Level design is one of the most labor-intensive processes in video game development – especially because communicating a creative vision across designers, artists, writers, and gameplay engineers requires extensive iterative refinement. Traditionally, this involves rounds of white boxing and set dressing, which distributes labor effectively but limits rapid exploration and creative experimentation. Recent advances in AI-driven image generation offer timely opportunities to transform these workflows, but risk losing control to the model’s interpretation and capabilities. We investigate the impact of generative AI on designers’ control, expressiveness, and efficiency through a mixed-methods study (n=20), comparing drawing (full control), text-to-image (full AI), and our approach: a visualization pipeline combining generative AI with user-centered spatial control. It succeeded in enhancing visual expressiveness and sense of control over bare AI, matched manual drawing (without necessitating advanced skills), and enabled faster iteration – highlighting the potential of giving back control to creative visionaries.

While multimodal survival prediction models are increasingly accurate, their complexity often reduces interpretability, limiting insight into how different data sources influence predictions. To address this, we introduce DIMAFx, an explainable multimodal framework for cancer survival prediction that produces disentangled, interpretable modality-specific and modality-shared representations from histopathology whole-slide images and transcriptomics data. Across four TCGA cancer cohorts, DIMAFx achieves survival prediction performance competitive with the state of the art and consistently stronger representation disentanglement. Leveraging its interpretable design, SHapley Additive exPlanations, and pathologist-in-the-loop annotations, DIMAFx facilitates systematic investigation of key multimodal interactions and the biological information encoded in the multimodal, disentangled representations. In breast cancer survival prediction, the most predictive features contain modality-shared information, including one capturing solid tumor morphology contextualized primarily by late estrogen response, where higher-grade morphology aligned with pathway downregulation was associated with increased risk, consistent with known breast cancer biology. Key modality-specific features capture microenvironmental signals from interacting adipose and stromal morphologies. These results show that DIMAFx substantially narrows the gap between performance and interpretability, supporting the application of such models in precision oncology.

ABSTRACT Traditional physics‐based fluid simulations typically rely on manual modeling and incremental adjustments to achieve desired effects, which can limit objectivity and generalizability to new scenarios. To address these challenges, we propose a novel neural fluid simulator that integrates visual priors from 2D image sequences with physically constrained continuous convolution. Specifically, we extract and refine point clouds from image sequences, then infer the kinetic properties of the fluid. We introduce an energy‐based physical constraint and incorporate it into a continuous convolution solver. By iteratively optimizing these inputs to enforce physical laws—particularly incompressibility—the solver produces accurate fluid motion predictions. Our approach uniquely combines visual data and physical constraints, enhancing the realism and accuracy while providing stronger generalization of fluid simulations.

Real-world decision making often unfolds in fluid, uncertain, and ill-defined contexts where objectives shift, data are incomplete, and non-quantifiable factors such as social values, ethics, and institutional constraints play critical roles. Conventional AI and decision-support systems assume fixed criteria and stable data, leaving these contexts underserved. Building on an interdisciplinary definition of decision making attentive to its ill-defined forms, we introduce DARE, an explainable AI and visualization framework that complements the FAIR data principles with the DARE principles: Deliberation, Agency, Resilience, and Empathy, which emphasize dialogue, human control, adaptability, and human sensitivity in design. DARE conceptualizes decision making as an iterative alignment of human-defined criteria with algorithmic representations through which decision structure gradually emerges. We revisit existing AI paradigms through this lens and illustrate how weak supervision and concept-based modeling exemplify this process by connecting heuristic human reasoning to interpretable model concepts. Input visualization serves as the expressive layer that captures evolving, qualitative, and uncertain reasoning through interaction, allowing humans to externalize and refine decision logic before formalization. Explainability in DARE arises not from post-hoc justification but from the continuous visibility of how human and algorithmic reasoning co-develop. Uncertainty is treated as an inherent dimension of deliberation, something to represent, navigate, and learn from within the decision process, while human and algorithmic heuristics are regarded not as truths or biases but as evolving hypotheses to examine and refine through interaction. Together, these elements support human-AI decision making that remains transparent, adaptable, and grounded in human judgment across value-laden and ill-defined contexts.

We present a new nonlinear dimensionality reduction method, MAPLE, that enhances UMAP by improving manifold modeling. MAPLE employs a self-supervised learning approach to more efficiently encode low-dimensional manifold geometry. Central to this approach are maximum manifold capacity representations (MMCRs), which help untangle complex manifolds by compressing variances among locally similar data points while amplifying variance among dissimilar data points. This design is particularly effective for high-dimensional data with substantial intra-cluster variance and curved manifold structures, such as biological or image data. Our qualitative and quantitative evaluations demonstrate that MAPLE can produce clearer visual cluster separations and finer subcluster resolution than UMAP while maintaining a tractable computational cost.

