There is a huge demand for trying on clothing at home. Recent methods to capture your figure mostly work in a 2d image plane and despite recent improvements of available technology the simulation of clothing is still not satisfactory. Especially the rendering of different clothing sizes is still a major challenge, which is only addressed by COTTON [1]. We propose an improvement to this approach by adding more control over the image generation process. For this we employ a special type of conditional diffusion model, namely ControlNet, and take keypoints of the fashion as conditional input.

Große Sprachmodelle wie ChatGPT benötigen große und teure Server und viel Energie. Man kann sie aber quantisieren, sodass sie mit viel weniger Speicher und Strom auskommen und sogar lokal auf einem Smartphone laufen. Wir erklären, warum quantisierte Modelle viel schneller antworten und trotzdem fast so schlau sind wie die großen Originale.

Despite being a specific sustainable development goal (SDG), the role of consumers for sustainable consumption is still ambiguous. This is exemplified by a vast amount of research on the attitude-intention-behavior gap, which generally describes consumers’ failures to behave as sustainable as theoretically predicted. Recent reviews have prompted further investigations beyond the existing literature on factors influencing this gap. We contribute to this call by quantitatively investigating five antagonistic dimensions – both intrapsychic and situation-related – of smartphone usage and sustainable consumer behavior in Germany (n=800). Our results indicate two novel concepts. Emotional connection – i.e., consumers’ connections with the consumption experience – can either promote or prevent sustainable behavior, while exploration-driven consumerism – i.e., new purchases due to exploration tendencies – typically attenuates sustainable behavior. This illustrates how and when sustainability is outweighed by other consumer attitudes. We contextualize these results and conclude our study by highlighting limitations and further research opportunities.

Literature reviews play a crucial role in Information Systems (IS) research. However, scholars have expressed concerns regarding the reproducibility of their results and the quality of documentation. The involvement of human reproducers in these reviews is often hindered by the time-consuming nature of the procedures. The emergence of Large Language Models (LLMs) seems promising to support researchers and to enhance reproducibility. To explore this potential, we conducted experiments using various LLMs, focusing on abstract scanning, and have presented initial evidence suggesting that the application of LLMs in structured literature reviews could assist researchers in refining and formulating rules for abstract scanning. Based on our preliminary findings, we identify potential future research directions in this research in progress paper.

As the output quality of neural networks in the fields of automatic speech recognition (ASR) and text-to-speech (TTS) continues to improve, new opportunities are becoming available to train models in a weakly supervised fashion, thus minimizing the manual effort required to annotate new audio data for supervised training. While weak supervision has recently shown very promising results in the domain of ASR, speech synthesis has not yet been thoroughly investigated regarding this technique despite requiring the equivalent training dataset structure of aligned audio-transcript pairs.
In this work, we compare the performance of TTS models trained using a well-curated and manually labeled training dataset to others trained on the same audio data with text labels generated using both grapheme- and phoneme-based ASR models. Phoneme-based approaches seem especially promising, since even for wrongly predicted phonemes, the resulting word is more likely to sound similar to the originally spoken word than for grapheme-based predictions.
For evaluation and ranking, we generate synthesized audio outputs from all previously trained models using input texts sourced from a selection of speech recognition datasets covering a wide range of application domains. These synthesized outputs are subsequently fed into multiple state-of-the-art ASR models with their output text predictions being compared to the initial TTS model input texts. This comparison enables an objective assessment of the intelligibility of the audio outputs from all TTS models, by utilizing metrics like word error rate and character error rate.
Our results not only show that models trained on data generated with weak supervision achieve comparable quality to models trained on manually labeled datasets, but can outperform the latter, even for small, well-curated speech datasets. These findings suggest that the future creation of labeled datasets for supervised training of TTS models may not require any manual annotation but can be fully automated.

