arXiv subjects

Soobin Park

Publications and source records attributed to Soobin Park.

9 recordsLinked to original sources

arXiv2026

One Is Not Enough: How People Use Multiple AI Models in Everyday Life

People increasingly use multiple Multimodal Large Language Models (MLLMs) concurrently, selecting each based on its perceived strengths. This cross-platform practice creates coordination challenges: adapting prompts to different interfaces, calibrating trust against inconsistent behaviors, and navigating separate conversation histories. Prior HCI research focused on single-agent interactions, leaving multi-MLLM orchestration underexplored. Through a diary study and semi-structured interviews (N=10), we examine how individuals organize work across competing AI systems. Our findings reveal that users construct primary and secondary hierarchies among models that shift over usage context. They also develop personalized switching patterns triggered by task aggregation to adjust effort and latency, and output credibility. These insights inform future tool design opportunities, supporting users to coordinate multi-MLLM workflows.

cs.HC↗

arXiv2026

"Oops! ChatGPT is Temporarily Unavailable!": A Diary Study on Knowledge Workers' Experiences of LLM Withdrawal

LLMs have become deeply embedded in knowledge work, raising concerns about growing dependency and the potential undermining of human skills. To investigate the pervasiveness of LLMs in work practices, we conducted a four-day diary study with frequent LLM users (N=10), observing how knowledge workers responded to a temporary withdrawal of LLMs. Our findings show how LLM withdrawal disrupted participants' workflows by identifying gaps in task execution, how self-directed work led participants to reclaim professional values, and how everyday practices revealed the extent to which LLM use had become inescapably normative. Conceptualizing LLMs as infrastructural to contemporary knowledge work, this research contributes empirical insights into the often invisible role of LLMs and proposes value-driven appropriation as an approach to supporting professional values in the current LLM-pervasive work environment.

cs.HC↗

arXiv2026

Human-AI Interaction Traces as Blackout Poetry: Reframing AI-Supported Writing as Found-Text Creativity

LLMs offer new creative possibilities for writers but also raise concerns about authenticity and reader trust, particularly when AI involvement is disclosed. Prior research has largely framed this as an issue of transparency and provenance, emphasizing the disclosure of human-AI interaction traces that account for how much the AI wrote and what the human did. Yet such audit-oriented disclosures may risk reducing creative collaboration to quantification and surveillance. In this position paper, we argue for a different lens by exploring how human-AI interaction traces might instead function as expressive artifacts that foreground the meaning-making inherent in human-AI collaboration. Drawing inspiration from blackout poetry, we frame AI-generated text as found material through which writers' acts of curation and reinterpretation become inscribed atop the AI's original output. In this way, we suggest that designing interaction traces as aesthetic artifacts may help readers better appreciate and trust writers' creative contributions in AI-assisted writing.

cs.HC↗

arXiv2025

Dual Recursive Feedback on Generation and Appearance Latents for Pose-Robust Text-to-Image Diffusion

Recent advancements in controllable text-to-image (T2I) diffusion models, such as Ctrl-X and FreeControl, have demonstrated robust spatial and appearance control without requiring auxiliary module training. However, these models often struggle to accurately preserve spatial structures and fail to capture fine-grained conditions related to object poses and scene layouts. To address these challenges, we propose a training-free Dual Recursive Feedback (DRF) system that properly reflects control conditions in controllable T2I models. The proposed DRF consists of appearance feedback and generation feedback that recursively refines the intermediate latents to better reflect the given appearance information and the user's intent. This dual-update mechanism guides latent representations toward reliable manifolds, effectively integrating structural and appearance attributes. Our approach enables fine-grained generation even between class-invariant structure-appearance fusion, such as transferring human motion onto a tiger's form. Extensive experiments demonstrate the efficacy of our method in producing high-quality, semantically coherent, and structurally consistent image generations. Our source code is available at https://github.com/jwonkm/DRF.

