Research

Combined statistical-mechanistic modeling links ion channel genes to physiology of cortical neuron types

Y Bernaerts, M Deistler, PJ Goncalves, J Beck (2023); bioRxiv (2023): 2023-03

In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation

J Bitterwolf, M Müller, M Hein (2023); arXiv preprint arXiv:2306.00826

Simulation-based inference for efficient identification of generative models in connectomics

J Boelts, R Gao, D Udvary, D Baum (2023); bioRxiv. 2023:2023-01

Predicting functional effects of ion channel variants using new phenotypic machine learning methods

CM Boßelmann (2023); PLOS Computational Biology

One bottleneck is not enough

M Bányai, CM Wu (2023)

Detecting Human-Object Contact in Images

Y Chen, SK Dwivedi, MJ Black (2023); InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023 (pp. 17100-17110)

End-to-end Autonomous Driving: Challenges and Frontiers

L Chen, P Wu, K Chitta, B Jaeger, A Geiger (2023); arXiv preprint arXiv:2306.16927

The wisdom of the coherent: Improving correspondence with coherence-weighted aggregation

RN Collins, DR Mandel, CW Karvetski, CM Wu (2023); Decision

Flow Matching for Scalable Simulation-Based Inference

M Dax, J Wildberger, SR Green (2023); arXiv preprint arXiv:2305.17161

Neural Importance Sampling for Rapid and Reliable Gravitational-Wave Inference

M Dax, SR Green, M Pürrer, J Wildberger (2023); Physical Review Letters

PlasmoFAB: a benchmark to foster machine learning for Plasmodium falciparum protein antigen candidate prediction

JC Ditz, J Wistuba (2023); Bioinformatics

Generalized Bayesian Inference for Scientific Simulators via Amortized Cost Estimation

R Gao, M Deistler, JH Macke (2023); InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

Don't trust your eyes: on the (un) reliability of feature visualizations

R Geirhos, RS Zimmermann, B Bilodeau (2023); arXiv preprint arXiv:2306.04719

Environmental variability and network structure determine the optimal plasticity mechanisms in embodied agents

E Giannakakis, S Khajehabdollahi, A Levina (2023); arXiv preprint arXiv:2303.06734

Locally adaptive cellular automata for goal-oriented self-organization

E Giannakakis, V Buendia (2023); arXiv preprint arXiv:2306.07067

Recurrent connectivity structure controls the emergence of co-tuned excitation and inhibition

E Giannakakis, O Vinogradov, V Buendia, A Levina (2023); bioRxiv. 2023:2023-02

Adversarial robustness of amortized Bayesian inference

M Glöckler, M Deistler, JH Macke (2023); arXiv preprint arXiv:2305.14984

Beyond Good Intentions: Reporting the Research Landscape of NLP for Social Good

F Gonzalez, Z Jin, B Schölkopf (2023); arXiv preprint arXiv:2305.05471

Parting with Misconceptions about Learning-based Vehicle Motion Planning

M Hallgarten, A Geiger, K Chitta (2023); arXiv preprint arXiv:2306.07962

Pre-trained perceptual features improve differentially private image generation

F Harder, DJ Sutherland (2023); Transactions on Machine Learning Research

Bayesian Numerical Integration with Neural Networks

P Hennig, FX Briol (2023); arXiv preprint arXiv:2305.13248

On the Richness of Calibration

B Höltgen, RC Williamson (2023); InProceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency

Hidden Biases of End-to-End Driving Models

B Jaeger, K Chitta, A Geiger (2023); arXiv preprint arXiv:2306.07957

Can Large Language Models Infer Causation from Correlation?

Z Jin, Z Lyu, S Poff, M Sachan, R Mihalcea (2023); arXiv preprint arXiv:2306.05836

Moûsai: Text-to-Music Generation with Long-Context Latent Diffusion

Z Jin, B Schölkopf (2023); arXiv preprint arXiv:2301.11757

Multiscale Metamorphic VAE for 3D Brain MRI Synthesis

J Kapoor, CF Baumgartner, JH Macke (2023); arXiv preprint arXiv:2305.13308

If at First You Don't Succeed, Try, Try Again: Faithful Diffusion-based Text-to-Image Generation by Selection

S Karthik, K Roth, M Mancini, Z Akata (2023); arXiv preprint arXiv:2305.13308.

Evaluating vaccine allocation strategies using simulation-assisted causal modeling

A Kekić, J Dehning, L Gresele, J von Kügelgen (2023); Patterns

Bridging the Gap between Model Explanations in Partially Annotated Multi-label Classification

Y Kim, JM Kim, C Schmid (2023); InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

Exposing and Mitigating Spurious Correlations for Cross-Modal Retrieval

JM Kim, A Koepke, C Schmid (2023); InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

Online Learning under Adversarial Nonlinear Constraints

P Kolev, G Martius, M Muehlebach (2023); arXiv preprint arXiv:2306.03655

The Geometry of Neural Nets' Parameter Spaces Under Reparametrization

A Kristiadi, F Dangel, P Hennig (2023); arXiv preprint arXiv:2302.07384

Predicting Visual Fixations

M Kümmerer, M Bethge (2023); Annual Review of Vision Science

Connectome-constrained deep mechanistic networks predict neural responses across the fly visual system at single-neuron resolution

JK Lappalainen, S Prakhya, M McGill (2023); bioRxiv. 2023:2023-03

Control-nerf: Editable feature volumes for scene rendering and manipulation

V Lazova, V Guzov, K Olszewski (2023); InProceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision 2023 (pp. 4340-4350)

Learning agile skills via adversarial imitation of rough partial demonstrations

C Li, M Vlastelica, S Blaes, J Frey (2023); InConference on Robot Learning 2023 Mar 6 (pp. 342-352)

Versatile skill control via self-supervised adversarial imitation of unlabeled mixed motions

C Li, S Blaes, P Kolev, M Vlastelica (2023); In2023 IEEE International Conference on Robotics and Automation (ICRA)

