Searcharxiv⌕ Search

arXiv subjects

Dominik Moritz

Publications and source records attributed to Dominik Moritz.

At least 19 recordsLinked to original sources

Human-Data Interaction, Exploration, and Visualization Systems in the AI Era: Challenges and Opportunities

The rapid advancement of AI is transforming human-centered systems, with profound implications for human-AI interaction, human-data interaction, and visual analytics. In the AI era, data analysis increasingly involves large-scale, heterogeneous, and multimodal data that is predominantly unstructured, as well as foundation models such as LLMs and VLMs, which introduce additional uncertainty into analytical processes. These shifts expose persistent challenges for human-data interactive systems, including perceptually misaligned latency, scalability constraints, limitations of existing interaction and exploration paradigms, and growing uncertainty regarding the reliability and interpretability of AI-generated insights. Responding to these challenges requires moving beyond conventional efficiency and scalability metrics, redefining the roles of humans and machines in analytical workflows, and incorporating cognitive, perceptual, and design principles into every level of the human-data interaction stack. This paper investigates the challenges introduced by recent advances in AI and examines how these developments are reshaping the ways users engage with data, while outlining limitations and open research directions for building human-centered AI systems for interactive data analysis in the AI era.

cs.DB↗

VACP: Visual Analytics Context Protocol

The rise of AI agents introduces a fundamental shift in Visual Analytics (VA), in which agents act as a new user group. Current agentic approaches - based on computer vision and raw DOM access - fail to perform VA tasks accurately and efficiently. This paper introduces the Visual Analytics Context Protocol (VACP), a framework designed to make VA applications "agent-ready" that extends generic protocols by explicitly exposing application state, available interactions, and mechanisms for direct execution. To support our context protocol, we contribute a formal specification of AI agent requirements and knowledge representations in VA interfaces. We instantiate VACP as a library compatible with major visualization grammars and web frameworks, enabling augmentation of existing systems and the development of new ones. Our evaluation across representative VA tasks demonstrates that VACP-enabled agents achieve higher success rates in interface interpretation and execution compared to current agentic approaches, while reducing token consumption and latency. VACP closes the gap between human-centric VA interfaces and machine perceivability, ensuring agents can reliably act as collaborative users in VA systems.

cs.HC↗

reComposer: Editable Planning for Controllable Image Generation

Prompt-based image generation makes it easy to produce visual assets, but offers little support for engaging with the creative process. Prompting collapses interdependent creative decisions into a monolithic instruction and returns a finished image, leaving control limited to revising the prompt or correcting the model's output. We present reComposer, a process-oriented image-generation interface built around editable planning, which decomposes users' evolving intent into meaningful creative decisions - such as subject, composition, or palette - and collaborates with users to explore underspecified goals and alternatives. reComposer supports conversational and direct manipulation of the plan, moving between concept-level intent and visual-level control. We evaluated reComposer with 8 design and non-design professionals. Compared to prompting, participants felt greater control and ownership while developing visual assets, exploring alternatives, and iterating on details. Our findings suggest how shifting generative AI interaction from specifying outputs to shaping process can support creative thinking alongside asset production.

cs.HC↗

Ender: Visual Scaffolding for Geometric Proof Comprehension

Geometric proof is a foundational but notoriously difficult topic in secondary mathematics, primarily due to the high cognitive load required to integrate visual diagrams with logical text. As proofs evolve, tracking the initial givens and an expanding set of derived truths can easily overwhelm working memory. While established scaffolding techniques are often visual and diagram-based, current digital learning environments mostly rely on static, text-heavy interfaces that force students to manage these complex mental models on their own. This paper introduces Ender, an interactive rendering system designed to visualize the logical status of two-column proofs. Ender's design is grounded in four literature-derived requirements: (1) diagram annotation, (2) structural tracing, (3) support for partial or incorrect work, and (4) synchronization between the diagram and text. To evaluate the system, we conducted a between-subjects, think-aloud experiment with 12 secondary school students in the United States, comparing Ender against a traditional digital proof interface. Our results indicate that students using Ender performed significantly better on proof comprehension tasks--specifically in identifying and correcting logical errors. These findings suggest that dynamic visual scaffolding may ease the working memory burden of digital interfaces, offering a promising building block for future AI-based proof tutoring systems.

cs.HC↗

Point, Revise, Review: Grounded Agentic Analysis in Reactive Notebooks with marimo-lens