There are many publications talking about the biases to be found in in generative AI solutions like large language models (LLMs, e.g., Mistral) or text-to-image models (T2IMs, e.g., Stable Diffusion). However, there is merely any publication to be found that questions what kind of behavior is actually desired, not only by a couple of researchers, but by society in general. Most researchers in this area seem to think that there would be a common agreement, but political debate in other areas shows that this is seldom the case, even for a single country. Climate change, for example, is an empirically well-proven scientific fact, 197 countries (including Germany) have declared to do their best to limit global warming to a maximum of 1.5°C in the Paris Agreement, but still renowned German scientists are calling LLMs biased if they state that there is human-made climate change and humanity is doing not enough to stop it. This trend is especially visible in Western individualistic societies that favor personal well-being over common good. In this article, we are exploring different aspects of biases found in LLMs and T2IMs, highlight potential divergence in the perception of ethically desirable outputs and discuss potential solutions with their advantages and drawbacks from the perspective of society. The analysis is carried out in an interdisciplinary manner with the authors coming from as diverse backgrounds as business information systems, political sciences, and law. Our contribution brings new insights to this debate and sheds light on an important aspect of the discussion that is largely ignored up to now.

In this paper we present a stable-diffusion based zero-shot approach to realistically transform the image of a

human body into a more fit version of that depicted person. Therefore we combine a modified stable diffusion

model with inpainting techniques and incorporated constraints. We introduce a prototype which allows users to

upload a photo and visualize a more fit version of themselves. We evaluated our approach in various experiments

and focused on the applicability and effectiveness of these techniques, with attention to gender-specific results.

This work contributes to the fields of computer vision and generative AI by demonstrating practical applications

and identifying areas for improvement in realistic body transformation visualizations.

This book is intended as a practical guide to the concepts of hardware and software configuration for industrial production automation using the TIA PORTAL software platform. Thus, anyone working in the field of automation will benefit from reading it, while it has been written for undergraduate students of electrical, mechanical and industrial engineering, as well as engineering students engaged in similar academic pursuits.

This book deals with the use of S7 1200 and S71500 PLCs to control operational components in automated systems, in accordance with current standards. It is a good starting point into the world of Siemens' Totally Integrated Automation (TIA) product range.

The book also contains practical examples and explanatory diagrams of the graphical interfaces of the TIA PORTAL software, which illustrate the programming and configuration procedures and techniques.

Those interested in developing local industrial communication networks to implement centralised and decentralised control system architectures will also find this book useful. It details techniques provided by Siemens that are well suited to programming plans under the TIA PORTAL platform.

It also introduces the reader to Human Machine Interface (HMI) development, covering topics such as hardware configuration, software programming, networking, testing and validation.

This book is an invaluable resource for those new to the field of industrial automation, as well as for teachers wishing to teach and gain expertise in this specialised area.

Background

The impact of the infecting SARS-CoV-2 variant of concern (VOC) and the vaccination status was determined on the magnitude, breadth, and durability of the neutralizing antibody (nAb) profile in a longitudinal multicentre cohort study.

Methods

173 vaccinated and 56 non-vaccinated individuals were enrolled after SARS-CoV-2 Alpha, Delta, or Omicron infection and visited four times within 6 months and nAbs were measured for D614G, Alpha, Delta, BA.1, BA.2, BA.5, BQ.1.1, XBB.1.5 and JN.1.

Findings

Magnitude-breadth-analysis showed enhanced neutralization capacity in vaccinated individuals against multiple VOCs. Longitudinal analysis revealed sustained neutralization magnitude-breadth after antigenically distant Delta or Omicron breakthrough infection (BTI), with triple-vaccinated individuals showing significantly elevated titres and improved breadth. Antigenic mapping and antibody landscaping revealed initial boosting of vaccine-induced WT-specific responses after BTI, a shift in neutralization towards infecting VOCs at peak responses and an immune imprinted bias towards dominating WT immunity in the long-term. Despite that bias, machine-learning models confirmed a sustained shift of the immune-profiles following BTI.

Interpretation

In summary, our longitudinal analysis revealed delayed and short lived nAb shifts towards the infecting VOC, but an immune imprinted bias towards long-term vaccine induced immunity after BTI.

Funding

This work was funded by the Bavarian State Ministry of Science and the Arts for the CoVaKo study and the ForCovid project. The funders had no influence on the study design, data analysis or data interpretation.