Generalizing and decoupling neural collapse via hyperspherical uniformity gap

W Liu, L Yu, A Weller, B Schölkopf (2023); arXiv preprint arXiv:2303.06484

Information theoretic measures of causal influences during transient neural events

NK Logothetis, M Besserve (2023); Frontiers in Network Physiology. 2023 May 31;3:1085347

Psychologically-Inspired Causal Prompts

Z Lyu, Z Jin, J Mattern, R Mihalcea, M Sachan (2023); arXiv preprint arXiv:2305.01764

Voices of her: Analyzing gender differences in the AI publication world

Z Lyu, K Zhang, B Schoelkopf (2023); arXiv preprint arXiv:2305.14597

CANDID: Correspondence AligNment for Deep-burst Image Denoising

A Mallick, H Lensch (2023); arXiv preprint arXiv:2306.09887

HARD: Hard Augmentations for Robust Distillation

AF Nix, MF Burg, FH Sinz (2023); arXiv preprint arXiv:2305.14890. 2023 May 24

Trained recurrent neural networks develop phase-locked limit cycles in a working memory task

M Pals, JH Macke, O Barak (2023); bioRxiv. 2023:2023-04

Object pop-up: Can we infer 3D objects and their poses from human interactions alone?

IA Petrov, R Marin, J Chibane (2023); InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023 (pp. 4726-4736)

COmic: convolutional kernel networks for interpretable end-to-end learning on (multi-) omics data

N Pfeifer (2023); Bioinformatics. 2023 Jun 1;39(Supplement_1):i76-85

All Roads Lead to Rome? Exploring the Invariance of Transformers' Representations

Y Ren, Q Guo, Z Jin, S Ravfogel, M Sachan (2023); arXiv preprint arXiv:2305.14555

Waffling around for Performance: Visual Classification with Random Words and Broad Concepts

K Roth, JM Kim, A Koepke, O Vinyals, C Schmid (2023); arXiv preprint arXiv:2306.07282

Reinforcement Learning with Simple Sequence Priors

T Saanum, N Éltető, M Binz (2023); arXiv preprint arXiv:2305.17109

Uncovering the organization of neural circuits with generalized phase locking analysis

S Safavi, TI Panagiotaropoulos, V Kapoor (2023); PLOS Computational Biology

In-Context Impersonation Reveals Large Language Models' Strengths and Biases

L Salewski, S Alaniz, I Rio-Torto, E Schulz (2023); arXiv preprint arXiv:2305.14930

The Rank-Reduced Kalman Filter: Approximate Dynamical-Low-Rank Filtering In High Dimensions

J Schmidt, P Hennig, F Tronarp (2023); arXiv preprint arXiv:2306.07774

Simultaneous identification of models and parameters of scientific simulators

C Schröder, JH Macke (2023); arXiv preprint arXiv:2305.15174

Decoding Attention from Gaze: A Benchmark Dataset and End-to-End Models

S Singh (2023); InAnnual Conference on Neural Information Processing Systems 2023 Apr 3 (pp. 219-240)

Nonparametric Indirect Active Learning

S Singh (2023); InInternational Conference on Artificial Intelligence and Statistics 2023 Apr 11 (pp. 2515-2541)

Automatic discovery and description of human planning strategies

J Skirzyński, YR Jain, F Lieder (2023); Behavior Research Methods

Constructing and deconstructing bias: modeling privilege and mentorship in agent-based simulations

AL Smith, K Keplinger, CM Wu (2023); arXiv preprint arXiv:2304.02351

Cystoscopic depth estimation using gated adversarial domain adaptation

P Somers, S Holdenried (2023); Biomedical Engineering Letters

The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks

A Spieler, N Rahaman, G Martius, B Schölkopf, A Levina (2023); International Conference on Learning Representations (ICLR)

normflows: A PyTorch Package for Normalizing Flows

V Stimper, D Liu, A Campbell, L Ryll (2023); arXiv preprint arXiv:2302.12014

Social learning with a grain of salt

W Toyokawa, W Gaissmaier, CM Wu (2023); psyArXiv preprint

3D human pose estimation via intuitive physics

S Tripathi, CHP Huang (2023); InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023 (pp. 4713-4725)

Model-Based Assimilation Transmits and Recombines World Models

R Uchiyama, C Tennie, CM Wu (2023); psyArXiv preprint

ProbVLM: Probabilistic Adapter for Frozen Vison-Language Models

U Upadhyay, M Mancini, Z Akata (2023); arXiv preprint arXiv:2307.00398

Adapting to noise distribution shifts in flow-based gravitational-wave inference

J Wildberger, M Dax, SR Green, M Pürrer (2023); Physical Review D. 2023 Apr 26;107(8):084046

Learning with Muscles: Benefits for Data-Efficiency and Robustness in Anthropomorphic Tasks

I Wochner, P Schumacher, G Martius (2023); InConference on Robot Learning 2023 Mar 6 (pp. 1178-1188)

Biases towards compositionally simpler hypotheses are robust and unaffected by learning

CM Wu (2023)

Compositionality under time pressure

CM Wu (2023); psyArXiv preprint

Learning progress and uncompensated rewards as motivational drivers of engagement

CM Wu, E Schulz (2023); InConference on Cognitive Computational Neuroscience

Playing to win or playing to learn? Human performance in a social card game task

CM Wu (2023)

Reward morphs non-spatial cognitive maps in humans

CM Wu, NW Schuck (2023)

The Dynamic and Structured Nature of Learning and Memory

CM Wu (2023)

Visual-spatial dynamics drive adaptive social learning in immersive environments

CM Wu, D Deffner, B Meder (2023); bioRxiv. 2023:2023-06

Trading Information between Latents in Hierarchical Variational Autoencoders

TZ Xiao (2023); arXiv preprint arXiv:2302.04855

Visibility aware human-object interaction tracking from single rgb camera

X Xie, BL Bhatnagar (2023); InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

Selective memory for reward-relevant features is modulated by expertise during reward learning

