Author name cluster

Patrick Schramowski

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

15 papers

2 author rows

ICML Conference 2025 Conference Paper

LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models

Lukas Helff
Felix Friedrich
Manuel Brack
Kristian Kersting
Patrick Schramowski

This paper introduces Llavaguard, a suite of VLM-based vision safeguards that address the critical need for reliable tools in the era of large-scale data and models. To this end, we establish a novel open framework, describing a customizable safety taxonomy, data preprocessing, augmentation, and training setup. For teaching a VLM safeguard on safety, we further create a multimodal safety dataset with high-quality human expert annotations, where each image is labeled with a safety rating, category, and rationale. We also employ advanced augmentations to support context-specific assessments. The resulting Llavaguard models, ranging from 0. 5B to 7B, serve as a versatile tool for evaluating the safety compliance of visual content against flexible policies. In comprehensive experiments, Llavaguard outperforms both state-of-the-art safeguards and VLMs in accuracy and in flexibly handling different policies. Additionally, we demonstrate Llavaguard’s performance in two real-world applications: large-scale dataset annotation and moderation of text-to-image models. We make our entire framework, including the dataset, model weights, and training code, publicly available at https: //ml-research. github. io/human-centered-genai/projects/llavaguard.

Details

NeurIPS Conference 2025 Conference Paper

Measuring and Guiding Monosemanticity

Ruben Härle
Felix Friedrich
Manuel Brack
Björn Deiseroth
Stephan Waeldchen
Patrick Schramowski
Kristian Kersting

There is growing interest in leveraging mechanistic interpretability and controllability to better understand and influence the internal dynamics of large language models (LLMs). However, current methods face fundamental challenges in reliably localizing and manipulating feature representations. Sparse Autoencoders (SAEs) have recently emerged as a promising direction for feature extraction at scale, yet they, too, are limited by incomplete feature isolation and unreliable monosemanticity. To systematically quantify these limitations, we introduce Feature Monosemanticity Score (FMS), a novel metric to quantify feature monosemanticity in latent representation. Building on these insights, we propose Guided Sparse Autoencoders (G-SAE), a method that conditions latent representations on labeled concepts during training. We demonstrate that reliable localization and disentanglement of target concepts within the latent space improve interpretability, detection of behavior, and control. Specifically, our evaluations on toxicity detection, writing style identification, and privacy attribute recognition show that G-SAE not only enhances monosemanticity but also enables more effective and fine-grained steering with less quality degradation. Our findings provide actionable guidelines for measuring and advancing mechanistic interpretability and control of LLMs.

PDF Details

ICLR Conference 2024 Conference Paper

Adaptive Rational Activations to Boost Deep Reinforcement Learning

Quentin Delfosse
Patrick Schramowski
Martin Mundt
Alejandro Molina 0001
Kristian Kersting

Latest insights from biology show that intelligence not only emerges from the connections between neurons, but that individual neurons shoulder more computational responsibility than previously anticipated. Specifically, neural plasticity should be critical in the context of constantly changing reinforcement learning (RL) environments, yet current approaches still primarily employ static activation functions. In this work, we motivate the use of adaptable activation functions in RL and show that rational activation functions are particularly suitable for augmenting plasticity. Inspired by residual networks, we derive a condition under which rational units are closed under residual connections and formulate a naturally regularised version. The proposed joint-rational activation allows for desirable degrees of flexibility, yet regularises plasticity to an extent that avoids overfitting by leveraging a mutual set of activation function parameters across layers. We demonstrate that equipping popular algorithms with (joint) rational activations leads to consistent improvements on different games from the Atari Learning Environment benchmark, notably making DQN competitive to DDQN and Rainbow.