cs.CV↗

arXiv2025

Electronic rotons and Wigner crystallites in a two-dimensional dipole liquid

A key concept proposed by Landau to explain superfluid liquid helium is the elementary excitation of quantum particles called rotons. The irregular arrangement of atoms in a liquid forms the aperiodic dispersion of rotons that played a pivotal role in understanding fractional quantum Hall liquid (magneto-rotons) and the supersolidity of Bose-Einstein condensates. Even for a two-dimensional electron or dipole liquid in the absence of a magnetic field, their repulsive interactions were predicted to form a roton minimum that can be used to trace the transition to Wigner crystals and superconductivity, but it has not been observed. Here, we report the observation of such electronic rotons in a two-dimensional dipole liquid of alkali-metal ions doping charges to surface layers of black phosphorus. Our data reveal a striking aperiodic dispersion of rotons characterized by a local minimum of energy at a finite momentum. As the density of dipoles decreases, where interactions dominate over kinetic energy, the roton gap reduces to 0 as in crystals, signalling Wigner crystallisation. Our model shows the importance of short-range order arising from repulsion between dipoles, which can be viewed as the formation of Wigner crystallites (bubbles or stripes) floating in the sea of Fermi liquids. Our results reveal that the primary origin of electronic rotons (and the pseudogap) is strong correlations.

cond-mat.str-el↗

arXiv2025

Constella: Supporting Storywriters' Interconnected Character Creation through LLM-based Multi-Agents

Creating a cast of characters by attending to their relational dynamics is a critical aspect of most long-form storywriting. However, our formative study (N=14) reveals that writers struggle to envision new characters that could influence existing ones, balance similarities and differences among characters, and intricately flesh out their relationships. Based on these observations, we designed Constella, an LLM-based multi-agent tool that supports storywriters' interconnected character creation process. Constella suggests related characters (FRIENDS DISCOVERY feature), reveals the inner mindscapes of several characters simultaneously (JOURNALS feature), and manifests relationships through inter-character responses (COMMENTS feature). Our 7-8 day deployment study with storywriters (N=11) shows that Constella enabled the creation of expansive communities composed of related characters, facilitated the comparison of characters' thoughts and emotions, and deepened writers' understanding of character relationships. We conclude by discussing how multi-agent interactions can help distribute writers' attention and effort across the character cast.

cs.HC↗

arXiv2025

Identity-preserving Distillation Sampling by Fixed-Point Iterator

Score distillation sampling (SDS) demonstrates a powerful capability for text-conditioned 2D image and 3D object generation by distilling the knowledge from learned score functions. However, SDS often suffers from blurriness caused by noisy gradients. When SDS meets the image editing, such degradations can be reduced by adjusting bias shifts using reference pairs, but the de-biasing techniques are still corrupted by erroneous gradients. To this end, we introduce Identity-preserving Distillation Sampling (IDS), which compensates for the gradient leading to undesired changes in the results. Based on the analysis that these errors come from the text-conditioned scores, a new regularization technique, called fixed-point iterative regularization (FPR), is proposed to modify the score itself, driving the preservation of the identity even including poses and structures. Thanks to a self-correction by FPR, the proposed method provides clear and unambiguous representations corresponding to the given prompts in image-to-image editing and editable neural radiance field (NeRF). The structural consistency between the source and the edited data is obviously maintained compared to other state-of-the-art methods.

cs.CV↗

arXiv2025

Reimagining Personal Data: Unlocking the Potential of AI-Generated Images in Personal Data Meaning-Making

Image-generative AI provides new opportunities to transform personal data into alternative visual forms. In this paper, we illustrate the potential of AI-generated images in facilitating meaningful engagement with personal data. In a formative autobiographical design study, we explored the design and use of AI-generated images derived from personal data. Informed by this study, we designed a web-based application as a probe that represents personal data through generative images utilizing Open AI's GPT-4 model and DALL-E 3. We then conducted a 21-day diary study and interviews using the probe with 16 participants to investigate users' in-depth experiences with images generated by AI in everyday lives. Our findings reveal new qualities of experiences in users' engagement with data, highlighting how participants constructed personal meaning from their data through imagination and speculation on AI-generated images. We conclude by discussing the potential and concerns of leveraging image-generative AI for personal data meaning-making.

cs.HC↗

arXiv2022

Passive Haptic Rehearsal for Accelerated Piano Skill Acquisition

Passive haptic learning (PHL) uses vibrotactile stimulation to train piano songs using repetition, even when the recipient of stimulation is focused on other tasks. However, many of the benefits of playing piano cannot be acquired without actively playing the instrument. In this position paper, we posit that passive haptic rehearsal, where active piano practice is assisted by separate sessions of passive stimulation, is of greater everyday use than solely PHL. We propose a study to examine the effects of passive haptic rehearsal for self-paced piano learners and consider how to incorporate passive rehearsal into everyday practice.

cs.HC↗