Y Xiong, M Bányai (2023); InConference on Cognitive Computational Neuroscience

High-Fidelity Clothed Avatar Reconstruction from a Single Image

Y Xiu, H Yi, X Liu (2023); InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

Generating holistic 3d human motion from speech

H Yi, Q Cao, Y Wen (2023); InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

MIME: Human-Aware 3D Scene Generation

H Yi, CHP Huang, S Tripathi (2023); InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities

A Zadaianchuk, M Seitzer, G Martius (2023); arXiv preprint arXiv:2306.04829

Resampling Gradients Vanish in Differentiable Sequential Monte Carlo Samplers

J Zenn (2023); arXiv preprint arXiv:2304.14390

Intrinsic timescales in the visual cortex change with selective attention and reflect spatial connectivity

R Zeraati, YL Shi, NA Steinmetz (2023); Nature communications

Provably Learning Object-Centric Representations

RS Zimmermann, Y Sharma (2023); arXiv preprint arXiv:2305.14229

Learning Random Feature Dynamics for Uncertainty Quantification

D Agudelo-Espana, N Yassine, B Schölkopf, J Zhu (2022);IEEE 61st Conference on Decision and Control (CDC)

Diffusion visual counterfactual explanations

M Augustin, V Boreiko, F Croce, M Hein (2022); Advances in Neural Information Processing Systems (NeurIPS)

Clinical validation of saliency maps for understanding deep neural networks in ophthalmology

MS Ayhan, LB Kümmerle, L Kühlewein, W Inhoffen, G Aliyeva, F Ziemssen, P Berens (2022); Medical Image Analysis

Interpretable Detection of Epiretinal Membrane from Optical Coherence Tomography with Deep Neural Networks

MS Ayhan, J Neubauer, MM Uzel, F Gelisken, P Berens (2022); medRxiv

Understanding Entropy Coding With Asymmetric Numeral Systems (ANS): a Statistician's Perspective

R Bamler (2022); arXiv preprint arXiv:2201.01741

Dynamical systems as a level of cognitive analysis of multi-agent learning

W Barfuss (2022); From Cells to Societies: Collective Learning across Scales

Non-linear dynamics of collective learning in uncertain environments

W Barfuss, R Across (2022); Neural Computing and Applications

Modeling the effects of environmental and perceptual uncertainty using deterministic reinforcement learning dynamics with partial observability

W Barfuss, RP Mann (2022); Physical Review E

Efficient identification of informative features in simulation-based inference

J Beck, M Deistler, Y Bernaerts, JH Macke, P Berens (2022); Advances in Neural Information Processing Systems (NeurIPS)

Boosting human decision-making with AI-generated decision aids

F Becker, J Skirzyński, B van Opheusden, F Lieder (2022); Computational Brain and Behavior

Retinal horizontal cells use different synaptic sites for global feedforward and local feedback signaling

C Behrens, SC Yadav, MM Korympidou, Y Zhang, S Haverkamp, S Irsen, A Schaedler, X Lu, Z, Liu, J Lause, F St-Pierre, K Franke, A Vlasits, K Dedek, RG Smith, T Euler, P Berens, T Schubert (2022); Current Biology

Cause-effect inference through spectral independence in linear dynamical systems: theoretical foundations

M Besserve, N Shajarisales, D Janzing, B Schölkopf, C Uhler, K Zhang (2022) ; Conference on Causal Learning and Reasoning

Learning soft interventions in complex equilibrium systems

M Besserve, B Schölkopf (2022); Proceedings of the 38th Conference on Uncertainty in Artificial Intelligence (UAI)

Behave: Dataset and method for tracking human object interactions

BL Bhatnagar, X Xie, IA Petrov, C Sminchisescu, C Theobalt, G Pons-Moll (2022); IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Breaking down out-of-distribution detection: Many methods based on ood training data estimate a combination of the same core quantities

J Bitterwolf, A Meinke, M Augustin, M Hein (2022); International Conference on Machine Learning (ICML)

Classifiers Should Do Well Even on Their Worst Classes

J Bitterwolf, A Meinke, V Boreiko, M Hein (2022); ICML 2022 Shift Happens Workshop

Flexible and efficient simulation-based inference for models of decision-making

J Boelts, JM Lueckmann, R Gao, JH Macke (2022), Elife

A Bandit Model for Human-Machine Decision Making with Private Information and Opacity

S Bordt, U Von Luxburg (2022); Proceedings of the 25th International Conference on Artificial Intelligence and Statistics (AISTATS)

Post-hoc explanations fail to achieve their purpose in adversarial contexts

S Bordt, M Finck, E Raidl, U von Luxburg (2022); FAccT '22: 2022 ACM Conference on Fairness, Accountability, and Transparency

Visual explanations for the detection of diabetic retinopathy from retinal fundus images

V Boreiko, I Ilanchezian, MS Ayhan, S Müller, LM Koch, H Faber, P Berens, M Hein, (2022) ; Medical Image Computing and Computer Assisted Intervention

Pick-and-mix information operators for probabilistic ODE solvers

N Bosch, F Tronarp, P Hennig (2022); Proceedings of the 25th International Conference on Artificial Intelligence and Statistics (AISTATS)

Samurai: Shape and material from unconstrained real-world arbitrary image collections

M Boss, A Engelhardt, A Kar, Y Li, D Sun, JT Barron, HPA Lensch, V Jampani (2022); Advances in Neural Information Processing Systems (NeurIPS);

Attraction-Repulsion Spectrum in Neighbor Embeddings

JN Böhm, P Berens, D Kobak (2022); Journal of Machine Learning Research

Function Classes for Identifiable Nonlinear Independent Component Analysis

S Buchholz, M Besserve, B Schölkopf (2022); Advances in Neural Information Processing Systems (NeurIPS)

Diverse task-driven modeling of macaque V4 reveals functional specialization towards semantic tasks

SA Cadena, KF Willeke, K Restivo, G Denfield, FH Sinz, M Bethge, AS Tolias, AS Ecker (2022); bioRxiv

Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation using Bounding Boxes

J Chibane, F Engelmann, T Anh Tran, G Pons-Moll (2022); Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science

TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving

Chitta, A Prakash, B Jaeger, Z Yu, K Renz, A Geiger (2022); Pattern Analysis and Machine Intelligence

Asymmetric reinforcement learning facilitates human inference of transitive relations

S Ciranka, J Linde, I Padezhki, C Wicharz, CM Wu, B Spitzer (2022) ; Nature Human Behaviour

Learned vertex descent: a new direction for 3D human model fitting

E Corona, G Pons-Moll, G Alenya, F Moreno-Noguer (2022) ; Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science

Adversarial Robustness against Multiple and Single -Threat Models via Quick Fine-Tuning of Robust Classifiers

F Croce, M Hein (2022); International Conference on Machine Learning (ICML)

On the interplay of adversarial robustness and architecture components: patches, convolution and attention

F Croce, M Hein (2022) ; arXiv preprint arXiv:2209.06953

Sparse-rs: a versatile framework for query-efficient sparse black-box adversarial attacks

F Croce, M Andriushchenko, ND Singh, N Flammarion, M Hein (2022); Proceedings of the 36th AAAI Conference on Artificial Intelligence

Contrastive learning unifies -SNE and UMAP

S Damrich, JN Böhm, FA Hamprecht, D Kobak (2022); preprint arXiv

Energy-efficient network activity from disparate circuit parameters

M Deistler, JH Macke, PJ Goncalves (2022); Proceedings of the National Academy of Sciences of the United States of America

Truncated proposals for scalable and hassle-free simulation-based inference

M Deistler, PJ Goncalves, JH Macke (2022); Advances in Neural Information Processing Systems (NeurIPS)

The Drive for Knowledge: The Science of Human Information Seeking

IC Dezza, E Schulz, CM Wu (2022); Cambridge University Press

Probable Domain Generalization via Quantile Risk Minimization

C Eastwood, A Robey, Singh, J von Kügelgen, H Hassani, GJ Pappas, B Schölkopf (2022); Advances in Neural Information Processing Systems (NeurIPS)

Ocular changes as a diagnostic tool for malaria

H Faber, P Berens, JM Rohrbach (2022); Der Ophthalmologe

Disentanglement and generalization under correlation shifts

CM Funke, P Vicol, KC Wang, M Kümmerer, R Zemel, M Bethge (2022); Conference on Lifelong Learning Agents

The bittersweet lesson: data-rich models narrow the behavioural gap to human vision

R Geirhos, K Narayanappa, B Mitzkus, T Thieringer, M Bethge, FA Wichmann, W Brendel (2022); Journal of Vision

Diverse Video Captioning by Adaptive Spatio-temporal Attention

Z Ghaderi, L Salewski, HPA Lensch (2022); German Conference on Pattern Recognition (DAGM)

Developmental changes in learning resemble stochastic optimization

AP Giron, S Ciranka, E Schulz, W van den Bos, CM Wu (2022); psyArXiv

Variational methods for simulation-based inference

M Glöckler, M Deistler, JH Macke (2022); International Conference on Learning Representations (ICLR)

Two-dimensional visualization of large document libraries using t-SNE

R González-Márquez, P Berens, D Kobak (2022); ICLR 2022 Workshop on Geometrical and Topological Representation Learning

Causal inference through the structural causal marginal problem

L Gresele, J Von Kügelgen, J Kübler, E Kirschbaum, B Schölkopf, D Janzing (2022); International Conference on Machine Learning (ICML)

Ggnn: Graph-based gpu nearest neighbor search

F Groh, L Ruppert, P Wieschollek, HPA Lensch (2022); IEEE Transactions on Big Data

Optimistic Optimization of Gaussian Process Samples

J Grosse, C Zhang, P Hennig (2022); arXiv preprint arXiv:2209.00895

Developing hierarchical anticipations via neural network-based event segmentation

C Gumbsch, M Adam, B Elsner, G Martius, M Butz (2022); IEEE International Conference on Development and Learning

Visually plausible human-object interaction capture from wearable sensors

V Guzov, T Sattler, G Pons (2022); arXiv preprint arXiv:2205.02830

King: Generating safety-critical driving scenarios for robust imitation via kinematics gradients

N Hanselmann, K Renz, K Chitta, A Bhattacharyya, A Geiger (2022); Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science

The scaling of mental computation in a sorting task

S Haridi, CM Wu, I Dasgupta, E Schulz (2022); psyArXiv

Neural Network Heuristic Functions: Taking Confidence into Account

D Heller, P Ferber, J Bitterwolf, M Hein, J Hoffmann (2022); Proceedings of the International Symposium on Combinatorial Search

Fast predictive uncertainty for classification with bayesian deep networks

M Hobbhahn, A Kristiadi, P Hennig (2022); Proceedings of the 38th Conference on Uncertainty in Artificial Intelligence (UAI 2022)

InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interaction

Y Huang, O Taheri, MJ Black, D Tzionas (2022); German Conference on Pattern Recognition (DAGM)

Logical fallacy detection

Z Jin, A Lalwani, T Vaidhya, X Shen, Y Ding, Z Lyu, M Sachan, R Mihalcea, B Schölkopf (2022); arXiv preprint

When to make exceptions: Exploring language models as accounts of human moral judgment

Z Jin, S Levine, F Gonzalez, O Kamal, M Sap, M Sachan, R Mihalcea, J Tenenbau, B Schölkopf (2022); Advances in Neural Information Processing Systems (NeurIPS)

Physical representation learning and parameter identification from video using differentiable physics

RK Kandukuri, J Achterhold, M Moeller, J Stückler (2022); International Journal of Computer Vision

Decoding internally generated transitions of conscious contents in the prefrontal cortex without subjective reports

V Kapoor, A Dwarakanath, S Safavi, J Werner, M Besserve, TI Panagiotaropoulos, NK Logothetis(2022); Nature Communications

Slangvolution: A causal analysis of semantic change and frequency dynamics in slang