Details

NeurIPS Conference 2024 Conference Paper

DeiSAM: Segment Anything with Deictic Prompting

Hikaru Shindo
Manuel Brack
Gopika Sudhakaran
Devendra S. Dhami
Patrick Schramowski
Kristian Kersting

Large-scale, pre-trained neural networks have demonstrated strong capabilities in various tasks, including zero-shot image segmentation. To identify concrete objects in complex scenes, humans instinctively rely on deictic descriptions in natural language, i. e. , referring to something depending on the context such as "The object that is on the desk and behind the cup. ". However, deep learning approaches cannot reliably interpret such deictic representations due to their lack of reasoning capabilities in complex scenarios. To remedy this issue, we propose DeiSAM — a combination of large pre-trained neural networks with differentiable logic reasoners — for deictic promptable segmentation. Given a complex, textual segmentation description, DeiSAM leverages Large Language Models (LLMs) to generate first-order logic rules and performs differentiable forward reasoning on generated scene graphs. Subsequently, DeiSAM segments objects by matching them to the logically inferred image regions. As part of our evaluation, we propose the Deictic Visual Genome (DeiVG) dataset, containing paired visual input and complex, deictic textual prompts. Our empirical results demonstrate that DeiSAM is a substantial improvement over purely data-driven baselines for deictic promptable segmentation.

PDF Details DOI

JAIR Journal 2024 Journal Article

Does CLIP Know My Face?

Dominik Hintersdorf
Lukas Struppek
Manuel Brack
Felix Friedrich
Patrick Schramowski
Kristian Kersting

With the rise of deep learning in various applications, privacy concerns around the protection of training data have become a critical area of research. Whereas prior studies have focused on privacy risks in single-modal models, we introduce a novel method to assess privacy for multi-modal models, specifically vision-language models like CLIP. The proposed Identity Inference Attack (IDIA) reveals whether an individual was included in the training data by querying the model with images of the same person. Letting the model choose from a wide variety of possible text labels, the model reveals whether it recognizes the person and, therefore, was used for training. Our large-scale experiments on CLIP demonstrate that individuals used for training can be identified with very high accuracy. We confirm that the model has learned to associate names with depicted individuals, implying the existence of sensitive information that can be extracted by adversaries. Our results highlight the need for stronger privacy protection in large-scale models and suggest that IDIAs can be used to prove the unauthorized use of data for training and to enforce privacy laws. This article appears in the AI & Society track.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Exploiting Cultural Biases via Homoglyphs inText-to-Image Synthesis (Abstract Reprint)

Lukas Struppek
Dominik Hintersdorf
Felix Friedrich
Manuel Brack
Patrick Schramowski
Kristian Kersting

Models for text-to-image synthesis, such as DALL-E 2 and Stable Diffusion, have recently drawn a lot of interest from academia and the general public. These models are capable of producing high-quality images that depict a variety of concepts and styles when conditioned on textual descriptions. However, these models adopt cultural characteristics associated with specific Unicode scripts from their vast amount of training data, which may not be immediately apparent. We show that by simply inserting single non-Latin characters in the textual description, common models reflect cultural biases in their generated images. We analyze this behavior both qualitatively and quantitatively and identify a model’s text encoder as the root cause of the phenomenon. Such behavior can be interpreted as a model feature, offering users a simple way to customize the image generation and reflect their own cultural background. Yet, malicious users or service providers may also try to intentionally bias the image generation. One goal might be to create racist stereotypes by replacing Latin characters with similarly-looking characters from non-Latin scripts, so-called homoglyphs. To mitigate such unnoticed script attacks, we propose a novel homoglyph unlearning method to fine-tune a text encoder, making it robust against homoglyph manipulations.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

ATMAN: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation

Björn Deiseroth
Mayukh Deb
Samuel Weinbach
Manuel Brack
Patrick Schramowski
Kristian Kersting

Generative transformer models have become increasingly complex, with large numbers of parameters and the ability to process multiple input modalities. Current methods for explaining their predictions are resource-intensive. Most crucially, they require prohibitively large amounts of additional memory, since they rely on backpropagation which allocates almost twice as much GPU memory as the forward pass. This makes it difficult, if not impossible, to use explanations in production. We present AtMan that provides explanations of generative transformer models at almost no extra cost. Specifically, AtMan is a modality-agnostic perturbation method that manipulates the attention mechanisms of transformers to produce relevance maps for the input with respect to the output prediction. Instead of using backpropagation, AtMan applies a parallelizable token-based search method relying on cosine similarity neighborhood in the embedding space. Our exhaustive experiments on text and image-text benchmarks demonstrate that AtMan outperforms current state-of-the-art gradient-based methods on several metrics while being computationally efficient. As such, AtMan is suitable for use in large model inference deployments.

