Search

This paper introduces a novel method for numerically stabilizing sequential continuous adjoint flow solvers utilizing an elliptic relaxation strategy. The proposed approach is formulated as a Partial Differential Equation (PDE) containing a single user-defined parameter, which analytical investigations reveal to represent the filter width of a probabilistic density function or Gaussian kernel. Key properties of the approach include (a) smoothing features with redistribution capabilities while (b) preserving integral properties. The technique targets explicit adjoint cross-coupling terms, such as the Adjoint Transpose Convection (ATC) term, which frequently causes numerical instabilities, especially on unstructured grids common in industrial applications. A trade-off is made by sacrificing sensitivity consistency to achieve enhanced numerical robustness. The method is validated on a two-phase, laminar, two-dimensional cylinder flow test case at Re=20 and Fn=0.75, focusing on minimizing resistance or maximizing lift. A range of homogeneous and inhomogeneous filter widths is evaluated. Subsequently, the relaxation method is employed to stabilize adjoint simulations during shape optimizations that aim at drag reduction of ship hulls. Two case studies are considered: A model-scale bulk carrier traveling at Re=7.246E+06 and Fn=0.142 as well as a harbor ferry cruising at Re=2.43E+08 and Fn=0.4 in full-scale conditions. Both cases, characterized by unstructured grids prone to adjoint divergence, demonstrate the effectiveness of the proposed method in overcoming stability challenges. The resulting optimizations achieve superior outcomes compared to approaches that omit problematic coupling terms.

Engineering simulations are usually based on complex, grid-based, or mesh-free methods for solving partial differential equations. The results of these methods cover large fields of physical quantities at very many discrete spatial locations and temporal points. Efficient compression methods can be helpful for processing and reusing such large amounts of data. A compression technique is attractive if it causes only a small additional effort and the loss of information with strong compression is low. The paper presents the development of an incremental Singular Value Decomposition (SVD) strategy for compressing time-dependent particle simulation results. The approach is based on an algorithm that was previously developed for grid-based, regular snapshot data matrices. It is further developed here to process highly irregular data matrices generated by particle simulation methods during simulation. Various aspects important for information loss, computational effort and storage requirements are discussed, and corresponding solution techniques are investigated. These include the development of an adaptive rank truncation approach, the assessment of imputation strategies to close snapshot matrix gaps caused by temporarily inactive particles, a suggestion for sequencing the data history into temporal windows as well as bundling the SVD updates. The simulation-accompanying method is embedded in a parallel, industrialized Smoothed-Particle Hydrodynamics software and applied to several 2D and 3D test cases. The proposed approach reduces the memory requirement by about 90% and increases the computational effort by about 10%, while preserving the required accuracy. For the final application of a water turbine, the temporal evolution of the force and torque values for the compressed and simulated data is in excellent agreement.

Domain adaptation is a sub-field of machine learning that involves transferring knowledge from a source domain to perform the same task in the target domain. It is a typical challenge in machine learning that arises, e.g., when data is obtained from various sources or when using a data basis that changes over time. Recent advances in the field offer promising methods, but it is still challenging for researchers and practitioners to determine if domain adaptation is suitable for a given problem -- and, subsequently, to select the appropriate approach. This article employs design science research to develop a problem-oriented framework for domain adaptation, which is matured in three evaluation episodes. We describe a framework that distinguishes between five domain adaptation scenarios, provides recommendations for addressing each scenario, and offers guidelines for determining if a problem falls into one of these scenarios. During the multiple evaluation episodes, the framework is tested on artificial and real-world datasets and an experimental study involving 100 participants. The evaluation demonstrates that the framework has the explanatory power to capture any domain adaptation problem effectively. In summary, we provide clear guidance for researchers and practitioners who want to employ domain adaptation but lack in-depth knowledge of the possibilities.

Across various applications, humans increasingly use black-box artificial intelligence (AI) systems without insight into these systems' reasoning. To counter this opacity, explainable AI (XAI) methods promise enhanced transparency and interpretability. While recent studies have explored how XAI affects human-AI collaboration, few have examined the potential pitfalls caused by incorrect explanations. The implications for humans can be far-reaching but have not been explored extensively. To investigate this, we ran a study (n=160) on AI-assisted decision-making in which humans were supported by XAI. Our findings reveal a misinformation effect when incorrect explanations accompany correct AI advice with implications post-collaboration. This effect causes humans to infer flawed reasoning strategies, hindering task execution and demonstrating impaired procedural knowledge. Additionally, incorrect explanations compromise human-AI team-performance during collaboration. With our work, we contribute to HCI by providing empirical evidence for the negative consequences of incorrect explanations on humans post-collaboration and outlining guidelines for designers of AI.