D Keidar, A Opedal, Z Jin, M Sachan (2022); Proceedings ofthe 60th Annual Meeting of the Association for Computational Linguistics

Evaluating vaccine allocation strategies using simulation-assisted causal modelling

A Kekić, J Dehning, L Gresele, J von Kügelgen, V Priesemann, B Schölkopf (2022); arXiv preprint

When to be critical? Performance and evolvability in different regimes of neural Ising agents

S Khajehabdollahi, J Prosi, E Giannakakis, G Martius, A Levina (2022) Artificial Life

A hierarchical model of attention over time

J Kim, S Singh, D Yurovsky, A Fisher, ED Thiessen, (2022); Proceedings of the 44th Annual Conference of the Cognitive ScienceSociety

Relating graph auto-encoders to linear models

S Klepper, U von Luxburg (2022); arXiv preprint arXiv:2211.01858

Hidden in plain sight: Subgroup shifts escape ood detection

LM Koch, CM Schürch, A Gretton, P Berens (2022); International Conference on Medical Imaging with Deep Learning

Audio retrieval with natural language queries: A benchmark study

AS Koepke, AM Oncescu, J Henriques, Z Akata, S Albanie (2022); IEEE Transactions on Multimedia

Functional Generalized Empirical Likelihood Estimation for Conditional Moment Restrictions

H Kremer, JJ Zhu, K Muandet, B Schölkopf (2022); International Conference on Machine Learning (ICML)

Being a bit frequentist improves Bayesian neural networks

A Kristiadi, M Hein, P Hennig (2022); Proceedings of the 25th International Conference on Artificial Intelligence and Statistics (AISTATS)

Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networks

A Kristiadi, R Eschenhagen, P Hennig (2022); Advances in Neural Information Processing Systems (NeurIPS)

Probabilistic ODE solutions in millions of dimensions

N Krämer, N Bosch, J Schmidt, P Hennig (2022); International Conference on Machine Learning (ICML)

Probabilistic numerical method of lines for time-dependent partial differential equations

N Krämer, J Schmidt, P Hennig (2022); Proceedings of the 25th International Conference on Artificial Intelligence and Statistics (AISTATS)

A witness two-sample test

JM Kübler, W Jitkrittum, B Schölkopf, K Muandet (2022); Proceedings of the 25th International Conference on Artificial Intelligence and Statistics (AISTATS)

AutoML Two-Sample Test

JM Kübler, V Stimper, S Buchholz, K Muandet, B Schölkopf (2022); Advances in Neural Information Processing Systems (NeurIPS)

Backtracking Counterfactuals

J von Kügelgen, A Mohamed, S Beckers (2022); arXiv preprint arXiv:2211.00472

On the fairness of causal algorithmic recourse

J von Kügelgen, AH Karimi, U Bhatt, I Valera, A Weller, B Schölkopf (2022); Proceedings of the 36th AAAI Conference on Artificial Intelligence

Deepgaze III: Modeling free-viewing human scanpaths with deep learning

M Kümmerer, M Bethge, TSA Wallis (2022); Journal of Vision

Using the DeepGaze III model to decompose spatial and dynamic contributions to fixation placement over time

M Kümmerer, TSA Wallis, M Bethge (2022); Journal of Vision

Disentanglement via mechanism sparsity regularization: A new principle for nonlinear ICA

S Lachapelle, P Rodriguez, Y Sharma, KE Everett, R Le Priol, A Lacoste, S Lacoste-Julien (2022)

Predicting the Force Map of an ERT-Based Tactile Sensor Using Simulation and Deep Networks

H Lee, H Sun, H Park, G Serhat, B Javot, G Martius, KJ Kuchenbecker (2022); IEEE Transactions on Automation Science and Engineering

Exploring the Latent Space of Autoencoders with Interventional Assays

F Leeb, S Bauer, M Besserve, B Schölkopf (2022); Advances in Neural Information Processing Systems (NeurIPS)

KITTI-360: A novel dataset and benchmarks for urban scene understanding in 2d and 3d

Y Liao, J Xie, A Geiger (2022); IEEE Transactions on Pattern Analysis and Machine Intelligence

Phase of firing does not reflect temporal order in sequence memory of humans and recurrent neural networks

S Liebe, J Niediek, M Pals, TP Reber, J Faber, J Bostroem, CE Elger, JH Macke, F Mormann (2022); bioRxiv

Can Large Language Models Distinguish Cause from Effect?

Z Lyu, Z Jin, R Mihalcea, M Sachan, B Schölkopf (2022); UAI 2022 Workshop on Causal Representation Learning

Approximate Bayesian Neural Operators: Uncertainty Quantification for Parametric PDEs

E Magnani, N Krämer, R Eschenhagen, L Rosasco, P Hennig (2022); arXiv preprint

Local Attention Guided Joint Depth Upsampling

A Mallick, A Engelhardt, R Braun, HPA Lensch (2022); In J. Bender, M. Botsch, and D.A. Keim (Eds.), Vision, Modeling, and Visualization. The Eurographics Association.

Differentially Private Language Models for Secure Data Sharing

J Mattern, Z Jin, B Weggenmann, B Schoelkopf, M Sachan (2022); arXiv preprint

Leveraging machine learning to automatically derive robust decision strategies from imperfect knowledge of the real world;

A Mehta, YR Jain, A Kemtur, J Stojcheski, S Consul, M Tosic, F Lieder (2022); Computational Brain and Behavior

Provably Adversarially Robust Detection of Out-of-distribution Data (almost) for free

A Meinke, J Bitterwolf, M Hein (2022); Advances in Neural Information Processing Systems (NeurIPS)

Audio-visual generalised zero-shot learning with cross-modal attention and language

OB Mercea, L Riesch, AS Koepke, Z Akata (2022); Computer Vision – ECCV 2022. Lecture Notes in Computer Science

Temporal and cross-modal attention for audio-visual zero-shot learning;

OB Mercea, T Hummel, AS Koepke, Z Akata (2022); Computer Vision – ECCV 2022. Lecture Notes in Computer Science