Judging the similarity of visualizations is crucial to various applications, such as visualization-based search and visualization recommendation systems.Recent studies show deep-feature-based similarity metrics correlate well with perceptual judgments of image similarity and serve as effective loss functions for tasks like image super-resolution and style transfer.We explore the application of such metrics to judgments of visualization similarity.We extend a similarity metric using five ML architectures and three pre-trained weight sets.We replicate results from previous crowdsourced studies on scatterplot and visual channel similarity perception.Notably, our metric using pre-trained ImageNet weights outperformed gradient-descent tuned MS-SSIM, a multi-scale similarity metric based on luminance, contrast, and structure.Our work contributes to understanding how deep-feature-based metrics can enhance similarity assessments in visualization, potentially improving visual analysis tools and techniques.Supplementary materials are available at https://osf.io/dj2ms/.

ABSTRACT The dynamic interface prediction of multi‐density fluids presents a fundamental challenge across computational fluid dynamics and graphics, rooted in nonlinear momentum transfer. We present Density‐Conditioned Dynamic Convolution, a novel neural operator framework that establishes differentiable density‐dynamics mapping through decoupled operator response. The core theoretical advancement lies in continuously adaptive neighborhood kernels that transform local density distributions into tunable filters, enabling unified representation from homogeneous media to multi‐phase fluid. Experiments demonstrate autonomous evolution of physically consistent interface separation patterns in density contrast scenarios, including cocktail and bidirectional hourglass flow. Quantitative evaluation shows improved computational efficiency compared to a SPH method and qualitatively plausible interface dynamics, with a larger time step size.

As deep neural networks are more commonly deployed in high-stakes domains, their black-box nature makes uncertainty quantification challenging. We investigate the effects of presenting conformal prediction sets—a distribution-free class of methods for generating prediction sets with specified coverage—to express uncertainty in AI-advised decision-making. Through a large online experiment, we compare the utility of conformal prediction sets to displays of Top-1 and Top-k predictions for AI-advised image labeling. In a pre-registered analysis, we find that the utility of prediction sets for accuracy varies with the difficulty of the task: while they result in accuracy on par with or less than Top-1 and Top-k displays for easy images, prediction sets excel at assisting humans in labeling out-of-distribution (OOD) images, especially when the set size is small. Our results empirically pinpoint practical challenges of conformal prediction sets and provide implications on how to incorporate them for real-world decision-making.

Abstract As the complexity of machine learning (ML) models increases and their application in different (and critical) domains grows, there is a strong demand for more interpretable and trustworthy ML. A direct, model‐agnostic, way to interpret such models is to train surrogate models—such as rule sets and decision trees—that sufficiently approximate the original ones while being simpler and easier‐to‐explain. Yet, rule sets can become very lengthy, with many if–else statements, and decision tree depth grows rapidly when accurately emulating complex ML models. In such cases, both approaches can fail to meet their core goal—providing users with model interpretability. To tackle this, we propose DeforestVis, a visual analytics tool that offers summarization of the behaviour of complex ML models by providing surrogate decision stumps (one‐level decision trees) generated with the Adaptive Boosting (AdaBoost) technique. DeforestVis helps users to explore the complexity versus fidelity trade‐off by incrementally generating more stumps, creating attribute‐based explanations with weighted stumps to justify decision making, and analysing the impact of rule overriding on training instance allocation between one or more stumps. An independent test set allows users to monitor the effectiveness of manual rule changes and form hypotheses based on case‐by‐case analyses. We show the applicability and usefulness of DeforestVis with two use cases and expert interviews with data analysts and model developers.

Stacking (or stacked generalization) is an ensemble learning method with one main distinctiveness from the rest: even though several base models are trained on the original data set, their predictions are further used as input data for one or more metamodels arranged in at least one extra layer. Composing a stack of models can produce high-performance outcomes, but it usually involves a trial-and-error process. Therefore, our previously developed visual analytics sys-tem, StackGenVis, was mainly designed to assist users in choosing a set of top-performing and diverse models by measuring their predictive performance. However, it only employs a single logistic regression metamodel. In this paper, we investigate the impact of alternative metamodels on the performance of stacking ensembles using a novel visualization tool, called MetaStackVis. Our interactive tool helps users to visually explore different singular and pairs of metamodels according to their predictive probabilities and multiple validation metrics, as well as their ability to predict specific problematic data instances. MetaStackVis was evaluated with a usage scenario based on a medical data set and via expert interviews.