PDF Details

JAIR Journal 2023 Journal Article

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

Lukas Struppek
Dominik Hintersdorf
Felix Friedrich
Manuel Brack
Patrick Schramowski
Kristian Kersting

PDF Details DOI

ICML Conference 2023 Conference Paper

ILLUME: Rationalizing Vision-Language Models through Human Interactions

Manuel Brack
Patrick Schramowski
Björn Deiseroth
Kristian Kersting

Bootstrapping from pre-trained language models has been proven to be an efficient approach for building vision-language models (VLM) for tasks such as image captioning or visual question answering. However, outputs of these models rarely align with user’s rationales for specific answers. In order to improve this alignment and reinforce commonsense reasons, we propose a tuning paradigm based on human interactions with machine-generated data. Our ILLUME executes the following loop: Given an image-question-answer prompt, the VLM samples multiple candidate rationales, and a human critic provides feedback via preference selection, used for fine-tuning. This loop increases the training data and gradually carves out the VLM’s rationalization capabilities that are aligned with human intent. Our exhaustive experiments demonstrate that ILLUME is competitive with standard supervised finetuning while using significantly fewer training data and only requiring minimal feedback.

Details

NeurIPS Conference 2023 Conference Paper

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

Marco Bellagente
Manuel Brack
Hannah Teufel
Felix Friedrich
Björn Deiseroth
Constantin Eichenberg
Andrew M. Dai
Robert Baldock

The recent popularity of text-to-image diffusion models (DM) can largely be attributed to the intuitive interface they provide to users. The intended generation can be expressed in natural language, with the model producing faithful interpretations of text prompts. However, expressing complex or nuanced ideas in text alone can be difficult. To ease image generation, we propose MultiFusion that allows one to express complex and nuanced concepts with arbitrarily interleaved inputs of multiple modalities and languages. MultiFusion leverages pre-trained models and aligns them for integration into a cohesive system, thereby avoiding the need for extensive training from scratch. Our experimental results demonstrate the efficient transfer of capabilities from individual modules to the downstream model. Specifically, the fusion of all independent components allows the image generation module to utilize multilingual, interleaved multimodal inputs despite being trained solely on monomodal data in a single language.

PDF Details

ECAI Conference 2023 Conference Paper

Revision Transformers: Instructing Language Models to Change Their Values

Felix Friedrich
Wolfgang Stammer
Patrick Schramowski
Kristian Kersting

Current transformer language models (LM) are large-scale models with billions of parameters. They have been shown to provide high performances on a variety of tasks but are also prone to shortcut learning and bias. Addressing such incorrect model behavior via parameter adjustments is very costly. This is particularly problematic for updating dynamic concepts, such as moral values, which vary culturally or interpersonally. In this work, we question the current common practice of storing all information in the model parameters and propose the Revision Transformer (RiT) to facilitate easy model updating. The specific combination of a large-scale pre-trained LM that inherently but also diffusely encodes world knowledge with a clear-structured revision engine makes it possible to update the model’s knowledge with little effort and the help of user interaction. We exemplify RiT on a moral dataset and simulate user feedback demonstrating strong performance in model revision even with small data. This way, users can easily design a model regarding their preferences, paving the way for more transparent AI models.