Visual Grounding of Inter-lingual Word-Embeddings

W Mohammed, H Shahmohammadi, HPA Lensch, H, Baayen (2022); Proceedings of the Workshop on Unimodal and Multimodal Induction of Linguistic Structures

Impossibility of Collective Intelligence

K Muandet (2022); arXiv preprint arXiv:2206.02786

A Generative Model Reveals the Influence of Patient Attributes on Fundus Images

S Müller, LM Koch, HPA Lensch, P Berens (2022); Conference on Medical Imaging with Deep Learning

How Adversarial Robustness Transfers from Pre-training to Downstream Tasks

LF Nern, Y Sharma (2022); arXiv preprint arXiv:2208.03835

Original or translated? A causal analysis of the impact of translationese on machine translation performance

J Ni, Z Jin, M Freitag, M Sachan, B Schölkopf (2022); Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Leading by example: Guiding knowledge transfer with adversarial data augmentation

A Nix, MF Burg, FH Sinz (2022); NeurIPS 2022 Workshop on Synthetic Data for Empowering ML Research

Probabilistic solvers enable a straight-forward exploration of numerical uncertainty in neuroscience models

J Oesterle, N Krämer, P Hennig, P Berens (2022); Journal of Computational Neuroscience

Direct advantage estimation

HR Pan, N Gürtler, A Neitz, B Schölkopf (2022); Advances in Neural Information Processing Systems (NeurIPS)

Semantic object-scene inconsistencies affect eye movements, but not in the way predicted by contextualized meaning maps

MA Pedziwiatr, M Kümmerer, TSA Wallis, M Bethge, C Teufel (2022); Journal of Vision

Causal discovery in heterogeneous environments under the sparse mechanism shift hypothesis

R Perry, J Von Kügelgen, B Schölkopf (2022); arXiv preprint arXiv:2206.02013

Physics-Informed Gaussian Process Regression Generalizes Linear PDE Solvers

M Pförtner, I Steinwart, P Hennig, J Wenger (2022); arXiv preprint

CCC: Continuously Changing Corruptions

O Press, S Schneider, M Kümmerer, M Bethge (2022); In ICML 2022 Shift Happens Workshop

Learning counterfactually invariant predictors

F Quinzan, C Casolo, K Muandet, Y Luo, N Kilbertus (2022); arXiv preprint

GATSBI: Generative adversarial training for simulation-based inference;

P Ramesh, JM Lueckmann, J Boelts, A Tejero-Cantero, DS Greenberg, PJ Gonçalves, JH Macke, (2022); International Conference on Learning Representations (ICLR)

Don't Throw it Away! The Utility of Unlabeled Data in Fair Decision Making

M Rateike, A Majumdar, O Mineeva, KP Gummadi, I Valera (2022); FAccT '22: 2022 ACM Conference on Fairness, Accountability, and Transparency

Embrace the Gap: VAEs Perform Independent Mechanism Analysis

P Reizinger, L Gresele, J Brady, J von Kügelgen, D Zietlow, B Schölkopf, G Martius, W Brendel, M Besserve (2022); Advances in Neural Information Processing Systems (NeurIPS)

Discovering inductive bias with Gibbs priors: A diagnostic tool for approximate Bayesian inference

L Rendsburg, A Kristiadi, P Hennig, U von Luxburg (2022); Proceedings of the 25th International Conference on Artificial Intelligence and Statistics (AISTATS)

PlanT: Explainable Planning Transformers via Object-Level Representations

K Renz, K Chitta, OB Mercea, AS Koepke, Z Akata, A Geiger (2022); Conference on Robot Learning

A Sequential Group VAE for Robot Learning of Haptic Representations

BA Richardson, Y Vardar, C Wallraven, KJ Kuchenbecker (2022); IEEE Transactions on Haptics

Learning to Feel Textures: Predicting Perceptual Similarities From Unconstrained Finger-Surface Interactions

BA Richardson, KJ Kuchenbecker, G Martius (2022); Conference on Robot Learning

ImageNet-D: A new challenging robustness dataset inspired by domain adaptation

E Rusak, S Schneider, PV Gehler, O Bringmann, W Brendel, M Bethge (2022); ICML 2022 Shift Happens Workshop

Clevr-x: A visual reasoning dataset for natural language explanations

L Salewski, AS Koepke, HPA Lensch, Z Akata (2022); xxAI - Beyond Explainable AI. xxAI 2020. Lecture Notes in Computer Science

Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation

C Sancaktar, S Blaes, G Martius (2022); Advances in Neural Information Processing Systems (NeurIPS)

VACA: Designing Variational Graph Autoencoders for Causal Queries

P Sánchez-Martin, M Rateike, I Valera (2022); Proceedings of the 36th AAAI Conference on Artificial Intelligence

Dep-rl: Embodied exploration for reinforcement learning in overactuated and musculoskeletal systems

P Schumacher, D Häufle, D Büchler, S Schmitt, G Martius (2022); arXiv preprint

Voxgraf: Fast 3d-aware image synthesis with sparse voxel grids

K Schwarz, A Sauer, M Niemeyer, Y Liao, A Geiger (2022); Advances in Neural Information Processing Systems (NeurIPS)

DeepGaze vs SceneWalk: what can DNNs and biological scan path models teach each other?