The selection of algorithms is a crucial step in designing AI services for real-world time series classification use cases. Traditional methods such as neural architecture search, automated machine learning, combined algorithm selection, and hyperparameter optimizations are effective but require considerable computational resources and necessitate access to all data points to run their optimizations. In this work, we introduce a novel data fingerprint that describes any time series classification dataset in a privacy-preserving manner and provides insight into the algorithm selection problem without requiring training on the (unseen) dataset. By decomposing the multi-target regression problem, only our data fingerprints are used to estimate algorithm performance and uncertainty in a scalable and adaptable manner. Our approach is evaluated on the 112 University of California riverside benchmark datasets, demonstrating its effectiveness in predicting the performance of 35 state-of-the-art algorithms and providing valuable insights for effective algorithm selection in time series classification service systems, improving a naive baseline by 7.32% on average in estimating the mean performance and 15.81% in estimating the uncertainty., Comment: Hawaii International Conference on System Sciences (HICSS-58) 2025

Federated Learning presents a way to revolutionize AI applications by eliminating the necessity for data sharing. Yet, research has shown that information can still be extracted during training, making additional privacy-preserving measures such as differential privacy imperative. To implement real-world federated learning applications, fairness, ranging from a fair distribution of performance to non-discriminative behaviour, must be considered. Particularly in high-risk applications (e.g. healthcare), avoiding the repetition of past discriminatory errors is paramount. As recent research has demonstrated an inherent tension between privacy and fairness, we conduct a multivocal literature review to examine the current methods to integrate privacy and fairness in federated learning. Our analyses illustrate that the relationship between privacy and fairness has been neglected, posing a critical risk for real-world applications. We highlight the need to explore the relationship between privacy, fairness, and performance, advocating for the creation of integrated federated learning frameworks., Comment: Proceedings of the 19th International Conference on Wirtschaftsinformatik (WI), 2024

Scale-resolving flow simulations often feature several million [thousand] spatial [temporal] discrete degrees of freedom. When storing or re-using these data, e.g., to subsequently train some sort of data-based surrogate or compute consistent adjoint flow solutions, a brute-force storage approach is practically impossible. Therefore, -- mandatory incremental -- Reduced Order Modeling (ROM) approaches are an attractive alternative since only a specific time horizon is effectively stored. This bunched flow solution is then used to enhance the already computed ROM so that the allocated memory can be released and the procedure repeats. This paper utilizes an incremental truncated Singular Value Decomposition (itSVD) procedure to compress flow data resulting from scale-resolving flow simulations. To this end, two scenarios are considered, referring to an academic Large Eddy Simulation (LES) around a circular cylinder at Re=1.4E+05 as well as an industrial case that employs a hybrid filtered/averaged Detached Eddy Simulation (DES) on the flow around the superstructure of a full-scale feeder ship at Re=5E+08. The paper's central focus is on an aspect of practical relevance: how much information of the computed scale-resolving solution should be used by the ROM, i.e., how much redundancy occurs in the resolved turbulent fluctuations that favors ROM. In the course of the tSVD employed, this goes hand in hand with the question of "how many singular values of the snapshot-matrix should be neglected (or considered)" -- without (a) re-running the simulation several times in a try-and-error procedure and (b) still obtain compressed results below the model and discretization error. An adaptive strategy is utilized to obtain a fully adaptive data reduction of O(95) percent via a computational overhead of O(10) percent with a mean accuracy of reconstructed local and global flow data of O(0.1) percent.

Artificial intelligence (AI) systems have become an indispensable component of modern technology. However, research on human behavioral responses is lagging behind, i.e., the research into human reliance on AI advice (AI reliance). Current shortcomings in the literature include the unclear influences on AI reliance, lack of external validity, conflicting approaches to measuring reliance, and disregard for a change in reliance over time. Promising avenues for future research include reliance on generative AI output and reliance in multi-user situations. In conclusion, we present a morphological box that serves as a guide for research on AI reliance.

