23.04.2025

MCML at ICLR 2025

52 Accepted Papers (35 Main, and 17 Workshops)

13th International Conference on Learning Representations, Singapore, Apr 24-28, 2025

We are happy to announce that MCML researchers have contributed a total of 52 papers to ICLR 2025: 35 Main, and 17 Workshop papers. Congrats to our researchers!

Main Track (35 papers)

E. Abdelrahman • L. Zhao • V. T. Hu • M. Cord • P. Perez • M. Elhoseiny
ToddlerDiffusion: Interactive Structured Image Generation with Cascaded Schrödinger Bridge.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL GitHub

H. Baniecki • G. Casalicchio • B. Bischl • P. Biecek
Efficient and Accurate Explanation Estimation with Distribution Compression.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. Spotlight Presentation. URL GitHub

M. Bini • L. Girrbach • Z. Akata
Decoupling Angles and Strength in Low-rank Adaptation.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL GitHub

K. Bhatia • F. Köhler • N. Thuerey
PRDP: Progressively Refined Differentiable Physics.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

Q. Bouniot • P. Mozharovskyi • F. d'Alché-Buc
Tailoring Mixup to Data for Calibration.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

S. Dahan • G. Bénédict • L. Z. J. Williams • Y. Guo • D. Rückert • R. Leech • E. C. Robinson
SIM: Surface-based fMRI Analysis for Inter-Subject Multimodal Decoding from Movie-Watching Experiments.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL GitHub

D. Frauen • K. Heß • S. Feuerriegel
Model-agnostic meta-learners for estimating heterogeneous treatment effects over time.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

A. Findeis • T. Kaufmann • E. Hüllermeier • S. Albanie • R. D. Mullins
Inverse Constitutional AI: Compressing Preferences into Principles.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL GitHub

L. Fang • Y. Wang • Z. Liu • C. Zhang • S. Jegelka • J. Gao • B. Ding • Y. Wang
What is Wrong with Perplexity for Long-context Language Modeling?
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL GitHub

L. Girrbach • Y. Huang • S. Alaniz • T. Darrell • Z. Akata
Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs).
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

K. Heß • S. Feuerriegel
Stabilized Neural Prediction of Potential Outcomes in Continuous Time.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

D. Herbst • S. Jegelka
Higher-Order Graphon Neural Networks: Approximation and Cut Distance.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. Spotlight Presentation. URL

C. Kern • M. P. Kim • A. Zhou
Multi-Accurate CATE is Robust to Unknown Covariate Shifts.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. Journal Track. URL URL

M. Kollovieh • M. Lienen • D. Lüdke • L. Schwinn • S. Günnemann
Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

J. Kaiser • K. Schwethelm • D. Rückert • G. Kaissis
Laplace Sample Information: Data Informativeness Through a Bayesian Lens.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

C. Kolb • T. Weber • B. Bischl • D. Rügamer
Deep Weight Factorization: Sparse Learning Through the Lens of Artificial Symmetries.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

L. Lux • A. H. Berger • A. Weers • N. Stucki • D. Rückert • U. Bauer • J. C. Paetzold
Topograph: An efficient Graph-Based Framework for Strictly Topology Preserving Image Segmentation.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

H. Lim • J. Choi • J. Choo • S. Schneider
Sparse autoencoders reveal selective remapping of visual concepts during adaptation.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

Y. Li • D. Rügamer • B. Bischl • M. Rezaei
Calibrating LLMs with Information-Theoretic Evidential Deep Learning.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL GitHub

R. G. Laiz • T. Schmidt • S. Schneider
Self-supervised contrastive learning performs non-linear system identification.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL GitHub

G. Manten • C. Casolo • E. Ferrucci • S. Mogensen • C. Salvi • N. Kilbertus
Signature Kernel Conditional Independence Tests in Causal Discovery for Stochastic Processes.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

M. Muschalik • F. Fumagalli • P. Frazzetto • J. Strotherm • L. Hermes • A. Sperduti • E. Hüllermeier • B. Hammer
Exact Computation of Any-Order Shapley Interactions for Graph Neural Networks.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

L. Rauchwerger • S. Jegelka • R. Levie
Generalization, Expressivity, and Universality of Graph Neural Networks on Attributed Graphs.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

P. Scholl • K. Bieker • H. Hauger • G. Kutyniok
ParFam -- (Neural Guided) Symbolic Regression Based on Continuous Global Optimization.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL GitHub

L. Sang • Z. Canfes • D. Cao • F. Bernard • D. Cremers
Implicit Neural Surface Deformation with Explicit Velocity Fields.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL GitHub

M. Sabanayagam • L. Gosch • S. Günnemann • D. Ghoshdastidar
Exact Certification of (Graph) Neural Networks Against Label Poisoning.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. Spotlight Presentation. URL GitHub

Y. Shehata • B. Holzschuh • N. Thuerey
Improved Sampling Of Diffusion Models In Fluid Dynamics With Tweedie's Formula.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

M. Schröder • V. Melnychuk • S. Feuerriegel
Differentially private learners for heterogeneous treatment effects.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

E. Sommer • J. Robnik • G. Nozadze • U. Seljak • D. Rügamer
Microcanonical Langevin Ensembles: Advancing the Sampling of Bayesian Neural Networks.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

B. Tahmasebi • S. Jegelka
Generalization Bounds for Canonicalization: A Comparative Study with Group Averaging.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

T. Uscidda • L. Eyring • K. Roth • F. J. Theis • Z. Akata • M. Cuturi
Disentangled Representation Learning with the Gromov-Monge Gap.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