L Schwetlick, M Kümmerer, R Engbert, M Bethge (2022); Journal of Vision

On the pitfalls of heteroscedastic uncertainty estimation with probabilistic neural networks

M Seitzer, A Tavakoli, D Antic, G Martius (2022); International Conference on Learning Representations (ICLR)

Language with vision: a study on grounded word and sentence embeddings

H Shahmohammadi, M Heitmeier, E Shafaei-Bajestan, HPA Lensch, H Baayen (2022); arXiv preprint

Visual grounding of abstract and concrete words: A response to Günther et al.(2020)

H Shahmohammadi, M Heitmeier, E Shafaei-Bajestan, HPA Lensch, H Baayen (2022); In xxAI-Beyond Explainable AI: International Workshop, Held in Conjunction with ICML 2020, July 18, 2020, Vienna, Austria, Revised and Extended Papers (pp. 69-88)

Pixel-level Correspondence for Self-Supervised Learning from Video

Y Sharma, Y Zhu, C Russell, T Brox (2022); First Workshop of Pre-training: Perspectives, Pitfalls, and Paths Forward at ICML 2022

Optimal Binary Classification Beyond Accuracy

S Singh, JT Khim (2022); Advances in Neural Information Processing Systems (NeurIPS)

A Silicon Valley love triangle: Hiring algorithms, pseudo-science, and the quest for auditability

M Sloane, E Moss, R Chowdhury (2022); Patterns

German AI Start-Ups and “AI Ethics”: Using A Social Practice Lens for Assessing and Implementing Socio-Technical Innovation

M Sloane, J Zakrzewski (2022); FAccT '22: 2022 ACM Conference on Fairness, Accountability, and Transparency

Participation is not a design fix for machine learning

M Sloane, E Moss, O Awomolo, L Forlano (2022); Conference on Equity and Access in Algorithms, Mechanisms, and Optimization

Causal Feature Selection via Orthogonal Search

A Soleymani, R Anant, S Bauer, B Schölkopf, M Besserve (2022); Transactions on Machine Learning Research

Resampling base distributions of normalizing flows

V Stimper, B Schölkopf, JM Hernandez-Lobato (2022); Proceedings of the 25th International Conference on Artificial Intelligence and Statistics (AISTATS)

A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models

A Stolfo, Z Jin, K Shridhar, B Schölkopf, M Sachan (2022); arXiv preprint

A soft thumb-sized vision-based sensor with accurate all-round force perception

H Sun, KJ Kuchenbecker, G Martius (2022); Nature Machine Intelligence

Guiding the design of superresolution tactile skins with taxel value isolines theory

H Sun, G Martius (2022); Science Robotics

Common fate based object learning in machines and humans

M Tangemann, M Kümmerer, TSA Wallis, M Bethge (2022); Journal of Vision

Late-Phase Second-Order Training; Has it Trained Yet?

L Tatzel, P Hennig, F Schneider (2022); NeurIPS 2022 Workshop

Pose-ndf: Modeling human pose manifolds with neural distance fields

G Tiwari, D Antić, JE Lenssen, N Sarafianos, T Tung, G Pons-Moll (2022) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science

Active Bayesian Causal Inference

C Toth, L Lorch, C Knoll, A Krause, F Pernkopf, R Peharz, J von Kügelgen (2022); Advances in Neural Information Processing Systems (NeurIPS)

Fenrir: Physics-Enhanced Regression for Initial Value Problems

F Tronarp, N Bosch, P Hennig (2022)International Conference on Machine Learning (ICML)

Orthonormal Expansions for Translation-Invariant Kernels

F Tronarp, T Karvonen (2022) Gaze Meets ML Workshop in conjunction with NeurIPS 2022

Digital twin reveals combinatorial code of non-linear computations in the mouse primary visual cortex

I Ustyuzhaninov, MF Burg, SA Cadena, J Fu, T Muhammad, K Ponder, E Froudarakis, Z Ding, M Bethge, AS Tolias, AS Ecker (2022); bioRxiv

Representational exchange in social learning: Blurring the lines between the ritual and instrumental

N Vélez, CM Wu, FA Cushman (2022); Behavioral and Brain Sciences

Interpolation and Regularization for Causal Learning

LC Vankadara, L Rendsburg, U von Luxburg, D Ghoshdastidar (2022); Advances in Neural Information Processing Systems (NeurIPS)

Provably Adversarially Robust Nearest Prototype Classifiers

V Voráček, M Hein (2022)International Conference on Machine Learning (ICML)

Neural Attentive Circuits

M Weiss, N Rahaman, F Locatello, C Pal, Y Bengio, B Schölkopf, N Ballas, LE Li (2022); Advances in Neural Information Processing Systems (NeurIPS)

Posterior and Computational Uncertainty in Gaussian Processes

J Wenger, G Pleiss, M Pförtner, P Hennig, JP Cunningham (2022); Advances in Neural Information Processing Systems (NeurIPS)

reconditioning for scalable Gaussian process hyperparameter optimization

J Wenger, G Pleiss, P Hennig, JP Cunningham, JR Gardner (2022); International Conference on Machine Learning (ICML)

Uncertainty in equation learning

M Werner, A Junginger, P Hennig, G Martius (2022); Proceedings of the 2022 Genetic and Evolutionary Computation Conference

The Sensorium competition on predicting large-scale mouse primary visual cortex activity

KF Willeke, PG Fahey, M Bashiri, L Pede, MF Burg, C Blessing, SA Cadena, Z Ding, KK Lurz, K Ponder, R Muhammad, SS Patel, AS Ecker, AS Tolias, FH Sinz (2022); arXiv preprint

Representational Exchange in Human Social Learning

CM Wu, N Vélez, FA Cushman (2022); In I. C. Dezza, E. Schulz, and C. M. Wu (Eds.), The Drive for Knowledge: The Science of Human Information-Seeking. Cambridge: Cambridge University Press

Time pressure changes how people explore and respond to uncertainty

CM Wu, E Schulz, TJ Pleskac, M Speekenbrink (2022); Scientific reports

Any-Shot GIN: Generalizing implicit networks for reconstructing novel classes

Y Xian, J Chibane, BL Bhatnagar, B Schiele, Z Akata, G Pons-Moll (2022); International Conference on 3D Vision (3DV)

Chore: Contact, human and object reconstruction from a single rgb image

X Xie, BL Bhatnagar, G Pons (2022); Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science

Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation

M Yatsura, K Sakmann, NG Hua, M Hein, JH Metzen (2022); arXiv preprint

Human-aware object placement for visual environment reconstruction

H Yi, CHP Huang, D Tzionas, M Kocabas, M Hassan, S Tang, J Thies, MJ Black (2022); IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