In a computational notebook, a human can point to a rendered result and ask about "this," while an agent acts through cells, dependencies, and runtime state. When what the human sees and what the agent operates on are disconnected, the human must describe what they mean and trace what the agent did in prose that strips away situated visual and computational context. We present marimo-lens, an extension to the reactive Python notebook marimo for grounded human-agent analysis. Lens connects a human's marked output and note to its producing cell and relevant contributing computation, giving the agent computational context for the request. It surfaces agent activity, returns selected results to the notebook, and preserves the initiating selection for human review and reopening. We illustrate the lifecycle through an exploratory human-agent analysis of a real-world open dataset, showing how visually situated questions lead to computational inspection, notebook action, and returned evidence for human review.

cs.HC↗

Teaching Geometric Proof with Tech: Pitfalls and Possibilities

Geometric proof is a foundational yet challenging topic in mathematics, requiring students to integrate visual, logical, and notational skills. While technology has enhanced learning in other mathematical domains, its impact on geometric proof remains limited. To investigate this gap, we interviewed 18 geometry teachers to establish the technical requirements of educational proof tools. These requirements inform our review of 33 commercial and research tools. Our findings reveal a critical mismatch: while teachers value certain digital tools for initial planning and exploration activities, they revert to pen-and-paper for formal proof because it supports diagram annotation and provides space for multiple approaches to proof-solving. Annotating the diagram is a key component of the proof-solving workflow that existing tools do not support. We propose four technical and human-centered design guidelines for educational proof tools to meet teacher needs at scale: integrating diagram and proof, generating problems and feedback automatically, supporting multiple proof formats, and reducing accidental complexity in the user experience.

cs.HC↗

Dimensionality Reduction Meets Network Science: Sensemaking on UMAP's kNN Graph

While UMAP is widely used for exploring high-dimensional data, typical workflows focus on its lower-dimensional embedding, largely overlooking the rich k-nearest-neighbor (kNN) graph that UMAP constructs internally. This graph encodes the data manifold in its original high-dimensional space, before the distortion that UMAP's 2D projection introduces. We demonstrate the untapped potential of this internal representation, showing how standard graph algorithms applied to this graph enhance data sensemaking: (1) PageRank identifies representative data points, (2) k-core decomposition reveals dense core regions versus sparse periphery, and (3) clustering coefficient detects tight-knit neighborhoods with highly-similar data points. Through quantitative and qualitative evaluation on MNIST and Fashion MNIST, we show that these graph-based analyses are not only practical but also competitive with or complementary to purpose-built methods (e.g., k-medoids for exemplar selection, HDBSCAN for density-based clustering).

cs.LG↗

Skeleton: Visual Authoring of Non-visual Data Experiences

When sighted practitioners author accessible data visualizations, they build navigation structures (the nodes, edges, and input bindings that govern how assistive technologies traverse an interface) entirely in code, with no visual representation. Without a representation to react to, practitioners cannot develop judgment about what makes navigation good or bad, and the quality ceiling of non-visual experiences is set by the absence of a feedback loop. We address this problem through longitudinal co-design with practitioners across cartography, design systems, and open-source visualization, and make three contributions. First, we introduce an Inspector that renders navigation graphs as interactive node-link diagrams, and a Dimensions API that expresses navigation in terms of data dimensions rather than explicit graph construction. Second we present Skeleton, a direct-manipulation authoring environment in which the properties of an accessible navigation structure are translated into visual representations authors can observe and manipulate. Key techniques include a dual-view editor that simultaneously shows the system's navigation model and the end user's spatial experience, a scaffolding engine that automates spatial node placement by repurposing a visualization rendering pipeline, a live label-template editor with real-time screen-reader-output preview, and a testing mode that makes traversal sequence visually trackable. Third, we evaluate Skeleton through an in-situ study with 8 practitioners across visualization design, engineering, and research. Making navigation structure visible changed how practitioners engaged with accessible design: they reconsidered the architecture of their own visualizations, attended to a broader range of input modalities, and shifted from treating accessibility as a compliance task to treating it as a design problem. (abstract shortened for arxiv)

cs.HC↗

Structured Visualization Design Knowledge for Grounding Generative Reasoning and Situated Feedback