This paper investigates the comparative effectiveness of model-to-model transformations generated by an LLM based upon user prompts versus those created with dedicated model transformation languages, using a standard benchmark. The emergence of Generative AI offers a novel approach, allowing developers to specify transformations in natural language rather than learning specialized languages. However, our findings suggest that, in its current state, generative AI does not yet pose a threat to dedicated model transformation languages. While AI-assisted approaches promise to provide flexibility and accessibility, dedicated model transformation languages still offer structured advantages crucial for complex transformations, especially when bidirectionality and incrementality are mandatory requirements. This research contributes to the ongoing discourse on the role of AI in software engineering, highlighting its potential and current limitations in enhancing model transformation processes.

Being able to maintain the consistency between various different, but related models is an important enabler for model-based software engineering. Research on bidirectional transformations (bx) addresses this issue and has resulted in various and diverse formal foundations, approaches, tools, and application scenarios. In order to understand and compare different bx approaches, we have developed benchmarx, a benchmarking framework specifically for bx. Up until now, however, benchmarx has been limited to one-sided model synchronisation tasks, where only one of two related models can be changed at a time.As the more general case of concurrent model synchronisation is crucial for many practical applications of bx, we propose in this paper an extension to our bx benchmarking framework to support concurrent model synchronisation tasks, where two related models can both be changed concurrently and must then be synchronised to restore consistency. To evaluate our new extensions we present an update of an existing benchmarx example, families-to-persons, to include new test cases requiring concurrent synchronisation. We discuss some of the challenges involved in defining such a benchmark including handling conflicts, defining the expected behavior of the bx tool under test, and providing bx tools with enough freedom to reject some of the changes to either model. We also present a solution to the updated families-to-persons benchmarx example implemented using BXtend as a bx tool.

We are presenting our approach for interactive cultural heritage storytelling in WebXR. Therefore, we are describing our scenes’ structure consisting of (stylized) photospheres of the historic locations, 3D models of 3D-scanned historic artifacts and animated 2D textures of historic characters generated with a machine learning toolset. The result is a platform-independent web-application in an immersive interactive WebXR environment running in browsers on PCs, tablets, phones and XR headsets thanks to the underlying software based on the open-source framework A-Frame. Our pa- per describes the process, the results and the limitations in detail. The resulting application, designed for the Fichtelgebirge region in Upper Franconia, Germany, offers users an immersive digital time travel experience in the virtual space and within a museum setting connecting real artifacts and virtual stories.

Roboter, die autonom und flexibel arbeiten, könnten in Zukunft im Haushalt helfen. Um ihre Schritte zu planen, brauchen sie künstliche Intelligenz. Generative Sprachmodelle sollen dafür nicht nur Sätze oder Programmcode schreiben, sondern die Abläufe auch strukturieren.

Traditional spatial hypertext systems, predominantly limited to two-dimensional (2D) interfaces, offer limited support for addressing long debated inherent problems such as orientation difficulties and navigation in large information spaces. In this context, we present opportunities from interdisciplinary fields such as immersive analytics (IA) and embodied cognition that may mitigate some of these challenges. However, while some research has explored the extension of spatial hypertext to three dimensions, there is a lack of discussion on recent advances in virtual reality technologies and related fields, and their potential impact on immersive spatial hypertext systems. This paper addresses this gap by exploring the integration of immersive technologies into spatial hypertext systems, proposing a novel approach to enhance user engagement and comprehension through three-dimensional (3D) environments and multisensory interaction.

This paper explores the integration of hypertext structures within Virtual Reality (VR) environments, differentiating between two distinct design philosophies: VR as a native framework for 3D embodiment-enabled spaces similar to traditional 2D spatial hypertext, and utilizing hypertext to enhance VR experiences. Focusing on the latter approach, we propose an abstract knowledge layer that bridges typical VR systems and human thinking, thus facilitating the integration of human cognitive capabilities. Finally, we explore ethical implications of VR systems that arise in the presented context and propose hypertext as a paradigm to address some of these concerns.