Abstract Despite the tremendous advances in machine learning (ML), training with imbalanced data still poses challenges in many real‐world applications. Among a series of diverse techniques to solve this problem, sampling algorithms are regarded as an efficient solution. However, the problem is more fundamental, with many works emphasizing the importance of instance hardness. This issue refers to the significance of managing unsafe or potentially noisy instances that are more likely to be misclassified and serve as the root cause of poor classification performance. This paper introduces HardVis, a visual analytics system designed to handle instance hardness mainly in imbalanced classification scenarios. Our proposed system assists users in visually comparing different distributions of data types, selecting types of instances based on local characteristics that will later be affected by the active sampling method, and validating which suggestions from undersampling or oversampling techniques are beneficial for the ML model. Additionally, rather than uniformly undersampling/oversampling a specific class, we allow users to find and sample easy and difficult to classify training instances from all classes. Users can explore subsets of data from different perspectives to decide all those parameters, while HardVis keeps track of their steps and evaluates the model's predictive performance in a test set separately. The end result is a well‐balanced data set that boosts the predictive power of the ML model. The efficacy and effectiveness of HardVis are demonstrated with a hypothetical usage scenario and a use case. Finally, we also look at how useful our system is based on feedback we received from ML experts.

Stacked generalization (also called stacking) is an ensemble method in machine learning that deploys a metamodel to summarize the predictive results of heterogeneous base models organized into one or more layers. Despite being capable of producing high-performance results, building a stack of models can be a trial-and-error procedure. Thus, our previously developed visual analytics system, entitled StackGen Vis, was designed to monitor and control the entire stacking process visually. In this work, we present the results of a comparative user study we performed for evaluating the StackGen-Vis system. We divided the study participants into two groups to test the usability and effectiveness of StackGen Vis compared to Orange Visual Stacking (OVS) in an exploratory usage scenario using health-care data. The results indicate that StackGen Vis is significantly more powerful than OVS based on the qualitative feedback provided by the participants. However, the average completion time for all tasks was comparable between both tools.

The machine learning (ML) life cycle involves a series of iterative steps, from the effective gathering and preparation of the data-including complex feature engineering processes-to the presentation and improvement of results, with various algorithms to choose from in every step. Feature engineering in particular can be very beneficial for ML, leading to numerous improvements such as boosting the predictive results, decreasing computational times, reducing excessive noise, and increasing the transparency behind the decisions taken during the training. Despite that, while several visual analytics tools exist to monitor and control the different stages of the ML life cycle (especially those related to data and algorithms), feature engineering support remains inadequate. In this paper, we present FeatureEnVi, a visual analytics system specifically designed to assist with the feature engineering process. Our proposed system helps users to choose the most important feature, to transform the original features into powerful alternatives, and to experiment with different feature generation combinations. Additionally, data space slicing allows users to explore the impact of features on both local and global scales. FeatureEnVi utilizes multiple automatic feature selection techniques; furthermore, it visually guides users with statistical evidence about the influence of each feature (or subsets of features). The final outcome is the extraction of heavily engineered features, evaluated by multiple validation metrics. The usefulness and applicability of FeatureEnVi are demonstrated with two use cases and a case study. We also report feedback from interviews with two ML experts and a visualization researcher who assessed the effectiveness of our system.

The recent development in the data analytics field provides a boost in production for modern industries. Small-sized factories intend to take full advantage of the data collected by sensors used in their machinery. The ultimate goal is to minimize cost and maximize quality, resulting in an increase in profit. In collaboration with domain experts, we implemented a data visualization tool to enable decision-makers in a plastic factory to improve their production process. We investigate three different aspects: methods for preprocessing multivariate time series data, clustering approaches for the already refined data, and visualization techniques that aid domain experts in gaining insights into the different stages of the production process. Here we present our ongoing results grounded in a human-centered development process. We adopt a formative evaluation approach to continuously upgrade our dashboard design that eventually meets partners’ requirements and follows the best practices within the field.

Abstract During the training phase of machine learning (ML) models, it is usually necessary to configure several hyperparameters. This process is computationally intensive and requires an extensive search to infer the best hyperparameter set for the given problem. The challenge is exacerbated by the fact that most ML models are complex internally, and training involves trial‐and‐error processes that could remarkably affect the predictive result. Moreover, each hyperparameter of an ML algorithm is potentially intertwined with the others, and changing it might result in unforeseeable impacts on the remaining hyperparameters. Evolutionary optimization is a promising method to try and address those issues. According to this method, performant models are stored, while the remainder are improved through crossover and mutation processes inspired by genetic algorithms. We present VisEvol, a visual analytics tool that supports interactive exploration of hyperparameters and intervention in this evolutionary procedure. In summary, our proposed tool helps the user to generate new models through evolution and eventually explore powerful hyperparameter combinations in diverse regions of the extensive hyperparameter space. The outcome is a voting ensemble (with equal rights) that boosts the final predictive performance. The utility and applicability of VisEvol are demonstrated with two use cases and interviews with ML experts who evaluated the effectiveness of the tool.

