Social norms govern culturally appropriate behavior in communication, enabling dialogue systems to produce responses that are not only coherent but also socially acceptable. We present NormGenesis, a multicultural framework for generating and annotating socially grounded dialogues across English, Chinese, and Korean. To model the dynamics of social interaction beyond static norm classification, we propose a novel dialogue type, Violation-to-Resolution (V2R), which models the progression of conversations following norm violations through recognition and socially appropriate repair. To improve pragmatic consistency in underrepresented languages, we implement an exemplar-based iterative refinement early in the dialogue synthesis process. This design introduces alignment with linguistic, emotional, and sociocultural expectations before full dialogue generation begins. Using this framework, we construct a dataset of 10,800 multi-turn dialogues annotated at the turn level for norm adherence, speaker intent, and emotional response. Human and LLM-based evaluations demonstrate that NormGenesis significantly outperforms existing datasets in refinement quality, dialogue naturalness, and generalization performance. We show that models trained on our V2R-augmented data exhibit improved pragmatic competence in ethically sensitive contexts. Our work establishes a new benchmark for culturally adaptive dialogue modeling and provides a scalable methodology for norm-aware generation across linguistically and culturally diverse languages.

In online markets, sellers can maliciously recapture others’ images on display screens to utilize as spoof images, which can be challenging to distinguish in human eyes. To prevent such harm, we propose an anti-spoofing method using the pairs of RGB images and depth maps provided by the mobile camera with a time-of-fight sensor. When images are recaptured on display screens, various patterns differing by the screens as known as the moiré patterns can be also captured in spoof images. These patterns lead the anti-spoofing model to be overfitted and unable to detect spoof images recaptured on unseen media. To avoid the issue, we build a novel representation model composed of two embedding models, which can be trained without considering the recaptured images. Also, we newly introduce mToF dataset, the largest and most diverse object anti-spoofing dataset, and the first to utilize the time-of-flight (ToF) data. Experimental results confirm that our model achieves robust generalization even across unseen domains.

We present an adaptive transmission scheme for the CR (cognitive radio) systems. The proposed scheme estimates the distance between a CR user and an incumbent user utilizing IT (interference temperature) information recognized through the spectrum sensing procedure. Then, the CR user determines the maximum transmission power which does not cause any interference to the incumbent user by using CR-APC (CR-adaptive power control). At the same time, in order to provide the maximum throughput to the CR user, the proposed scheme adaptively selects the modulation order considering the determined transmission power and the IT value by applying CR-AMC (CR-adaptive modulation and coding) in the given channel state. Hence, wireless communication equipments using the proposed scheme are able to adaptively transmit the data without interference on the incumbent users in various channel environments.