Literature review requires researchers to synthesize a large amount of information and is increasingly challenging as the scientific literature expands. In this work, we investigate the potential of LLMs for producing hierarchical organizations of scientific studies to assist researchers with literature review. We define hierarchical organizations as tree structures where nodes refer to topical categories and every node is linked to the studies assigned to that category. Our naive LLM-based pipeline for hierarchy generation from a set of studies produces promising yet imperfect hierarchies, motivating us to collect CHIME, an expert-curated dataset for this task focused on biomedicine. Given the challenging and time-consuming nature of building hierarchies from scratch, we use a human-in-the-loop process in which experts correct errors (both links between categories and study assignment) in LLM-generated hierarchies. CHIME contains 2,174 LLM-generated hierarchies covering 472 topics, and expert-corrected hierarchies for a subset of 100 topics. Expert corrections allow us to quantify LLM performance, and we find that while they are quite good at generating and organizing categories, their assignment of studies to categories could be improved. We attempt to train a corrector model with human feedback which improves study assignment by 12.6 F1 points. We release our dataset and models to encourage research on developing better assistive tools for literature review., Comment: 2024 ACL Findings

The rhythmic pumping motion of the heart stands as a cornerstone in life, as it circulates blood to the entire human body through a series of carefully timed contractions of the individual chambers. Changes in the size, shape and movement of the chambers can be important markers for cardiac disease and modeling this in relation to clinical demography or disease is therefore of interest. Existing methods for spatio-temporal modeling of the human heart require shape correspondence over time or suffer from large memory requirements, making it difficult to use for complex anatomies. We introduce a novel conditional generative model, where the shape and movement is modeled implicitly in the form of a spatio-temporal neural distance field and conditioned on clinical demography. The model is based on an auto-decoder architecture and aims to disentangle the individual variations from that related to the clinical demography. It is tested on the left atrium (including the left atrial appendage), where it outperforms current state-of-the-art methods for anatomical sequence completion and generates synthetic sequences that realistically mimics the shape and motion of the real left atrium. In practice, this means we can infer functional measurements from a static image, generate synthetic populations with specified demography or disease and investigate how non-imaging clinical data effect the shape and motion of cardiac anatomies., Comment: Accepted for MICCAI2024

In the landscape of generative artificial intelligence, diffusion-based models have emerged as a promising method for generating synthetic images. However, the application of diffusion models poses numerous challenges, particularly concerning data availability, computational requirements, and privacy. Traditional approaches to address these shortcomings, like federated learning, often impose significant computational burdens on individual clients, especially those with constrained resources. In response to these challenges, we introduce a novel approach for distributed collaborative diffusion models inspired by split learning. Our approach facilitates collaborative training of diffusion models while alleviating client computational burdens during image synthesis. This reduced computational burden is achieved by retaining data and computationally inexpensive processes locally at each client while outsourcing the computationally expensive processes to shared, more efficient server resources. Through experiments on the common CelebA dataset, our approach demonstrates enhanced privacy by reducing the necessity for sharing raw data. These capabilities hold significant potential across various application areas, including the design of edge computing solutions. Thus, our work advances distributed machine learning by contributing to the evolution of collaborative diffusion models., Comment: 13 pages, 7 figures

AI is becoming increasingly common across different domains. However, as sophisticated AI-based systems are often black-boxed, rendering the decision-making logic opaque, users find it challenging to comply with their recommendations. Although researchers are investigating Explainable AI (XAI) to increase the transparency of the underlying machine learning models, it is unclear what types of explanations are effective and what other factors increase compliance. To better understand the interplay of these factors, we conducted an experiment with 562 participants who were presented with the recommendations of an AI and two different types of XAI. We find that users' compliance increases with the introduction of XAI but is also affected by AI literacy. We also find that the relationships between AI literacy XAI and users' compliance are mediated by the users' mental model of AI. Our study has several implications for successfully designing AI-based systems utilizing XAI.

Progress in AI is often demonstrated by new models claiming improved performance on tasks measuring model capabilities. Evaluating language models in particular is challenging, as small changes to how a model is evaluated on a task can lead to large changes in measured performance. There is no common standard setup, so different models are evaluated on the same tasks in different ways, leading to claims about which models perform best not being reproducible. We propose OLMES, a completely documented, practical, open standard for reproducible LLM evaluations. In developing this standard, we identify and review the varying factors in evaluation practices adopted by the community - such as details of prompt formatting, choice of in-context examples, probability normalizations, and task formulation. In particular, OLMES supports meaningful comparisons between smaller base models that require the unnatural "cloze" formulation of multiple-choice questions against larger models that can utilize the original formulation. OLMES includes well-considered recommendations guided by results from existing literature as well as new experiments investigating open questions.