X. Wang • C. Hu • P. Röttger • B. Plank
Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

Y. Wang • M. Schröder • D. Frauen • J. Schweisthal • K. Heß • S. Feuerriegel
Constructing Confidence Intervals for Average Treatment Effects from Multiple Datasets.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

M. Weber • L. Yu • Q. Yu • X. Deng • X. Shen • D. Cremers • L.-C. Chen
MaskBit: Embedding-free Image Generation via Bit Tokens.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. Journal Track. URL URL

Q. Zhang • Y. Wang • J. Cui • X. Pan • Q. Lei • S. Jegelka • Y. Wang
Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

Workshops (17 papers)

C. Bülte • S. Maskey • P. Scholl • J. von Berg • G. Kutyniok
Graph Neural Networks for Enhancing Ensemble Forecasts of Extreme Rainfall.
Climate Change AI @ICLR 2025 - Workshop on Tackling Climate Change with Machine Learning at the 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

T. Decker • V. Tresp • F. Buettner
Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations.
XAI4Science @ICLR 2025 - Workshop XAI4Science: From Understanding Model Behavior to Discovering New Scientific Knowledge at the 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

S. Dziadzio • V. Udandarao • K. Roth • A. Prabhu • Z. Akata • S. Albanie • M. Bethge
How to Merge Multimodal Models Over Time?
MCDC @ICLR 2025 - Workshop on Modularity for Collaborative, Decentralized, and Continual Deep Learning at the 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

K. Forster • V. Wagner • L. Keil • M. A. Müller • T. Sellhorn • S. Feuerriegel
Tracking ESG Disclosures of European Companies with Retrieval-Augmented Generation.
Climate Change AI @ICLR 2025 - Workshop on Tackling Climate Change with Machine Learning at the 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

C. Kolb • B. Bischl • D. Rügamer
Differentiable Attention Sparsity via Structured D-Gating.
SLLM @ICLR 2025 - Workshop on Sparsity in LLMs at the 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

J. Kobialka • E. Sommer • J. Kwon • D. Dold • D. Rügamer
Approximate Posteriors in Neural Networks: A Sampling Perspective.
FPI @ICLR 2025 - Workshop on Frontiers in Probabilistic Inference: Learning meets Sampling at the 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. Spotlight Presentation. URL

C. Koke • Y. Shen • A. Saroha • M. Eisenberger • B. Rieck • M. M. Bronstein • D. Cremers
Graph Networks struggle with variable Scale.
ICBINB @ICLR 2025 - Workshop I Can’t Believe It’s Not Better: Challenges in Applied Deep Learning at the 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

C. Koke • Y. Shen • A. Saroha • M. Eisenberger • B. Rieck • M. M. Bronstein • D. Cremers
On Incorporating Scale into Graph Networks.
MLMP @ICLR 2025 - Workshop on Machine Learning Multiscale Processes at the 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. Best Paper Award. URL

C. Koke • D. Schnaus • Y. Shen • A. Saroha • M. Eisenberger • B. Rieck • M. M. Bronstein • D. Cremers
On multi-scale Graph Representation Learning.
LMRL @ICLR 2025 - Workshop on Learning Meaningful Representations of Life at the 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

Z. Li • S. Yan • Y. Ma • Y. Li • X. Lyu • M. Schubert
Beyond Single-Step: Multi-Frame Action-Conditiones Video Generation for Reinforcement Learning Environments.
World Models @ICLR 2025 - Workshop on World Models: Understanding, Modelling and Scaling at the 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

A. Modarressi • A. Köksal • A. Imani • M. Fayyaz • H. Schütze
MemLLM: Finetuning LLMs to Use An Explicit Read-Write Memory.
NFAM @ICLR 2025 - Workshop on New Frontiers in Associative Memories at the 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

L. Meynent • I. Melev • K. Schürholt • G. Kauermann • D. Borth
Structure Is Not Enough: Leveraging Behavior for Neural Network Weight Reconstruction.
Weight Space Learning @ICLR 2025 - Workshop on Weight Space Learning at the 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. arXiv URL

T. Nagler • D. Rügamer
Uncertainty Quantification for Prior-Fitted Networks using Martingale Posteriors.
FPI @ICLR 2025 - Workshop on Frontiers in Probabilistic Inference: Learning meets Sampling at the 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. arXiv URL

A. Reuter • T. G. J. Rudner • V. Fortuin • D. Rügamer
Can Transformers Learn Full Bayesian Inference in Context?
FPI @ICLR 2025 - Workshop on Frontiers in Probabilistic Inference: Learning meets Sampling at the 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. arXiv URL

A. Reuter • T. G. J. Rudner • V. Fortuin • D. Rügamer
Can Transformers Learn Full Bayesian Inference in Context?
SynthData @ICLR 2025 - Workshop SynthData: Will Synthetic Data Finally Solve the Data Access Problem? at the 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

D. Rundel • E. Sommer • B. Bischl • D. Rügamer • M. Feurer
Efficiently Warmstarting MCMC for BNNs.
FPI @ICLR 2025 - Workshop on Frontiers in Probabilistic Inference: Learning meets Sampling at the 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL

L. Wimmer • B. Bischl • L. Bothmann
Trust Me, I Know the Way: Predictive Uncertainty in the Presence of Shortcut Learning.
SCSL @ICLR 2025 - Workshop on Spurious Correlation and Shortcut Learning: Foundations and Solutions at the 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL