Kristian Kersting

research

∙ 09/20/2023

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

Text-conditioned image generation models have recently achieved astonish...

0 Manuel Brack, et al. ∙

research

∙ 08/25/2023

Learning to Intervene on Concept Bottlenecks

While traditional deep learning models often lack interpretability, conc...

0 David Steinmann, et al. ∙

research

∙ 08/24/2023

Causal Parrots: Large Language Models May Talk Causality But Are Not Causal

Some argue scale is all what is needed to achieve AI, covering even caus...

0 Matej Zečević, et al. ∙

research

∙ 08/18/2023

Balancing Transparency and Risk: The Security and Privacy Risks of Open-Source Machine Learning Models

The field of artificial intelligence (AI) has experienced remarkable pro...

0 Dominik Hintersdorf, et al. ∙

research

∙ 08/18/2023

Vision Relation Transformer for Unbiased Scene Graph Generation

Recent years have seen a growing interest in Scene Graph Generation (SGG...

0 Gopika Sudhakaran, et al. ∙

research

∙ 07/10/2023

Self Expanding Neural Networks

The results of training a neural network are heavily dependent on the ar...

0 Rupert Mitchell, et al. ∙

research

∙ 06/14/2023

OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments

Cognitive science and psychology suggest that object-centric representat...

12 Quentin Delfosse, et al. ∙

research

∙ 06/14/2023

Scalable Neural-Probabilistic Answer Set Programming

The goal of combining the robustness of neural networks and the expressi...

6 Arseny Skryagin, et al. ∙

research

∙ 06/07/2023

ChatGPT is fun, but it is not funny! Humor is still challenging Large Language Models

Humor is a central aspect of human communication that has not been solve...

9 Sophie Jentzsch, et al. ∙

research

∙ 06/06/2023

Masked Autoencoders are Efficient Continual Federated Learners

Machine learning is typically framed from a perspective of i.i.d., and m...

7 Subarnaduti Paul, et al. ∙

research

∙ 06/03/2023

Deep Classifier Mimicry without Data Access

Access to pre-trained models has recently emerged as a standard across n...

7 Steven Braun, et al. ∙

research

∙ 05/28/2023

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

Text-conditioned image generation models have recently achieved astonish...

1 Manuel Brack, et al. ∙

research

∙ 05/24/2023

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

The recent popularity of text-to-image diffusion models (DM) can largely...

24 Marco Bellagente, et al. ∙

research

∙ 05/22/2023

Know your Enemy: Investigating Monte-Carlo Tree Search with Opponent Models in Pommerman

In combination with Reinforcement Learning, Monte-Carlo Tree Search has ...

2 Jannis Weil, et al. ∙

research

∙ 04/28/2023

Representation Matters: The Game of Chess Poses a Challenge to Vision Transformers

While transformers have gained the reputation as the "Swiss army knife o...

8 Johannes Czech, et al. ∙

research

∙ 04/14/2023

One Explanation Does Not Fit XIL

Current machine learning models produce outstanding results in many area...

19 Felix Friedrich, et al. ∙

research

∙ 03/16/2023

Image Classifiers Leak Sensitive Attributes About Their Classes

Neural network-based image classifiers are powerful tools for computer v...

1 Lukas Struppek, et al. ∙

research

∙ 02/13/2023

Probabilistic Circuits That Know What They Don't Know

Probabilistic circuits (PCs) are models that allow exact and tractable p...

4 Fabrizio Ventola, et al. ∙

research

∙ 02/07/2023

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

Generative AI models have recently achieved astonishing results in quali...

0 Felix Friedrich, et al. ∙

research

∙ 01/28/2023

SEGA: Instructing Diffusion using Semantic Dimensions

Text-to-image diffusion models have recently received a lot of interest ...

8 Manuel Brack, et al. ∙

research

∙ 01/19/2023

AtMan: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation

Generative transformer models have become increasingly complex, with lar...

36 Mayukh Deb, et al. ∙

research

∙ 12/23/2022

Pearl Causal Hierarchy on Image Data: Intricacies Challenges

Many researchers have voiced their support towards Pearl's counterfactua...

20 Matej Zečević, et al. ∙

research

∙ 12/12/2022

The Stable Artist: Steering Semantics in Diffusion Latent Space

Large, text-conditioned generative diffusion models have recently gained...

6 Manuel Brack, et al. ∙

research

∙ 11/16/2022

Boosting Object Representation Learning via Motion and Object Continuity

Recent unsupervised multi-object detection models have shown impressive ...

0 Quentin Delfosse, et al. ∙

research

∙ 11/14/2022

Speaking Multiple Languages Affects the Moral Bias of Language Models

Pre-trained multilingual language models (PMLMs) are commonly used when ...

8 Katharina Hämmerl, et al. ∙

research

∙ 11/09/2022

Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models

Text-conditioned image generation models have recently achieved astonish...