In numerous high-stakes domains, training novices via conventional learning systems does not suffice. To impart tacit knowledge, experts' hands-on guidance is imperative. However, training novices by experts is costly and time-consuming, increasing the need for alternatives. Explainable artificial intelligence (XAI) has conventionally been used to make black-box artificial intelligence systems interpretable. In this work, we utilize XAI as an alternative: An (X)AI system is trained on experts' past decisions and is then employed to teach novices by providing examples coupled with explanations. In a study with 249 participants, we measure the effectiveness of such an approach for a classification task. We show that (X)AI-based learning systems are able to induce learning in novices and that their cognitive styles moderate learning. Thus, we take the first steps to reveal the impact of XAI on human learning and point AI developers to future options to tailor the design of (X)AI-based learning systems., Comment: Thirty-Second European Conference on Information Systems (ECIS 2024), Paphos, Cyprus

As organizations face the challenges of processing exponentially growing data volumes, their reliance on analytics to unlock value from this data has intensified. However, the intricacies of big data, such as its extensive feature sets, pose significant challenges. A crucial step in leveraging this data for insightful analysis is an in-depth understanding of both the data and its domain. Yet, existing literature presents a fragmented picture of what comprises an effective understanding of data and domain, varying significantly in depth and focus. To address this research gap, we conduct a systematic literature review, aiming to delineate the dimensions of data understanding. We identify five dimensions: Foundations, Collection & Selection, Contextualization & Integration, Exploration & Discovery, and Insights. These dimensions collectively form a comprehensive framework for data understanding, providing guidance for organizations seeking meaningful insights from complex datasets. This study synthesizes the current state of knowledge and lays the groundwork for further exploration., Comment: Accepted at 32nd European Conference on Information Systems (2024)

The widespread use of artificial intelligence (AI) systems across various domains is increasingly surfacing issues related to algorithmic fairness, especially in high-stakes scenarios. Thus, critical considerations of how fairness in AI systems might be improved -- and what measures are available to aid this process -- are overdue. Many researchers and policymakers see explainable AI (XAI) as a promising way to increase fairness in AI systems. However, there is a wide variety of XAI methods and fairness conceptions expressing different desiderata, and the precise connections between XAI and fairness remain largely nebulous. Besides, different measures to increase algorithmic fairness might be applicable at different points throughout an AI system's lifecycle. Yet, there currently is no coherent mapping of fairness desiderata along the AI lifecycle. In this paper, we we distill eight fairness desiderata, map them along the AI lifecycle, and discuss how XAI could help address each of them. We hope to provide orientation for practical applications and to inspire XAI research specifically focused on these fairness desiderata.

Generative AI, in general, and synthetic visual data generation, in specific, hold much promise for benefiting surgical training by providing photorealism to simulation environments. Current training methods primarily rely on reading materials and observing live surgeries, which can be time-consuming and impractical. In this work, we take a significant step towards improving the training process. Specifically, we use diffusion models in combination with a zero-shot video diffusion method to interactively generate realistic laparoscopic images and videos by specifying a surgical action through text and guiding the generation with tool positions through segmentation masks. We demonstrate the performance of our approach using the publicly available Cholec dataset family and evaluate the fidelity and factual correctness of our generated images using a surgical action recognition model as well as the pixel-wise F1-score for the spatial control of tool generation. We achieve an FID of 38.097 and an F1-score of 0.71., Comment: 7 pages, 4 figures

The topic of fairness in AI, as debated in the FATE (Fairness, Accountability, Transparency, and Ethics in AI) communities, has sparked meaningful discussions in the past years. However, from a legal perspective, particularly from the perspective of European Union law, many open questions remain. Whereas algorithmic fairness aims to mitigate structural inequalities at design-level, European non-discrimination law is tailored to individual cases of discrimination after an AI model has been deployed. The AI Act might present a tremendous step towards bridging these two approaches by shifting non-discrimination responsibilities into the design stage of AI models. Based on an integrative reading of the AI Act, we comment on legal as well as technical enforcement problems and propose practical implications on bias detection and bias correction in order to specify and comply with specific technical requirements.

Artificial intelligence (AI) has the potential to significantly enhance human performance across various domains. Ideally, collaboration between humans and AI should result in complementary team performance (CTP) -- a level of performance that neither of them can attain individually. So far, however, CTP has rarely been observed, suggesting an insufficient understanding of the principle and the application of complementarity. Therefore, we develop a general concept of complementarity and formalize its theoretical potential as well as the actual realized effect in decision-making situations. Moreover, we identify information and capability asymmetry as the two key sources of complementarity. Finally, we illustrate the impact of each source on complementarity potential and effect in two empirical studies. Our work provides researchers with a comprehensive theoretical foundation of human-AI complementarity in decision-making and demonstrates that leveraging these sources constitutes a viable pathway towards designing effective human-AI collaboration, i.e., the realization of CTP.

Large language models (LLMs) adapted to follow user instructions are now widely deployed as conversational agents. In this work, we examine one increasingly common instruction-following task: providing writing assistance to compose a long-form answer. To evaluate the capabilities of current LLMs on this task, we construct KIWI, a dataset of knowledge-intensive writing instructions in the scientific domain. Given a research question, an initial model-generated answer and a set of relevant papers, an expert annotator iteratively issues instructions for the model to revise and improve its answer. We collect 1,260 interaction turns from 234 interaction sessions with three state-of-the-art LLMs. Each turn includes a user instruction, a model response, and a human evaluation of the model response. Through a detailed analysis of the collected responses, we find that all models struggle to incorporate new information into an existing answer, and to perform precise and unambiguous edits. Further, we find that models struggle to judge whether their outputs successfully followed user instructions, with accuracy at least 10 points short of human agreement. Our findings indicate that KIWI will be a valuable resource to measure progress and improve LLMs' instruction-following capabilities for knowledge intensive writing tasks.

The Solar energetic particle analysis platform for the inner heliosphere (SERPENTINE) project presents it's new multi-spacecraft SEP event catalog for events observed in solar cycle 25. Observations from five different viewpoints are utilized, provided by Solar Orbiter, Parker Solar Probe, STEREO A, BepiColombo, and the near-Earth spacecraft Wind and SOHO. The catalog contains key SEP parameters for 25-40 MeV protons, 1 MeV electrons, and 100 keV electrons. Furthermore, basic parameters of the associated flare and type-II radio burst are listed, as well as the coordinates of the observer and solar source locations. SEP onset times are determined using the Poisson-CUSUM method. SEP peak times and intensities refer to the global intensity maximum. If different viewing directions are available, we use the one with the earliest onset for the onset determination and the one with the highest peak intensity for the peak identification. Associated flares are identified using observations from near Earth and Solar Orbiter. Associated type II radio bursts are determined from ground-based observations in the metric frequency range and from spacecraft observations in the decametric range. The current version of the catalog contains 45 multi-spacecraft events observed in the period from Nov 2020 until May 2023, of which 13 were widespread events and four were classified as narrow-spread events. Using X-ray observations by GOES/XRS and Solar Orbiter/STIX, we were able to identify the associated flare in all but four events. Using ground-based and space-borne radio observations, we found an associated type-II radio burst for 40 events. In total, the catalog contains 142 single event observations, of which 20 (45) have been observed at radial distances below 0.6 AU (0.8 AU).

In the landscape of generative artificial intelligence, diffusion-based models present challenges for socio-technical systems in data requirements and privacy. Traditional approaches like federated learning distribute the learning process but strain individual clients, especially with constrained resources (e.g., edge devices). In response to these challenges, we introduce CollaFuse, a novel framework inspired by split learning. Tailored for efficient and collaborative use of denoising diffusion probabilistic models, CollaFuse enables shared server training and inference, alleviating client computational burdens. This is achieved by retaining data and computationally inexpensive GPU processes locally at each client while outsourcing the computationally expensive processes to the shared server. Demonstrated in a healthcare context, CollaFuse enhances privacy by highly reducing the need for sensitive information sharing. These capabilities hold the potential to impact various application areas, such as the design of edge computing solutions, healthcare research, or autonomous driving. In essence, our work advances distributed machine learning, shaping the future of collaborative GenAI networks., Comment: Thirty-Second European Conference on Information Systems (ECIS 2024)

Aims. We studied the first multi-spacecraft high-energy solar energetic particle (SEP) event of solar cycle 25, which triggered a ground level enhancement (GLE) on 28 October 2021, using data from multiple observers that were widely distributed throughout the heliosphere. Methods. We performed detail modelling of the shock wave and investigated the magnetic connectivity of each observer to the solar surface and examined the shock magnetic connection. We performed 3D SEP propagation simulations to investigate the role of particle transport in the distribution of SEPs to distant magnetically connected observers. Results. Observations and modelling show that a strong shock wave formed promptly in the low corona. At the SEP release time windows, we find a connection with the shock for all the observers. PSP, STA, and Solar Orbiter were connected to strong shock regions with high Mach numbers, whereas the Earth and other observers were connected to lower Mach numbers. The SEP spectral properties near Earth demonstrate two power laws, with a harder (softer) spectrum in the low-energy (high-energy) range. Composition observations from SIS (and near-Earth instruments) show no serious enhancement of flare-accelerated material. Conclusions. A possible scenario consistent with the observations and our analysis indicates that high-energy SEPs at PSP, STA, and Solar Orbiter were dominated by particle acceleration and injection by the shock, whereas high-energy SEPs that reached near-Earth space were associated with a weaker shock; it is likely that efficient transport of particles from a wide injection source contributed to the observed high-energy SEPs. Our study cannot exclude a contribution from a flare-related process; however, composition observations show no evidence of an impulsive composition of suprathermals during the event, suggestive of a non-dominant flare-related process.