A flexible Bayesian framework for unbiased estimation of timescales

R Zeraati, TA Engel, A Levina (2022); Nature Computational Science

Topology-dependent coalescence controls scaling exponents in finite networks

R Zeraati, V Buendía, TA Engel, A Levina (2022); arXiv preprint

Couch: towards controllable human-chair interactions

X Zhang, BL Bhatnagar, S Starke, V Guzov, G Pons-Moll (2022); Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science

Adjoint rigid transform network: Task-conditioned alignment of 3d shapes

K Zhou, BL Bhatnagar, B Schiele, G Pons-Moll (2022); International Conference on 3D Vision (3DV)

TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinement

K Zhou, BL Bhatnagar, JE Lenssen, G Pons-Moll (2022); Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science

Increasing Confidence in Adversarial Robustness Evaluations

RS Zimmermann, W Brendel, F Tramer, N Carlini (2022); Advances in Neural Information Processing Systems (NeurIPS)

Research

Playing repeated games with Large Language Models

Multitask Learning for Activity Detection in Neovascular Age-Related Macular Degeneration

Intrinsic fluctuations of reinforcement learning promote cooperation

Combined statistical-mechanistic modeling links ion channel genes to physiology of cortical neuron types

In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation

Simulation-based inference for efficient identification of generative models in connectomics

Chatgpt participates in a computer science exam

From Shapley values to generalized additive models and back

The Manifold Hypothesis for Gradient-Based Explanations

Probabilistic Exponential Integrators

Predicting functional effects of ion channel variants using new phenotypic machine learning methods

One bottleneck is not enough

Detecting Human-Object Contact in Images

End-to-end Autonomous Driving: Challenges and Frontiers

The wisdom of the coherent: Improving correspondence with coherence-weighted aggregation

Flow Matching for Scalable Simulation-Based Inference

Neural Importance Sampling for Rapid and Reliable Gravitational-Wave Inference

PlasmoFAB: a benchmark to foster machine learning for Plasmodium falciparum protein antigen candidate prediction

Generalized Bayesian Inference for Scientific Simulators via Amortized Cost Estimation

Don't trust your eyes: on the (un) reliability of feature visualizations

Environmental variability and network structure determine the optimal plasticity mechanisms in embodied agents

Locally adaptive cellular automata for goal-oriented self-organization

Recurrent connectivity structure controls the emergence of co-tuned excitation and inhibition

Adversarial robustness of amortized Bayesian inference

Beyond Good Intentions: Reporting the Research Landscape of NLP for Social Good

Parting with Misconceptions about Learning-based Vehicle Motion Planning

Pre-trained perceptual features improve differentially private image generation

Bayesian Numerical Integration with Neural Networks

On the Richness of Calibration

Hidden Biases of End-to-End Driving Models

Can Large Language Models Infer Causation from Correlation?

Moûsai: Text-to-Music Generation with Long-Context Latent Diffusion

Multiscale Metamorphic VAE for 3D Brain MRI Synthesis

If at First You Don't Succeed, Try, Try Again: Faithful Diffusion-based Text-to-Image Generation by Selection

Evaluating vaccine allocation strategies using simulation-assisted causal modeling

Bridging the Gap between Model Explanations in Partially Annotated Multi-label Classification

Exposing and Mitigating Spurious Correlations for Cross-Modal Retrieval

Online Learning under Adversarial Nonlinear Constraints

The Geometry of Neural Nets' Parameter Spaces Under Reparametrization

Predicting Visual Fixations

Connectome-constrained deep mechanistic networks predict neural responses across the fly visual system at single-neuron resolution

Control-nerf: Editable feature volumes for scene rendering and manipulation

Learning agile skills via adversarial imitation of rough partial demonstrations

Versatile skill control via self-supervised adversarial imitation of unlabeled mixed motions

Generalizing and decoupling neural collapse via hyperspherical uniformity gap

Information theoretic measures of causal influences during transient neural events

Psychologically-Inspired Causal Prompts

Voices of her: Analyzing gender differences in the AI publication world

CANDID: Correspondence AligNment for Deep-burst Image Denoising

HARD: Hard Augmentations for Robust Distillation

Trained recurrent neural networks develop phase-locked limit cycles in a working memory task

Object pop-up: Can we infer 3D objects and their poses from human interactions alone?

COmic: convolutional kernel networks for interpretable end-to-end learning on (multi-) omics data

All Roads Lead to Rome? Exploring the Invariance of Transformers' Representations

Waffling around for Performance: Visual Classification with Random Words and Broad Concepts

Reinforcement Learning with Simple Sequence Priors

Uncovering the organization of neural circuits with generalized phase locking analysis

In-Context Impersonation Reveals Large Language Models' Strengths and Biases

The Rank-Reduced Kalman Filter: Approximate Dynamical-Low-Rank Filtering In High Dimensions

Simultaneous identification of models and parameters of scientific simulators

Decoding Attention from Gaze: A Benchmark Dataset and End-to-End Models

Nonparametric Indirect Active Learning

Automatic discovery and description of human planning strategies

Constructing and deconstructing bias: modeling privilege and mentorship in agent-based simulations

Cystoscopic depth estimation using gated adversarial domain adaptation

The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks

normflows: A PyTorch Package for Normalizing Flows

Social learning with a grain of salt

3D human pose estimation via intuitive physics

Model-Based Assimilation Transmits and Recombines World Models

ProbVLM: Probabilistic Adapter for Frozen Vison-Language Models

Adapting to noise distribution shifts in flow-based gravitational-wave inference

Learning with Muscles: Benefits for Data-Efficiency and Robustness in Anthropomorphic Tasks

Biases towards compositionally simpler hypotheses are robust and unaffected by learning

Compositionality under time pressure

Learning progress and uncompensated rewards as motivational drivers of engagement

Playing to win or playing to learn? Human performance in a social card game task

Reward morphs non-spatial cognitive maps in humans

The Dynamic and Structured Nature of Learning and Memory