1 Patrick Schramowski, et al. ∙

research

∙ 11/04/2022

Rickrolling the Artist: Injecting Invisible Backdoors into Text-Guided Image Generation Models

While text-to-image synthesis currently enjoys great popularity among re...

1 Lukas Struppek, et al. ∙

research

∙ 10/19/2022

Revision Transformers: Getting RiT of No-Nos

Current transformer language models (LM) are large-scale models with bil...

9 Felix Friedrich, et al. ∙

research

∙ 09/19/2022

The Biased Artist: Exploiting Cultural Biases via Homoglyphs in Text-Guided Image Generation Models

Text-guided image generation models, such as DALL-E 2 and Stable Diffusi...

22 Lukas Struppek, et al. ∙

research

∙ 09/15/2022

CLIPping Privacy: Identity Inference Attacks on Multi-Modal Machine Learning Models

As deep learning is now used in many real-world applications, research h...

6 Dominik Hintersdorf, et al. ∙

research

∙ 08/24/2022

Transformer-Boosted Anomaly Detection with Fuzzy Hashes

Fuzzy hashes are an important tool in digital forensics and are used in ...

12 Frieder Uhlig, et al. ∙

research

∙ 08/17/2022

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

Bootstrapping from pre-trained language models has been proven to be an ...

16 Manuel Brack, et al. ∙

research

∙ 06/24/2022

HANF: Hyperparameter And Neural Architecture Search in Federated Learning

Automated machine learning (AutoML) is an important step to make machine...

11 Jonas Seng, et al. ∙

research

∙ 06/14/2022

Attributions Beyond Neural Networks: The Linear Program Case

Linear Programs (LPs) have been one of the building blocks in machine le...

13 Florian Peter Busch, et al. ∙

research

∙ 06/14/2022

Can Foundation Models Talk Causality?

Foundation models are subject to an ongoing heated debate, leaving open ...

11 Moritz Willig, et al. ∙

research

∙ 06/14/2022

Towards a Solution to Bongard Problems: A Causal Approach

To date, Bongard Problems (BP) remain one of the few fortresses of AI hi...

0 Salahedine Youssef, et al. ∙

research

∙ 06/14/2022

Tearing Apart NOTEARS: Controlling the Graph Prediction via Variance Manipulation

Simulations are ubiquitous in machine learning. Especially in graph lear...

4 Jonas Seng, et al. ∙

research

∙ 06/14/2022

Machines Explaining Linear Programs

There has been a recent push in making machine learning models more inte...

10 David Steinmann, et al. ∙

research

∙ 05/16/2022

Gradient-based Counterfactual Explanations using Tractable Probabilistic Models

Counterfactual examples are an appealing class of post-hoc explanations ...

12 Xiaoting Shao, et al. ∙

research

∙ 05/03/2022

Adaptable Adapters

State-of-the-art pretrained NLP models contain a hundred million to tril...

1 Nafise Sadat Moosavi, et al. ∙

research

∙ 03/29/2022

Finding Structure and Causality in Linear Programs

Linear Programs (LP) are celebrated widely, particularly so in machine l...

7 Matej Zečević, et al. ∙

research

∙ 03/18/2022

Do Multilingual Language Models Capture Differing Moral Norms?

Massively multilingual sentence representations are trained on large cor...

0 Katharina Hämmerl, et al. ∙

research

∙ 03/04/2022

A Typology to Explore and Guide Explanatory Interactive Machine Learning

Recently, more and more eXplanatory Interactive machine Learning (XIL) m...

57 Felix Friedrich, et al. ∙

research

∙ 03/02/2022

Neuro-Symbolic Verification of Deep Neural Networks

Formal verification has emerged as a powerful approach to ensure the saf...

18 Xuan Xie, et al. ∙

research

∙ 02/14/2022

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

Large datasets underlying much of current machine learning raise serious...

0 Patrick Schramowski, et al. ∙

research

∙ 02/01/2022

Right for the Right Latent Factors: Debiasing Generative Models via Disentanglement

A key assumption of most statistical machine learning methods is that th...

7 Xiaoting Shao, et al. ∙

research

∙ 01/28/2022

Plug Play Attacks: Towards Robust and Flexible Model Inversion Attacks

Model inversion attacks (MIAs) aim to create synthetic images that refle...

2 Lukas Struppek, et al. ∙

research

∙ 12/04/2021

Interactive Disentanglement: Learning Concepts by Interacting with their Prototype Representations

Learning visual concepts from raw images without strong supervision is a...

5 Wolfgang Stammer, et al. ∙

research

∙ 11/17/2021

Do Not Trust Prediction Scores for Membership Inference Attacks

Membership inference attacks (MIAs) aim to determine whether a specific ...

3 Dominik Hintersdorf, et al. ∙

research

∙ 11/12/2021

Learning to Break Deep Perceptual Hashing: The Use Case NeuralHash

Apple recently revealed its deep perceptual hashing system NeuralHash to...

10 Lukas Struppek, et al. ∙

Kristian Kersting

Featured Co-authors