The integration of artificial intelligence (AI) into human decision-making processes at the workplace presents both opportunities and challenges. One promising approach to leverage existing complementary capabilities is allowing humans to delegate individual instances of decision tasks to AI. However, enabling humans to delegate instances effectively requires them to assess several factors. One key factor is the analysis of both their own capabilities and those of the AI in the context of the given task. In this work, we conduct a behavioral study to explore the effects of providing contextual information to support this delegation decision. Specifically, we investigate how contextual information about the AI and the task domain influence humans' delegation decisions to an AI and their impact on the human-AI team performance. Our findings reveal that access to contextual information significantly improves human-AI team performance in delegation settings. Finally, we show that the delegation behavior changes with the different types of contextual information. Overall, this research advances the understanding of computer-supported, collaborative work and provides actionable insights for designing more effective collaborative systems.

The demand for high-speed data is exponentially growing. To conquer this, optical networks underwent significant changes getting more complex and versatile. The increasing complexity necessitates the fault management to be more adaptive to enhance network assurance. In this paper, we experimentally compare the performance of soft-failure management of different machine learning algorithms. We further introduce a machine-learning based soft-failure management framework. It utilizes a variational autoencoder based generative adversarial network (VAE-GAN) running on optical spectral data obtained by optical spectrum analyzers. The framework is able to reliably run on a fraction of available training data as well as identifying unknown failure types. The investigations show, that the VAE-GAN outperforms the other machine learning algorithms when up to 10\% of the total training data is available in identification tasks. Furthermore, the advanced training mechanism for the GAN shows a high F1-score for unknown spectrum identification. The failure localization comparison shows the advantage of a low complexity neural network in combination with a VAE over established machine learning algorithms.

In this paper we explore the idea of using multi-spacecraft observations of Jovian electrons to measure the 3D distribution of these particles in the inner heliosphere. We present simulations of Jovian electron intensities along selected spacecraft trajectories for 2021 and compare these, admittedly qualitatively, to these measurements. Using the data-model comparison we emphasize how such a study can be used to constrain the transport parameters in the inner heliosphere, and how this can lead to additional insight into energetic particle transport. Model results are also shown along the expected trajectories of selected spacecraft, including the off-ecliptic phase of the Solar Orbiter mission from 2025 onward. Lastly, we revisit the use of historical data and discuss upcoming missions that may contribute to Jovian electron measurements., Comment: Accepted for publication in ApJ

Recent advances in synthetic imaging open up opportunities for obtaining additional data in the field of surgical imaging. This data can provide reliable supplements supporting surgical applications and decision-making through computer vision. Particularly the field of image-guided surgery, such as laparoscopic and robotic-assisted surgery, benefits strongly from synthetic image datasets and virtual surgical training methods. Our study presents an intuitive approach for generating synthetic laparoscopic images from short text prompts using diffusion-based generative models. We demonstrate the usage of state-of-the-art text-to-image architectures in the context of laparoscopic imaging with regard to the surgical removal of the gallbladder as an example. Results on fidelity and diversity demonstrate that diffusion-based models can acquire knowledge about the style and semantics in the field of image-guided surgery. A validation study with a human assessment survey underlines the realistic nature of our synthetic data, as medical personnel detects actual images in a pool with generated images causing a false-positive rate of 66%. In addition, the investigation of a state-of-the-art machine learning model to recognize surgical actions indicates enhanced results when trained with additional generated images of up to 5.20%. Overall, the achieved image quality contributes to the usage of computer-generated images in surgical applications and enhances its path to maturity.

