arXiv subjects

Eunhye Kim

Publications and source records attributed to Eunhye Kim.

8 recordsLinked to original sources

arXiv2026

Maru: Information Architecture as a Shared Language for Generating Aligned and Persistent User Interfaces

Generative user interfaces (GenUIs) promise on-demand components tailored to users' needs. As users iterate on information tasks, they construct personal structures over information they encounter---how items are grouped, what gets prioritized, and what terms mean in their context. Yet, current systems leave these structural decisions to the model at each generation, ignoring the structural logic users have established. Without a persistent representational structure shared between user and system, GenUIs have no basis to remain aligned with what users have established. We draw on Information Architecture (IA), a design practice for organizing and structuring information, as a shared language to bridge user-constructed structure and system generation. We present a framework identifying four IA elements---partition, hierarchy, order, and vocabulary---and characterize how each maps to concrete UI generation decisions. We instantiate this framework in Maru, a conversational system that captures user prompts and interactions as IA preferences, persisting as rules both user and system draw on across generations. A user study revealed that IA persistence kept generated UIs aligned as sessions progressed, while alignment without it degraded, with diverse patterns emerging across users and contexts, pointing to the value of IA persistence in aligning GenUI to individual needs.

cs.HC↗

arXiv2026

Real-Time Long Horizon Air Quality Forecasting via Group-Relative Policy Optimization

Accurate long horizon forecasting of particulate matter (PM) concentration fields is essential for operational public health decisions. However, achieving reliable forecasts remains challenging in regions with complex terrain and strong atmospheric dynamics such as East Asia. While foundation models such as Aurora offer global generality, they often miss region-specific dynamics and rely on non-real-time inputs, limiting their practical utility for localized warning systems. To address this gap, we construct and release the real-world observations and high-resolution CMAQ-OBS dataset for East Asia, reducing regional error by 59.5% and enabling real-time 48-120 hour forecasts critical for public health alerts. However, standard point-wise objectives cannot reflect asymmetric operational costs, where false alarms deteriorate public trust while missed severe events endanger populations. This cost mismatch causes SFT models to over-predict and yield high False Alarm Rates. We introduce Group-Relative Policy Optimization (GRPO) with class-wise rewards and curriculum rollout to align predictions with operational priorities. Experimental results demonstrate that our framework significantly improves the reliability of the forecast. Compared to the SFT-only baseline, our model reduces the False Alarm Rate by 47.3% while achieving a competitive F1-score, proving its effectiveness for practical, real-world air quality forecasting systems on long lead time scenarios. Code and dataset are publicly available at https://github.com/kaist-cvml/FAKER-Air.

cs.CV↗

arXiv2026

Trace-Aware Workflows for Co-Creating Branded Content with Generative AI

Generative AI tools have lowered barriers to producing branded social media images and captions, yet small-business owners (SBOs) still struggle to create on-brand posts without access to professional designers or marketing consultants. Although these tools enable fast image generation from text prompts, aligning outputs with a brand's intended look and feel remains a demanding, iterative task. In this position paper, we explore how SBOs navigate iterative content creation and how AI-assisted systems can support SBOs' content creation workflow. We conducted a preliminary study with 12 SBOs who independently manage their businesses and social media presence, using a questionnaire to collect their branding practices, content workflows, and use of generative AI alongside conventional design tools. We identified three recurring challenges: (1) translating brand "feel" into effective prompts, (2) difficulty revisiting and comparing prior image generations, and (3) difficulty making sense of changes between iterations to steer refinement. Based on these findings, we present a prototype that scaffolds brand articulation, supports feedback-informed exploration, and maintains a traceboard of branching image iterations. Our work illustrates how traces of the iterative process can serve as workflow support that helps SBOs keep track of explorations, make sense of changes, and refine content.

cs.HC↗

arXiv2026

Benchmarking Large Language Models for Diagnosing Students' Cognitive Skills from Handwritten Math Work

Students' handwritten math work provides a rich resource for diagnosing cognitive skills, as it captures intermediate reasoning beyond final answers. We investigate how current large language models (LLMs) perform in diagnosing cognitive skills from such work. However, student responses vary widely, often omitting steps or providing only vague, contextually implicit evidence. Despite recent advances in LLMs' multimodal and reasoning capabilities, their performance under such conditions remains underexplored. To address this gap, we constructed MathCog, a benchmark dataset containing 3,036 diagnostic verdicts across 639 student responses to 110 math problems, annotated by teachers using TIMSS-grounded cognitive skill checklists with evidential strength labels (Evident/Vague). Evaluating 18 LLMs, we find that (1) all models underperform (F1 < 0.5) regardless of capability, and (2) performance degrades sharply under vague evidence. Error analysis reveals systematic patterns: models frequently misattribute Vague evidence as Evident, overthink minimal cues, and hallucinate nonexistent evidence. We discuss implications for evidence-aware, teacher-in-the-loop designs for LLM-based cognitive diagnosis in educational settings.

