arXiv subjects

Hye-rin Kim

Publications and source records attributed to Hye-rin Kim.

3 recordsLinked to original sources

arXiv2026

Language-Grounded Multi-Domain Image Translation via Semantic Difference Guidance

Multi-domain image-to-image translation re quires grounding semantic differences ex pressed in natural language prompts into corresponding visual transformations, while preserving unrelated structural and seman tic content. Existing methods struggle to maintain structural integrity and provide fine grained, attribute-specific control, especially when multiple domains are involved. We propose LACE (Language-grounded Attribute Controllable Translation), built on two compo nents: (1) a GLIP-Adapter that fuses global semantics with local structural features to pre serve consistency, and (2) a Multi-Domain Control Guidance mechanism that explicitly grounds the semantic delta between source and target prompts into per-attribute translation vec tors, aligning linguistic semantics with domain level visual changes. Together, these modules enable compositional multi-domain control with independent strength modulation for each attribute. Experiments on CelebA(Dialog) and BDD100K demonstrate that LACE achieves high visual fidelity, structural preservation, and interpretable domain-specific control, surpass ing prior baselines. This positions LACE as a cross-modal content generation framework bridging language semantics and controllable visual translation.

cs.CV↗

arXiv2017

How social information can improve estimation accuracy in human groups

In our digital and connected societies, the development of social networks, online shopping, and reputation systems raises the question of how individuals use social information, and how it affects their decisions. We report experiments performed in France and Japan, in which subjects could update their estimates after having received information from other subjects. We measure and model the impact of this social information at individual and collective scales. We observe and justify that when individuals have little prior knowledge about a quantity, the distribution of the logarithm of their estimates is close to a Cauchy distribution. We find that social influence helps the group improve its properly defined collective accuracy. We quantify the improvement of the group estimation when additional controlled and reliable information is provided, unbeknownst to the subjects. We show that subjects' sensitivity to social influence permits to define five robust behavioral traits and increases with the difference between personal and group estimates. We then use our data to build and calibrate a model of collective estimation, to analyze the impact on the group performance of the quantity and quality of information received by individuals. The model quantitatively reproduces the distributions of estimates and the improvement of collective performance and accuracy observed in our experiments. Finally, our model predicts that providing a moderate amount of incorrect information to individuals can counterbalance the human cognitive bias to systematically underestimate quantities, and thereby improve collective performance.

physics.soc-ph↗

arXiv2014

Less-is-more in a 5-star rating system: an experimental study of human combined decisions in a multi-armed bandit problem

Given the rapid proliferation of advanced information technologies, including the Internet, modern humans can easily access vast amount of socially transmitted information. Intuitively, this situation is isomorphic to some eusocial insects that are known to solve the exploration-exploitation dilemma collectively through information transfer (e.g., honeybees [Seeley et al., 1991]; and ants [Shaffer, Sasaki & Pratt, 2013]). Yet, in contrast from the eusocial insects, whose colonies are composed of kin, human collective performance may be affected by an inherent free-rider problem [Bolton & Harris, 1999; Kameda, Tsukasaki, Hastie & Berg, 2011]. Specifically, in groups involving non-kin members, it is expected that free-riders, who allow others to search for better alternatives and then exploit their findings through social learning ("information scroungers"), will frequently appear, and consequently undermine the advantage of collective intelligence [Rogers, 1998; Kameda & Nakanishi, 2003].

cs.SI↗