In machine learning (ML), ensemble methods-such as bagging, boosting, and stacking-are widely-established approaches that regularly achieve top-notch predictive performance. Stacking (also called "stacked generalization") is an ensemble method that combines heterogeneous base models, arranged in at least one layer, and then employs another metamodel to summarize the predictions of those models. Although it may be a highly-effective approach for increasing the predictive performance of ML, generating a stack of models from scratch can be a cumbersome trial-and-error process. This challenge stems from the enormous space of available solutions, with different sets of data instances and features that could be used for training, several algorithms to choose from, and instantiations of these algorithms using diverse parameters (i.e., models) that perform differently according to various metrics. In this work, we present a knowledge generation model, which supports ensemble learning with the use of visualization, and a visual analytics system for stacked generalization. Our system, StackGenVis, assists users in dynamically adapting performance metrics, managing data instances, selecting the most important features for a given data set, choosing a set of top-performant and diverse algorithms, and measuring the predictive performance. In consequence, our proposed tool helps users to decide between distinct models and to reduce the complexity of the resulting stack by removing overpromising and underperforming models. The applicability and effectiveness of StackGenVis are demonstrated with two use cases: a real-world healthcare data set and a collection of data related to sentiment/stance detection in texts. Finally, the tool has been evaluated through interviews with three ML experts.

Abstract Machine learning (ML) models are nowadays used in complex applications in various domains, such as medicine, bioinformatics, and other sciences. Due to their black box nature, however, it may sometimes be hard to understand and trust the results they provide. This has increased the demand for reliable visualization tools related to enhancing trust in ML models, which has become a prominent topic of research in the visualization community over the past decades. To provide an overview and present the frontiers of current research on the topic, we present a State‐of‐the‐Art Report (STAR) on enhancing trust in ML models with the use of interactive visualization. We define and describe the background of the topic, introduce a categorization for visualization techniques that aim to accomplish this goal, and discuss insights and opportunities for future research directions. Among our contributions is a categorization of trust against different facets of interactive ML, expanded and improved from previous research. Our results are investigated from different analytical perspectives: (a) providing a statistical overview, (b) summarizing key findings, (c) performing topic analyses, and (d) exploring the data sets used in the individual papers, all with the support of an interactive web‐based survey browser. We intend this survey to be beneficial for visualization researchers whose interests involve making ML models more trustworthy, as well as researchers and practitioners from other disciplines in their search for effective visualization techniques suitable for solving their tasks with confidence and conveying meaning to their data.

t-Distributed Stochastic Neighbor Embedding (t-SNE) for the visualization of multidimensional data has proven to be a popular approach, with successful applications in a wide range of domains. Despite their usefulness, t-SNE projections can be hard to interpret or even misleading, which hurts the trustworthiness of the results. Understanding the details of t-SNE itself and the reasons behind specific patterns in its output may be a daunting task, especially for non-experts in dimensionality reduction. In this article, we present t-viSNE, an interactive tool for the visual exploration of t-SNE projections that enables analysts to inspect different aspects of their accuracy and meaning, such as the effects of hyper-parameters, distance and neighborhood preservation, densities and costs of specific neighborhoods, and the correlations between dimensions and visual patterns. We propose a coherent, accessible, and well-integrated collection of different views for the visualization of t-SNE projections. The applicability and usability of t-viSNE are demonstrated through hypothetical usage scenarios with real data sets. Finally, we present the results of a user study where the tool's effectiveness was evaluated. By bringing to light information that would normally be lost after running t-SNE, we hope to support analysts in using t-SNE and making its results better understandable.

Software evolution analysis can shed light on various aspects of software development and maintenance. Up to date, there is little empirical evidence on the evolution of JavaScript (JS) applications in terms of maintainability and changeability, even though JavaScript is among the most popular scripting languages for front-end web applications, including IoT applications. In this study, we investigate JS applications’ quality and changeability trends over time by examining the relevant Laws of Lehman. We analyzed over 7,500 releases of JS applications and reached some interesting conclusions. The results show that JS applications continuously change and grow, there are no clear signs of quality degradation while the complexity remains the same over time, despite the fact that the understandability of the code deteriorates.

Abstract Managing the maintenance process and estimating accurately the effort and duration required for a new release is considered to be a crucial task as it affects successful software project survival and progress over time. In this study, we propose the combination of two well‐known machine learning (ML) techniques, Bayesian networks (BNs), and association rules (ARs) for modeling the maintenance process by identifying the relationships among the internal and external quality metrics related to a particular project release to both the maintainability of the project and the maintenance process indicators (ie, effort and duration). We also exploit Bayesian inference, to test the effect of certain changes in internal and external project factors to the maintainability of a project. We evaluate our approach through a case study on 957 releases of five open source JavaScript applications. The results show that the maintainability of a release, the changes observed between subsequent releases, and the time required between two releases can be accurately predicted from size, complexity, and activity metrics. The proposed combined approach achieves higher accuracy when evaluated against the BN model accuracy.