Daniel A. Keim

The Avant‐Garde of the early 20th‐century was characterized by thriving artistic collaborations that gave rise to overlapping movements such as Expressionism, Cubism and Futurism. Although exhibitions acted as central hubs, the resulting artists' networks remain difficult to investigate due to inconsistent documentation, uneven temporal coverage, and rapidly shifting geographic contexts. We introduce Kandinsky , a Visual Analytics approach tailored to uncovering Avant‐Garde exhibition networks. Kandinsky combines a radial clustering layout that captures cohesive artistic ensembles with coordinated views, situating exhibition activity across time and region to enable a structured analysis of historically situated artistic relations. A task‐based validation and usability study with ten experts, supported by an extended case study, show that Kandinsky traces structural communities, transnational and temporal relations, and previously unrecognized patterns. This offers a data‐driven complement to traditional art‐historical inquiry.

The increasing complexity and volume of network data demand effective analysis approaches, with visual exploration proving particularly beneficial. Immersive technologies, such as augmented reality, virtual reality, and large display walls, have enabled the emerging field of immersive analytics, offering new opportunities to enhance user engagement, spatial awareness, and problem-solving. A growing body of work has explored immersive environments for network visualisation, ranging from design studies to fully integrated applications across various domains. Despite these advancements, the field remains fragmented, lacking a clear description of the design space and a structured overview of the aspects that have already been empirically evaluated. To address this gap, we present a survey of visual network analysis in immersive environments, covering 138 publications retrieved through a structured pipeline. We systematically analyse the key aspects that define the design space, investigate their coverage in prior applications (n=87), and review user evaluations (n=59) that provide empirical evidence for essential design-related questions. By synthesising experimental findings and evaluating existing applications, we identify key achievements, highlight research gaps, and offer guidance for the design of future approaches. Additionally, we provide an online resource to explore our results interactively, which will be updated as new developments emerge.

Searching in highly homogeneous marine video collections remains a challenging task even in the era of large multimodal deep networks.This difficulty arises because marine video content often falls outside the everyday vocabulary of users, while the visual homogeneity leads to frequent abstract labels such as fish or coral.This paper investigates the effectiveness of supplementing text queries with spatial location information to better address specific search intents.To effectively process location information, we investigate several strategies for video frame partitioning and content representation, formally defining and experimentally testing both static grid and dynamic segmentation variants.Furthermore, we present the results of a large-scale cognitive user study involving 220 participants.The study utilizes standard working memory interference techniques, comprising a target exposure phase, a distraction period, and a subsequent query specification from memory.The user queries are then evaluated against the proposed spatial retrieval models to determine how human spatial memory decay impacts retrieval effectiveness.Our results reveal that while dynamic segmentation models achieve the highest theoretical retrieval bounds under perfect conditions, their strict geometric boundaries are severely affected by human memory decay.Consequently, static overlapping grids demonstrate high robustness, outperforming dynamic models under more realistic, memory-driven search constraints.Finally, our experiments show that the observed spatial annotation perturbations can be modeled using a four-dimensional Kernel Density Estimation (KDE) method, enabling the simulation of realistic human memory decay on ideal bounding boxes.

Binary choices, as often used for reinforcement learning from human feedback (RLHF), convey only the direction of a preference. A person may choose apples over oranges and bananas over grapes, but which preference is stronger? Strength is crucial for decision-making under uncertainty and generalization of preference models, but hard to measure reliably. Metadata such as response times and inter-annotator agreement can serve as proxies for strength, but are often noisy and confounded. We propose ResponseRank to address the challenge of learning from noisy strength signals. Our method uses relative differences in proxy signals to rank responses to pairwise comparisons by their inferred preference strength. To control for systemic variation, we compare signals only locally within carefully constructed strata. This enables robust learning of utility differences consistent with strength-derived rankings while making minimal assumptions about the strength signal. Our contributions are threefold: (1) ResponseRank, a novel method that robustly learns preference strength by leveraging locally valid relative strength signals; (2) empirical evidence of improved sample efficiency and robustness across diverse tasks: synthetic preference learning (with simulated response times), language modeling (with annotator agreement), and RL control tasks (with simulated episode returns); and (3) the Pearson Distance Correlation (PDC), a novel metric that isolates cardinal utility learning from ordinal accuracy.

Legal exploration, analysis, and interpretation remain complex and demanding tasks, even for experienced legal scholars, due to the domain-specific language, tacit legal concepts, and intentional ambiguities embedded in legal texts. In related, text-based domains, Visual Analytics (VA) has become an indispensable tool for navigating documents, representing knowledge, and supporting analytical reasoning. However, legal scholarship presents distinct challenges: it requires managing formal legal structure, drawing on tacit domain knowledge, and documenting intricate and accurate reasoning processes – needs that current VA system designs for law fail to address adequately. We identify and describe key challenges and underexplored opportunities in applying VA to law, exploring how these technologies might better serve the legal domain. Interviews with nine legal experts reveal that current legal information retrieval interfaces do not adequately support the navigational complexity of law, often forcing users to rely on internalized legal expertise instead. To address this gap, we identify a three-phase workflow for legal experts, which highlights opportunities for VA to support legal reasoning through knowledge externalization and provenance tracking, leveraging tree-, graph-, and hierarchy-based visualizations. Through this contribution, our work establishes a user-centered VA workflow for the legal domain, recognizing tacit legal knowledge as a critical element of sense-making and insight generation, and situates these contributions within a broader research agenda for VA in law and other text-based disciplines.

Detecting and interpreting common patterns in relational data is crucial for understanding complex topological structures across various domains. These patterns, or network motifs, can often be detected algorithmically. However, visual inspection remains vital for exploring and discovering patterns. This paper focuses on presenting motifs within BioFabric network visualizations-a unique technique that opens opportunities for research on scaling to larger networks, design variations, and layout algorithms to better expose motifs. Our goal is to show how highlighting motifs can assist users in identifying and interpreting patterns in BioFabric visualizations. To this end, we leverage existing motif simplification techniques. We replace edges with glyphs representing fundamental motifs such as staircases, cliques, paths, and connector nodes. The results of our controlled experiment and usage scenarios demonstrate that motif simplification for BioFabric is useful for detecting and interpreting network patterns. Our participants were faster and more confident using the simplified view without sacrificing accuracy. The efficacy of our current motif simplification approach depends on which extant layout algorithm is used. We hope our promising findings on user performance will motivate future research on layout algorithms tailored to maximizing motif presentation.