Hyunsoo Jang

Dong-Guw Lee, Tai Hyoung Rhee, Hyunsoo Jang et al.

Despite the inherent advantages of thermal infrared(TIR) imaging, large-scale data collection and annotation remain a major bottleneck for TIR-based perception. A practical alternative is to synthesize pseudo TIR data via image translation; however, most RGB-to-TIR approaches heavily rely on RGB-centric priors that overlook thermal physics, yielding implausible heat distributions. In this paper, we introduce TherA, a controllable RGB-to-TIR translation framework that produces diverse and thermally plausible images at both scene and object level. TherA couples TherA-VLM with a latent-diffusion-based translator. Given a single RGB image and a user-prompted condition pair, TherA-VLM yields a thermal-aware embedding that encodes scene, object, material, and heat-emission context reflecting the input scene-condition pair. Conditioning the diffusion model on this embedding enables realistic TIR synthesis and fine-grained control across time of day, weather, and object state. Compared to other baselines, TherA achieves state-of-the-art translation performance, demonstrating improved zero-shot translation performance up to 33% increase averaged across all metrics.

Ji Eun Song, Eunchae Lee, Juhee Im et al.

Account sharing is common in subscription services and is now extending to generative AI platforms, which are still primarily designed for individual use. Sharing often requires workarounds that create new tensions. This study examines how LLM subscriptions are shared and the norms that develop. We combined a survey of 245 users with interviews of 36 participants to understand both patterns and lived experiences. Our analysis identified four types of account sharing, organized along two dimensions: whether the owner uses the account and whether subscription costs are shared. Within these types, we examined how norms were formed and how their fragility, especially privacy, became evident in practice. Users, fully aware of this, subtly adjusted their behavior, which we interpret through the lens of the observer effect. We frame LLM account sharing as a social practice of appropriation and outline design implications to adapt single-user platforms to multi-user realities.

Ji Eun Song, Hyunsoo Jang, Juhee Im et al.

On algorithmic social platforms, exchanging memes via direct messages (DMs) serves as phatic communication that affirms relationships, yet users often interpret these exchanges as signals shaping personalized recommendations, creating tension between relational practice and algorithmic control. This study examines how users perceive DM meme exchanges on Instagram rather than auditing Instagram's underlying recommender mechanisms, and how beliefs about DM-recommendation linkages shape coping strategies and feelings of powerlessness. We conducted semi-structured interviews with 21 active meme-DM users. Participants classified memes as recipient-friendly or recipient-unfriendly based on relational fit; many described the spread of unfriendly memes as "algorithmic contagion." Controls were constrained by relational norms, low perceived efficacy of feedback tools, and opaque DM-recommendation linkages. We articulate how DM-based relational practices are entangled with personalization infrastructures and propose three design implications: transparent linkage explanations, conversation-level opt-outs, and conservative learning that down-weights DM-originated signals.