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...
share
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...
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...
research
∙
03/16/2023
Image Classifiers Leak Sensitive Attributes About Their Classes
Neural network-based image classifiers are powerful tools for computer v...
research
∙
02/07/2023
Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness
Generative AI models have recently achieved astonishing results in quali...
research
∙
01/28/2023
SEGA: Instructing Diffusion using Semantic Dimensions
Text-to-image diffusion models have recently received a lot of interest ...
research
∙
01/19/2023
AtMan: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation
Generative transformer models have become increasingly complex, with lar...
research
∙
12/12/2022
The Stable Artist: Steering Semantics in Diffusion Latent Space
Large, text-conditioned generative diffusion models have recently gained...
research
∙
11/14/2022
Speaking Multiple Languages Affects the Moral Bias of Language Models
Pre-trained multilingual language models (PMLMs) are commonly used when ...
research
∙
11/09/2022
Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models
Text-conditioned image generation models have recently achieved astonish...
research
∙
10/19/2022
Revision Transformers: Getting RiT of No-Nos
Current transformer language models (LM) are large-scale models with bil...
research
∙
10/16/2022
LAION-5B: An open large-scale dataset for training next generation image-text models
Groundbreaking language-vision architectures like CLIP and DALL-E proved...
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 ...
research
∙
03/18/2022
Do Multilingual Language Models Capture Differing Moral Norms?
Massively multilingual sentence representations are trained on large cor...
research
∙
03/04/2022
A Typology to Explore and Guide Explanatory Interactive Machine Learning
Recently, more and more eXplanatory Interactive machine Learning (XIL) m...
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...
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...
research
∙
10/08/2021
Inferring Offensiveness In Images From Natural Language Supervision
Probing or fine-tuning (large-scale) pre-trained models results in state...
research
∙
03/08/2021
Language Models have a Moral Dimension
Artificial writing is permeating our lives due to recent advances in lar...
research
∙
02/18/2021
Recurrent Rational Networks
Latest insights from biology show that intelligence does not only emerge...
research
∙
11/25/2020
Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanations
Most explanation methods in deep learning map importance estimates for a...
research
∙
09/11/2020
Alfie: An Interactive Robot with a Moral Compass
This work introduces Alfie, an interactive robot that is capable of answ...
research
∙
01/15/2020
Right for the Wrong Scientific Reasons: Revising Deep Networks by Interacting with their Explanations
Deep neural networks have shown excellent performances in many real-worl...
research
∙
12/11/2019
BERT has a Moral Compass: Improvements of ethical and moral values of machines
Allowing machines to choose whether to kill humans would be devastating ...
research
∙
07/15/2019
Padé Activation Units: End-to-end Learning of Flexible Activation Functions in Deep Networks
The performance of deep network learning strongly depends on the choice ...
research
∙
03/12/2018