Automated visualization design navigates a tension between symbolic systems and generative models. Constraint solvers enforce structural and perceptual validity, but the rules they require are difficult to author and too rigid to capture situated design knowledge. Large language models require no formal rules and can reason about contextual nuance, but they prioritize popular conventions over empirically grounded best practices. We address this tension by proposing a cataloging scheme that structures visualization design knowledge as natural-language guidelines with semantically typed metadata. This allows experts to author knowledge that machines can query. An expert study ($N=18$) indicates that practitioners routinely adapt heuristics to situational factors such as audience and communicative intent. To capture this reasoning, guideline sections specify not only advice but also the contexts where it applies, exceptions that invalidate it, and the sources from which it derives. We demonstrate the scheme's expressiveness by cataloging 744 guidelines drawn from cognitive science, accessibility standards, data journalism, and research on rhetorical aspects of visual communication. We embed guideline sections in a vector space, opening the knowledge itself to structural analysis. This reveals conflicting advice across sources and transferable principles between domains. Rather than replacing constraint-based tools, our scheme provides what they lack: situated guidance that generative systems can retrieve to ground their reasoning, users can verify against cited sources, and experts can author as knowledge evolves.

cs.HC↗

Apple Intelligence Foundation Language Models

We present foundation language models developed to power Apple Intelligence features, including a ~3 billion parameter model designed to run efficiently on devices and a large server-based language model designed for Private Cloud Compute. These models are designed to perform a wide range of tasks efficiently, accurately, and responsibly. This report describes the model architecture, the data used to train the model, the training process, how the models are optimized for inference, and the evaluation results. We highlight our focus on Responsible AI and how the principles are applied throughout the model development.

cs.AI↗

Understanding Annotator Safety Policy with Interpretability

Safety policies define what constitutes safe and unsafe AI outputs, guiding data annotation and model development. However, annotation disagreement is pervasive and can stem from multiple sources such as operational failures (annotators misunderstand or misexecute the task), policy ambiguity (policy wording leaves room for interpretation), or value pluralism (different annotators hold different perspectives on safety). Distinguishing these sources matters. For example, operational failures call for quality control, ambiguity calls for policy clarification, and pluralism calls for deliberation about incorporating diverse perspectives. Yet understanding why annotators disagree is difficult. Directly asking annotators for their reasoning is costly, substantially increasing annotation burden, and can be unreliable for both human and LLM annotators as self-reported reasoning often fails to reflect actual decision processes. We introduce Annotator Policy Models (APMs), interpretable models that learn annotators' internal safety policies from labeling behavior alone, making annotator reasoning visible and comparable without additional annotation effort. We validate that APMs accurately model annotator safety policy (>80% accuracy), faithfully predict responses to counterfactual edits, and recover known policy differences in controlled settings. Applying APMs to LLM and human annotations, we demonstrate two core applications: (1) surfacing policy ambiguity by revealing how annotators interpret safety instructions differently, and (2) surfacing value pluralism by uncovering systematic differences in safety priorities across demographic groups. Together, these capabilities support more targeted, transparent, and inclusive safety policy design.

cs.AI↗

Semantic Regexes: Auto-Interpreting LLM Features with a Structured Language

Automated interpretability aims to translate large language model (LLM) features into human understandable descriptions. However, natural language feature descriptions can be vague, inconsistent, and require manual relabeling. In response, we introduce semantic regexes, structured language descriptions of LLM features. By combining primitives that capture linguistic and semantic patterns with modifiers for contextualization, composition, and quantification, semantic regexes produce precise and expressive feature descriptions. Across quantitative benchmarks and qualitative analyses, semantic regexes match the accuracy of natural language while yielding more concise and consistent feature descriptions. Their inherent structure affords new types of analyses, including quantifying feature complexity across layers, scaling automated interpretability from insights into individual features to model-wide patterns. Finally, in user studies, we find that semantic regexes help people build accurate mental models of LLM features.

cs.CL↗

Constructive Circuit Amplification: Improving Math Reasoning in LLMs via Targeted Sub-Network Updates

Prior studies investigating the internal workings of LLMs have uncovered sparse subnetworks, often referred to as circuits, that are responsible for performing specific tasks. Additionally, it has been shown that model performance improvement through fine-tuning often results from the strengthening of existing circuits in the model. Taken together, these findings suggest the possibility of intervening directly on such circuits to make precise, task-targeted updates. Motivated by these findings, we propose a novel method called Constructive Circuit Amplification which identifies pivotal tokens from model reasoning traces as well as model components responsible for the desired task, and updates only those components. Applied to mathematical reasoning, it improves accuracy by up to +11.4% across multiple models while modifying as little as 1.59% of model components, with minimal impact on other abilities as measured by MMLU, TriviaQA, and TruthfulQA. These results demonstrate that targeted capabilities can be reliably enhanced by selectively updating a sparse set of model components.