A significant challenge in image-guided surgery is the accurate measurement task of relevant structures such as vessel segments, resection margins, or bowel lengths. While this task is an essential component of many surgeries, it involves substantial human effort and is prone to inaccuracies. In this paper, we develop a novel human-AI-based method for laparoscopic measurements utilizing stereo vision that has been guided by practicing surgeons. Based on a holistic qualitative requirements analysis, this work proposes a comprehensive measurement method, which comprises state-of-the-art machine learning architectures, such as RAFT-Stereo and YOLOv8. The developed method is assessed in various realistic experimental evaluation environments. Our results outline the potential of our method achieving high accuracies in distance measurements with errors below 1 mm. Furthermore, on-surface measurements demonstrate robustness when applied in challenging environments with textureless regions. Overall, by addressing the inherent challenges of image-guided surgery, we lay the foundation for a more robust and accurate solution for intra- and postoperative measurements, enabling more precise, safe, and efficient surgical procedures., Comment: 38th AAAI Conference on Artificial Intelligence (AAAI-24)

Extracting fine-grained experimental findings from literature can provide dramatic utility for scientific applications. Prior work has developed annotation schemas and datasets for limited aspects of this problem, failing to capture the real-world complexity and nuance required. Focusing on biomedicine, this work presents CARE -- a new IE dataset for the task of extracting clinical findings. We develop a new annotation schema capturing fine-grained findings as n-ary relations between entities and attributes, which unifies phenomena challenging for current IE systems such as discontinuous entity spans, nested relations, variable arity n-ary relations and numeric results in a single schema. We collect extensive annotations for 700 abstracts from two sources: clinical trials and case reports. We also demonstrate the generalizability of our schema to the computer science and materials science domains. We benchmark state-of-the-art IE systems on CARE, showing that even models such as GPT4 struggle. We release our resources to advance research on extracting and aggregating literature findings., Comment: To appear at NAACL Findings 2024

The joint alignment of multivariate functional data plays an important role in various fields such as signal processing, neuroscience and medicine, including the statistical analysis of data from wearable devices. Traditional methods often ignore the phase variability and instead focus on the variability in the observed amplitude. We present a novel method for joint alignment of multivariate quasi-periodic functions using deep neural networks, decomposing, but retaining all the information in the data by preserving both phase and amplitude variability. Our proposed neural network uses a special activation of the output that builds on the unit simplex transformation, and we utilize a loss function based on the Fisher-Rao metric to train our model. Furthermore, our method is unsupervised and can provide an optimal common template function as well as subject-specific templates. We demonstrate our method on two simulated datasets and one real example, comprising data from 12-lead 10s electrocardiogram recordings., Comment: 28 pages, 6 figures

Collisionless shock waves have long been considered amongst the most prolific particle accelerators in the universe. Shocks alter the plasma they propagate through and often exhibit complex evolution across multiple scales. Interplanetary (IP) traveling shocks have been recorded in-situ for over half a century and act as a natural laboratory for experimentally verifying various aspects of large-scale collisionless shocks. A fundamentally interesting problem in both helio and astrophysics is the acceleration of electrons to relativistic energies (more than 300 keV) by traveling shocks. This letter presents first observations of field-aligned beams of relativistic electrons upstream of an IP shock observed thanks to the instrumental capabilities of Solar Orbiter. This study aims to present the characteristics of the electron beams close to the source and contribute towards understanding their acceleration mechanism. On 25 July 2022, Solar Orbiter encountered an IP shock at 0.98 AU. The shock was associated with an energetic storm particle event which also featured upstream field-aligned relativistic electron beams observed 14 minutes prior to the actual shock crossing. The distance of the beam's origin was investigated using a velocity dispersion analysis (VDA). Peak-intensity energy spectra were anaylzed and compared with those obtained from a semi-analytical fast-Fermi acceleration model. By leveraging Solar Orbiter's high-time resolution Energetic Particle Detector (EPD), we have successfully showcased an IP shock's ability to accelerate relativistic electron beams. Our proposed acceleration mechanism offers an explanation for the observed electron beam and its characteristics, while we also explore the potential contributions of more complex mechanisms., Comment: Main text: 6 pages, 2 figures. Supplementary material: 6 pages, 7 figures

In this critical survey, we analyze typical claims on the relationship between explainable AI (XAI) and fairness to disentangle the multidimensional relationship between these two concepts. Based on a systematic literature review and a subsequent qualitative content analysis, we identify seven archetypal claims from 175 scientific articles on the alleged fairness benefits of XAI. We present crucial caveats with respect to these claims and provide an entry point for future discussions around the potentials and limitations of XAI for specific fairness desiderata. Importantly, we notice that claims are often (i) vague and simplistic, (ii) lacking normative grounding, or (iii) poorly aligned with the actual capabilities of XAI. We suggest to conceive XAI not as an ethical panacea but as one of many tools to approach the multidimensional, sociotechnical challenge of algorithmic fairness. Moreover, when making a claim about XAI and fairness, we emphasize the need to be more specific about what kind of XAI method is used, which fairness desideratum it refers to, how exactly it enables fairness, and who is the stakeholder that benefits from XAI., Comment: ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT '24)

