Patrick Schramowski

PhD thesis, 2023

Exploiting Cultural Biases via Homoglyphs in Text-to-Image Synthesis.

[BibT_eX]

[DOI]

J. Artif. Intell. Res., 2023

Distilling Adversarial Prompts from Safety Benchmarks: Report for the Adversarial Nibbler Challenge.

[BibT_eX]

[DOI]

Manuel Brack

Andrés Felipe Cruz-Salinas

CoRR, 2023

Mitigating Inappropriateness in Image Generation: Can there be Value in Reflecting the World's Ugliness?

[BibT_eX]

[DOI]

CoRR, 2023

Image Classifiers Leak Sensitive Attributes About Their Classes.

[BibT_eX]

[DOI]

CoRR, 2023

Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness.

[BibT_eX]

[DOI]

CoRR, 2023

SEGA: Instructing Diffusion using Semantic Dimensions.

[BibT_eX]

[DOI]

CoRR, 2023

AtMan: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation.

[BibT_eX]

[DOI]

CoRR, 2023

ATMAN: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

SEGA: Instructing Text-to-Image Models using Semantic Guidance.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

MultiFusion: Fusing Pre-Trained Models for Multi-Lingual, Multi-Modal Image Generation.

[BibT_eX]

[DOI]

Constantin Eichenberg

Samuel Weinbach

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

ILLUME: Rationalizing Vision-Language Models through Human Interactions.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

Revision Transformers: Instructing Language Models to Change Their Values.

[BibT_eX]

[DOI]

Proceedings of the ECAI 2023 - 26th European Conference on Artificial Intelligence, September 30 - October 4, 2023, Kraków, Poland, 2023

Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Speaking Multiple Languages Affects the Moral Bias of Language Models.

[BibT_eX]

[DOI]

Alexander Fraser

Proceedings of the Findings of the Association for Computational Linguistics: ACL 2023, 2023

2022

Large pre-trained language models contain human-like biases of what is right and wrong to do.

[BibT_eX]

[DOI]

Nico Andersen

Nat. Mach. Intell., 2022

The Stable Artist: Steering Semantics in Diffusion Latent Space.

[BibT_eX]

[DOI]

CoRR, 2022

Revision Transformers: Getting RiT of No-Nos.

[BibT_eX]

[DOI]

CoRR, 2022

LogicRank: Logic Induced Reranking for Generative Text-to-Image Systems.

[BibT_eX]

[DOI]

CoRR, 2022

ILLUME: Rationalizing Vision-Language Models by Interacting with their Jabber.

[BibT_eX]

[DOI]

CoRR, 2022

Do Multilingual Language Models Capture Differing Moral Norms?

[BibT_eX]

[DOI]

CoRR, 2022

A Typology to Explore and Guide Explanatory Interactive Machine Learning.

[BibT_eX]

[DOI]

CoRR, 2022

LAION-5B: An open large-scale dataset for training next generation image-text models.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Interactively Providing Explanations for Transformer Language Models.

[BibT_eX]

[DOI]

Felix Friedrich

Christopher Tauchmann

Proceedings of the HHAI 2022: Augmenting Human Intellect, 2022

Can Machines Help Us Answering Question 16 in Datasheets, and In Turn Reflecting on Inappropriate Content?

[BibT_eX]

[DOI]

Christopher Tauchmann

Proceedings of the FAccT '22: 2022 ACM Conference on Fairness, Accountability, and Transparency, Seoul, Republic of Korea, June 21, 2022

Interactive Disentanglement: Learning Concepts by Interacting with their Prototype Representations.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2021

Inferring Offensiveness In Images From Natural Language Supervision.

[BibT_eX]

[DOI]

CoRR, 2021

Interactively Generating Explanations for Transformer Language Models.

[BibT_eX]

[DOI]

Felix Friedrich

Christopher Tauchmann

CoRR, 2021

Language Models have a Moral Dimension.

[BibT_eX]

[DOI]

Nico Andersen

CoRR, 2021

Recurrent Rational Networks.

[BibT_eX]

[DOI]

CoRR, 2021

Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting With Their Explanations.

[BibT_eX]

[DOI]

Wolfgang Stammer

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Right for Better Reasons: Training Differentiable Models by Constraining their Influence Functions.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020

Making deep neural networks right for the right scientific reasons by interacting with their explanations.

[BibT_eX]

[DOI]

Nat. Mach. Intell., 2020

The Moral Choice Machine.

[BibT_eX]

[DOI]

Sophie F. Jentzsch

Frontiers Artif. Intell., 2020

Right for the Wrong Scientific Reasons: Revising Deep Networks by Interacting with their Explanations.

[BibT_eX]

[DOI]

CoRR, 2020

Alfie: An Interactive Robot with Moral Compass.

[BibT_eX]

[DOI]

Proceedings of the ICMI '20: International Conference on Multimodal Interaction, 2020

Padé Activation Units: End-to-end Learning of Flexible Activation Functions in Deep Networks.

[BibT_eX]

[DOI]

Alejandro Molina

Proceedings of the 8th International Conference on Learning Representations, 2020

2019

Extending Hyperspectral Imaging for Plant Phenotyping to the UV-Range.

[BibT_eX]

[DOI]

Remote. Sens., 2019

BERT has a Moral Compass: Improvements of ethical and moral values of machines.

[BibT_eX]

[DOI]

Sophie F. Jentzsch

CoRR, 2019

Semantics Derived Automatically from Language Corpora Contain Human-like Moral Choices.

[BibT_eX]

[DOI]

Sophie F. Jentzsch

Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, 2019

2018

Neural Conditional Gradients.

[BibT_eX]

[DOI]

Christian Bauckhage