cs.CL↗

A Composable Agentic System for Automated Visual Data Reporting

To address the brittleness of monolithic AI agents, our prototype for automated visual data reporting explores a Human-AI Partnership model. Its hybrid, multi-agent architecture strategically externalizes logic from LLMs to deterministic modules, leveraging the rule-based system Draco for principled visualization design. The system delivers a dual-output: an interactive Observable report with Mosaic for reader exploration, and executable Marimo notebooks for deep, analyst-facing traceability. This granular architecture yields a fully automatic yet auditable and steerable system, charting a path toward a more synergistic partnership between human experts and AI. For reproducibility, our implementation and examples are available at https://peter-gy.github.io/VISxGenAI-2025/.

cs.HC↗

Towards softerware: Enabling personalization of interactive data representations for users with disabilities

Accessible design for some may still produce barriers for others. This tension, called access friction, creates challenges for both designers and end-users with disabilities. To address this, we present the concept of softerware, a system design approach that provides end users with agency to meaningfully customize and adapt interfaces to their needs. To apply softerware to visualization, we assembled 195 data visualization customization options centered on the barriers we expect users with disabilities will experience. We built a prototype that applies a subset of these options and interviewed practitioners for feedback. Lastly, we conducted a design probe study with blind and low vision accessibility professionals to learn more about their challenges and visions for softerware. We observed access frictions between our participant's designs and they expressed that for softerware's success, current and future systems must be designed with accessible defaults, interoperability, persistence, and respect for a user's perceived effort-to-outcome ratio.

cs.HC↗

EncQA: Benchmarking Vision-Language Models on Visual Encodings for Charts

Multimodal vision-language models (VLMs) continue to achieve ever-improving scores on chart understanding benchmarks. Yet, we find that this progress does not fully capture the breadth of visual reasoning capabilities essential for interpreting charts. We introduce EncQA, a novel benchmark informed by the visualization literature, designed to provide systematic coverage of visual encodings and analytic tasks that are crucial for chart understanding. EncQA provides 2,076 synthetic question-answer pairs, enabling balanced coverage of six visual encoding channels (position, length, area, color quantitative, color nominal, and shape) and eight tasks (find extrema, retrieve value, find anomaly, filter values, compute derived value exact, compute derived value relative, correlate values, and correlate values relative). Our evaluation of 9 state-of-the-art VLMs reveals that performance varies significantly across encodings within the same task, as well as across tasks. Contrary to expectations, we observe that performance does not improve with model size for many task-encoding pairs. Our results suggest that advancing chart understanding requires targeted strategies addressing specific visual reasoning gaps, rather than solely scaling up model or dataset size.

cs.CV↗

Policy Maps: Tools for Guiding the Unbounded Space of LLM Behaviors

AI policy sets boundaries on acceptable behavior for AI models, but this is challenging in the context of large language models (LLMs): how do you ensure coverage over a vast behavior space? We introduce policy maps, an approach to AI policy design inspired by the practice of physical mapmaking. Instead of aiming for full coverage, policy maps aid effective navigation through intentional design choices about which aspects to capture and which to abstract away. With Policy Projector, an interactive tool for designing LLM policy maps, an AI practitioner can survey the landscape of model input-output pairs, define custom regions (e.g., "violence"), and navigate these regions with if-then policy rules that can act on LLM outputs (e.g., if output contains "violence" and "graphic details," then rewrite without "graphic details"). Policy Projector supports interactive policy authoring using LLM classification and steering and a map visualization reflecting the AI practitioner's work. In an evaluation with 12 AI safety experts, our system helps policy designers craft policies around problematic model behaviors such as incorrect gender assumptions and handling of immediate physical safety threats.

cs.HC↗

Mosaic Selections: Managing and Optimizing User Selections for Scalable Data Visualization Systems

Though powerful tools for analysis and communication, interactive visualizations often fail to support real-time interaction with large datasets with millions or more records. To highlight and filter data, users indicate values or intervals of interest. Such selections may span multiple components, combine in complex ways, and require optimizations to ensure low-latency updates. We describe Mosaic Selections, a model for representing, managing, and optimizing user selections, in which one or more filter predicates are added to queries that request data for visualizations and input widgets. By analyzing both queries and selection predicates, Mosaic Selections enable automatic optimizations, including pre-aggregating data to rapidly compute selection updates. We contribute a formal description of our selection model and optimization methods, and their implementation in the open-source Mosaic architecture. Benchmark results demonstrate orders-of-magnitude latency improvements for selection-based optimizations over unoptimized queries and existing optimizers for the Vega language. The Mosaic Selection model provides infrastructure for flexible, interoperable filtering across multiple visualizations, alongside automatic optimizations to scale to millions and even billions of records.

cs.HC↗