cs.AI↗

arXiv2025

BloomIntent: Automating Search Evaluation with LLM-Generated Fine-Grained User Intents

If 100 people issue the same search query, they may have 100 different goals. While existing work on user-centric AI evaluation highlights the importance of aligning systems with fine-grained user intents, current search evaluation methods struggle to represent and assess this diversity. We introduce BloomIntent, a user-centric search evaluation method that uses user intents as the evaluation unit. BloomIntent first generates a set of plausible, fine-grained search intents grounded on taxonomies of user attributes and information-seeking intent types. Then, BloomIntent provides an automated evaluation of search results against each intent powered by large language models. To support practical analysis, BloomIntent clusters semantically similar intents and summarizes evaluation outcomes in a structured interface. With three technical evaluations, we showed that BloomIntent generated fine-grained, evaluable, and realistic intents and produced scalable assessments of intent-level satisfaction that achieved 72% agreement with expert evaluators. In a case study (N=4), we showed that BloomIntent supported search specialists in identifying intents for ambiguous queries, uncovering underserved user needs, and discovering actionable insights for improving search experiences. By shifting from query-level to intent-level evaluation, BloomIntent reimagines how search systems can be assessed -- not only for performance but for their ability to serve a multitude of user goals.

cs.HC↗

arXiv2025

Beyond Tools: Understanding How Heavy Users Integrate LLMs into Everyday Tasks and Decision-Making

Large language models (LLMs) are increasingly used for both everyday and specialized tasks. While HCI research focuses on domain-specific applications, little is known about how heavy users integrate LLMs into everyday decision-making. Through qualitative interviews with heavy LLM users (n=7) who employ these systems for both intuitive and analytical thinking tasks, our findings show that participants use LLMs for social validation, self-regulation, and interpersonal guidance, seeking to build self-confidence and optimize cognitive resources. These users viewed LLMs either as rational, consistent entities or average human decision-makers. Our findings suggest that heavy LLM users develop nuanced interaction patterns beyond simple delegation, highlighting the need to reconsider how we study LLM integration in decision-making processes.

cs.HC↗

arXiv2024

Fields, Bridges, and Foundations: How Researchers Browse Citation Network Visualizations

Visualizing citation relations with network structures is widely used, but the visual complexity can make it challenging for individual researchers trying to navigate them. We collected data from 18 researchers with an interface that we designed using network simplification methods and analyzed how users browsed and identified important papers. Our analysis reveals six major patterns used for identifying papers of interest, which can be categorized into three key components: Fields, Bridges, and Foundations, each viewed from two distinct perspectives: layout-oriented and connection-oriented. The connection-oriented approach was found to be more reliable for selecting relevant papers, but the layout-oriented method was adopted more often, even though it led to unexpected results and user frustration. Our findings emphasize the importance of integrating these components and the necessity to balance visual layouts with meaningful connections to enhance the effectiveness of citation networks in academic browsing systems.

cs.HC↗

arXiv2009

Hydrodynamic interactions in colloidal ferrofluids: A lattice Boltzmann study

We use lattice Boltzmann simulations, in conjunction with Ewald summation methods, to investigate the role of hydrodynamic interactions in colloidal suspensions of dipolar particles, such as ferrofluids. Our work addresses volume fractions $ϕ$ of up to 0.20 and dimensionless dipolar interaction parameters $λ$ of up to 8. We compare quantitatively with Brownian dynamics simulations, in which many-body hydrodynamic interactions are absent. Monte Carlo data are also used to check the accuracy of static properties measured with the lattice Boltzmann technique. At equilibrium, hydrodynamic interactions slow down both the long-time and the short-time decays of the intermediate scattering function $S(q,t)$, for wavevectors close to the peak of the static structure factor $S(q)$, by a factor of roughly two. The long-time slowing is diminished at high interaction strengths whereas the short-time slowing (quantified via the hydrodynamic factor $H(q)$) is less affected by the dipolar interactions, despite their strong effect on the pair distribution function arising from cluster formation. Cluster formation is also studied in transient data following a quench from $λ= 0$; hydrodynamic interactions slow the formation rate, again by a factor of roughly two.

cond-mat.mes-hall↗