Details

NeurIPS Conference 2023 Conference Paper

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

Manuel Brack
Felix Friedrich
Dominik Hintersdorf
Lukas Struppek
Patrick Schramowski
Kristian Kersting

Text-to-image diffusion models have recently received a lot of interest for their astonishing ability to produce high-fidelity images from text only. However, achieving one-shot generation that aligns with the user’s intent is nearly impossible, yet small changes to the input prompt often result in very different images. This leaves the user with little semantic control. To put the user in control, we show how to interact with the diffusion process to flexibly steer it along semantic directions. This semantic guidance (SEGA) generalizes to any generative architecture using classifier-free guidance. More importantly, it allows for subtle and extensive edits, composition and style changes, and optimizing the overall artistic conception. We demonstrate SEGA’s effectiveness on both latent and pixel-based diffusion models such as Stable Diffusion, Paella, and DeepFloyd-IF using a variety of tasks, thus providing strong evidence for its versatility and flexibility.

PDF Details

NeurIPS Conference 2022 Conference Paper

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

Christoph Schuhmann
Romain Beaumont
Richard Vencu
Cade Gordon
Ross Wightman
Mehdi Cherti
Theo Coombes
Aarush Katta

Groundbreaking language-vision architectures like CLIP and DALL-E proved the utility of training on large amounts of noisy image-text data, without relying on expensive accurate labels used in standard vision unimodal supervised learning. The resulting models showed capabilities of strong text-guided image generation and transfer to downstream tasks, while performing remarkably at zero-shot classification with noteworthy out-of-distribution robustness. Since then, large-scale language-vision models like ALIGN, BASIC, GLIDE, Flamingo and Imagen made further improvements. Studying the training and capabilities of such models requires datasets containing billions of image-text pairs. Until now, no datasets of this size have been made openly available for the broader research community. To address this problem and democratize research on large-scale multi-modal models, we present LAION-5B - a dataset consisting of 5. 85 billion CLIP-filtered image-text pairs, of which 2. 32B contain English language. We show successful replication and fine-tuning of foundational models like CLIP, GLIDE and Stable Diffusion using the dataset, and discuss further experiments enabled with an openly available dataset of this scale. Additionally we provide several nearest neighbor indices, an improved web-interface for dataset exploration and subset generation, and detection scores for watermark, NSFW, and toxic content detection.

PDF Details

AAAI Conference 2021 Conference Paper

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

Xiaoting Shao
Arseny Skryagin
Wolfgang Stammer
Patrick Schramowski
Kristian Kersting

Explaining black-box models such as deep neural networks is becoming increasingly important as it helps to boost trust and debugging. Popular forms of explanations map the features to a vector indicating their individual importance to a decision on the instance-level. They can then be used to prevent the model from learning the wrong bias in data possibly due to ambiguity. For instance, Ross et al. ’s “right for the right reasons” propagates user explanations backwards to the network by formulating differentiable constraints based on input gradients. Unfortunately, input gradients as well as many other widely used explanation methods form an approximation of the decision boundary and assume the underlying model to be fixed. Here, we demonstrate how to make use of influence functions—a well known robust statistic—in the constraints to correct the model’s behaviour more effectively. Our empirical evidence demonstrates that this “right for better reasons”(RBR) considerably reduces the time to correct the classifier at training time and boosts the quality of explanations at inference time compared to input gradients. Besides, we also showcase the effectiveness of RBR in correcting ”Clever Hans”-like behaviour in real, high-dimensional domain.

PDF Details

ICLR Conference 2020 Conference Paper

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

Alejandro Molina 0001
Patrick Schramowski
Kristian Kersting

The performance of deep network learning strongly depends on the choice of the non-linear activation function associated with each neuron. However, deciding on the best activation is non-trivial and the choice depends on the architecture, hyper-parameters, and even on the dataset. Typically these activations are fixed by hand before training. Here, we demonstrate how to eliminate the reliance on first picking fixed activation functions by using flexible parametric rational functions instead. The resulting Padé Activation Units (PAUs) can both approximate common activation functions and also learn new ones while providing compact representations. Our empirical evidence shows that end-to-end learning deep networks with PAUs can increase the predictive performance. Moreover, PAUs pave the way to approximations with provable robustness.

Details