICCV 2025
Jessica Bader, Leander Girrbach, Stephan Alaniz, Zeynep Akata
SUB: Benchmarking CBM Generalization via Synthetic Attribute Substitutions. arXiv
Shyamgopal Karthik, Huseyin Coskun, Zeynep Akata, Sergey Tulyakov, Jian Ren, Anil Kag
Scalable Ranked Preference Optimization for Text-to-Image Generation. arXIv
Neurips AI4Drug 2025
Neurips AI4Drug 2025
Yang An, Felix Drost, Adrian Straub, Annalisa Marsico, Dirk Busch, Benjamin Schubert
TCRGenesis: Generation of SIINFEKL-specific T-cell receptor sequences using autoregressive Transformer. OpenReview
ICML 2024
ICML 2024
Massimo Bini, Karsten Roth, Zeynep Akata, Anna Khoreva
ETHER: Efficient Finetuning of Large-Scale Models with Hyperplane Reflections. arXiv
Kouroche Bouchiat, Alexander Immer, Hugo Yèche, Gunnar Ratsch, Vincent Fortuin
Improving Neural Additive Models with Bayesian Principles. arXiv
Theodore Papamarkou, Maria Skoularidou,Konstantina Palla, Laurence Aitchison, Julyan Arbel, David Dunson, Maurizio Filippone, Vincent Fortuin, Philipp Hennig, José Miguel Hernández-Lobato, Aliaksandr Hubin, Alexander Immer, Theofanis Karaletsos, Mohammad Emtiyaz Khan, Agustinus Kristiadi, Yingzhen Li, Stephan Mandt, Christopher Nemeth, Michael A Osborne, Tim G. J. Rudner
Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI. arXiv
Julian Coda-Forno, Marcel Binz, Jane X. Wang, Eric Schulz
CogBench: A large language model walks into a psychology lab. arXiv
Johannes A. Schubert, Akshay K. Jagadish, Marcel Binz, Eric Schulz
In-context learning agents are asymmetric belief updaters. arXiv
Akshay K. Jagadish, Julian Coda-Forno, Mirko Thalmann, Eric Schulz, Marcel Binz
Ecologically rational meta-learned inference explains human category learning . arXiv
Theodore Papamarkou, Tolga Birdal, Michael M. Bronstein, Gunnar E. Carlsson, Justin Curry, Yue Gao, Mustafa Hajij, Roland Kwitt, Pietro Lio, Paolo Di Lorenzo,Vasileios Maroulas, Nina Miolane, Farzana Nasrin, Karthikeyan Natesan Ramamurthy, Bastian Rieck, Simone Scardapane, Michael T Schaub, Petar Veličković, Bei Wang, Yusu Wang
Position: Topological Deep Learning is the New Frontier for Relational Learning. arXiv
Jeremy Wayland, Corinna Coupette, Bastian Rieck
Mapping the Multiverse of Latent Representations. arXiv
Georgios Kaissis, Stefan Kolek, Borja Balle, Jamie Hayes, Daniel Rueckert
Beyond the Calibration Point: Mechanism Comparison in Differential Privacy. arXiv
NeurIPS 2024
NeurIPS 2024
Dominik Klein, Théo Uscidda, Fabian Theis, Marco Cuturi
GENOT: Entropic (Gromov) Wasserstein Flow Matching with Applications to Single-Cell Genomics. arXiv
Artur Szałata, Andrew Benz, Robrecht Cannoodt, Mauricio Cortes, Jason Fong, Sunil Kuppasani, Richard Lieberman, Tianyu Liu, Javier Mas-Rosario, Rico Meinl, Jalil Nourisa, Jared Tumiel, Tin M. Tunjic, Mengbo Wang, Noah Weber, Hongyu Zhao, Benedict Anchang, Fabian Theis, Malte Luecken, Daniel Burkhardt
A Benchmark for Prediction of Transcriptomic Responses to Chemical Perturbations Across Cell Types.
Sirine Ayadi, Leon Hetzel, Johanna Sommer, Fabian Theis, Stephan Günnemann
Unified Guidance for Geometry-Conditioned Molecular Generation. arXiv
Tristan Cinquin, Marvin Pförtner, Vincent Fortuin, Philipp Hennig, Robert Bamler
FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning. arXiv
Rayen Dhahri, Alexander Immer, Bertrand Charpentier, Stephan Günnemann, Vincent Fortuin
Shaving Weights with Occam’s Razor: Bayesian Sparsification for Neural Networks using the Marginal Likelihood. arXiv
Karsten Roth, Vishaal Udandarao, Sebastian Dziadzio, Ameya Prabhu, Medhi Cherti, Oriol Vinyals, Olivier Henaff, Samuel Albanie, Matthias Bethge, Zeynep Akata
A Practitioner’s Guide to Continual Multimodal Pretraining. arXiv
Luca Eyring, Shyamgopal Karthik, Karsten Roth, Alexey Dosovitskiy, Zeynep Akata
ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization. arXiv
Elisabeth Ailer, Niclas Dern, Jason Hartford, Niki Kilbertus
Targeted Sequential Indirect Experiment Design. arXiv
Yashas Annadani, Panagiotis Tigas, Stefan Bauer, Adam Foster
Amortized Active Causal Induction with Deep Reinforcement Learning. arXiv
Christina Bukas, Harshavardhan Subramanian, Fenja See, Carina Steinchen, Ivan Ezhov, Gowtham Boosarpu, Sara Asgharpour, Gerald Burgstaller, Mareike Lehmann, Florian Kofler, Marie Piraud
MultiOrg: A Multi-rater Organoid-detection Dataset. arXiv
Can Demircan, Tankred Saanum, Leonardo Pettini, Marcel Binz, Blazej Baczkowski, Christian Doeller, Mona Garvert, Eric Schulz
Evaluating Alignment Between Humans and Neural Network Representations in Image Based Learning Tasks. arXiv
Thomas Altstidl, David Dobre, Arthur Kosmala, Bjoern Eskofier, Gauthier Gidel, Leo Schwinn
On the Scalability of Certified Adversarial Robustness with Generated Data.
Katharina Limbeck, Rayna Andreeva, Rik Sarkar, Bastian Rieck
Metric Space Magnitude for Evaluating the Diversity of Latent Representations. arXiv