The true potential of human-AI collaboration lies in exploiting the complementary capabilities of humans and AI to achieve a joint performance superior to that of the individual AI or human, i.e., to achieve complementary team performance (CTP). To realize this complementarity potential, humans need to exercise discretion in following AI 's advice, i.e., appropriately relying on the AI's advice. While previous work has focused on building a mental model of the AI to assess AI recommendations, recent research has shown that the mental model alone cannot explain appropriate reliance. We hypothesize that, in addition to the mental model, human learning is a key mediator of appropriate reliance and, thus, CTP. In this study, we demonstrate the relationship between learning and appropriate reliance in an experiment with 100 participants. This work provides fundamental concepts for analyzing reliance and derives implications for the effective design of human-AI decision-making.

We explore the implementation of deep learning techniques for precise building damage assessment in the context of natural hazards, utilizing remote sensing data. The xBD dataset, comprising diverse disaster events from across the globe, serves as the primary focus, facilitating the evaluation of deep learning models. We tackle the challenges of generalization to novel disasters and regions while accounting for the influence of low-quality and noisy labels inherent in natural hazard data. Furthermore, our investigation quantitatively establishes that the minimum satellite imagery resolution essential for effective building damage detection is 3 meters and below 1 meter for classification using symmetric and asymmetric resolution perturbation analyses. To achieve robust and accurate evaluations of building damage detection and classification, we evaluated different deep learning models with residual, squeeze and excitation, and dual path network backbones, as well as ensemble techniques. Overall, the U-Net Siamese network ensemble with F-1 score of 0.812 performed the best against the xView2 challenge benchmark. Additionally, we evaluate a Universal model trained on all hazards against a flood expert model and investigate generalization gaps across events, and out of distribution from field data in the Ahr Valley. Our research findings showcase the potential and limitations of advanced AI solutions in enhancing the impact assessment of climate change-induced extreme weather events, such as floods and hurricanes. These insights have implications for disaster impact assessment in the face of escalating climate challenges., Comment: 9 pages, 4 figures

Explainability techniques are rapidly being developed to improve human-AI decision-making across various cooperative work settings. Consequently, previous research has evaluated how decision-makers collaborate with imperfect AI by investigating appropriate reliance and task performance with the aim of designing more human-centered computer-supported collaborative tools. Several human-centered explainable AI (XAI) techniques have been proposed in hopes of improving decision-makers' collaboration with AI; however, these techniques are grounded in findings from previous studies that primarily focus on the impact of incorrect AI advice. Few studies acknowledge the possibility of the explanations being incorrect even if the AI advice is correct. Thus, it is crucial to understand how imperfect XAI affects human-AI decision-making. In this work, we contribute a robust, mixed-methods user study with 136 participants to evaluate how incorrect explanations influence humans' decision-making behavior in a bird species identification task, taking into account their level of expertise and an explanation's level of assertiveness. Our findings reveal the influence of imperfect XAI and humans' level of expertise on their reliance on AI and human-AI team performance. We also discuss how explanations can deceive decision-makers during human-AI collaboration. Hence, we shed light on the impacts of imperfect XAI in the field of computer-supported cooperative work and provide guidelines for designers of human-AI collaboration systems., Comment: Accepted to ACM CSCW 2024. 27 pages, 9 figures, 1 table, additional figures/table in the appendix

We introduce the task of automatically revising scientific papers based on peer feedback and release ARIES, a dataset of review comments and their corresponding paper edits. The data is drawn from real reviewer-author interactions from computer science, and we provide labels linking each reviewer comment to the specific paper edits made by the author in response. We automatically create a high-precision silver training set, as well as an expert-labeled test set that shows high inter-annotator agreement. In experiments with 10 models covering the state of the art, we find that they struggle even to identify which edits correspond to a comment -- especially when the relationship between the edit and the comment is indirect and requires reasoning to uncover. We also extensively analyze GPT-4's ability to generate edits given a comment and the original paper. We find that it often succeeds on a superficial level, but tends to rigidly follow the wording of the feedback rather than the underlying intent, and lacks technical details compared to human-written edits., Comment: ACL 2024, 10 pages, 2 figures