Hyein Lee

Hyein Lee, Jihong Park, Sooyoung Kim et al.

In this paper, we introduce a novel semantic generative communication (SGC) framework, where generative users leverage text-to-image (T2I) generators to create images locally from downloaded text prompts, while non-generative users directly download images from a base station (BS). Although generative users help reduce downlink transmission energy at the BS, they consume additional energy for image generation and for uploading their generator state information (GSI). We formulate the problem of minimizing the total energy consumption of the BS and the users, and devise a generative user selection algorithm. Simulation results corroborate that our proposed algorithm reduces total energy by up to 54% compared to a baseline with all non-generative users.

Guijin Son, Seungone Kim, Catherine Arnett et al.

Following the recent achievement of gold-medal performance on the IMO by frontier LLMs, the community is searching for the next meaningful and challenging target for measuring LLM reasoning. Whereas olympiad-style problems measure step-by-step reasoning alone, research-level problems use such reasoning to advance the frontier of mathematical knowledge itself, emerging as a compelling alternative. Yet research-level math benchmarks remain scarce because such problems are difficult to source (e.g., Riemann Bench and FrontierMath-Tier 4 contain 25 and 50 problems, respectively). To support reliable evaluation of next-generation frontier models, we introduce Soohak, a 439-problem benchmark newly authored from scratch by 64 mathematicians. Soohak comprises two subsets. On the Challenge subset, frontier models including Gemini-3-Pro, GPT-5, and Claude-Opus-4.5 reach 30.4%, 26.4%, and 10.4% respectively, leaving substantial headroom, while leading open-weight models such as Qwen3-235B, GPT-OSS-120B, and Kimi-2.5 remain below 15%. Notably, beyond standard problem solving, Soohak introduces a refusal subset that probes a capability intrinsic to research mathematics: recognizing ill-posed problems and pausing rather than producing confident but unjustified answers. On this subset, no model exceeds 50%, identifying refusal as a new optimization target that current models do not directly address. To prevent contamination, the dataset will be publicly released in late 2026, with model evaluations available upon request in the interim.

Jipmin Jung, Phillip Park, Jaedong Lee et al.

Objectives; The accumulation and usefulness of clinical data have increased with IT development. While using clinical data that needs to be identifiable to obtain meaningful information, it is essential to ensure that data is de-identified and unnecessary clinical information is minimized to protect personal information. This process requires criteria and an appropriate method as there are clear identifiers as well as quasi-identifiers that are not readily identifiable. Methods; To formulate such a method, first, primary quasi-identifiers were selected by classifying information in 20 clinical personal information database tables into Direct-Identifier (DID), Quasi-Identifier (QI), Sensitive Attribute (SA), and Non-Sensitive Attribute (NSA) according to its type. Secondary QIs were then selected by assessing the risk for outliers by measuring uniqueness values of the selected data and scoring re-identification by calculating equivalence class of the influence on other data on QI removal. Third, the risk of re-identification of data users was numeralized and classified. Lastly, the final QI according to user class was determined by comparing the calculated re-identification scores to the threshold values of user classes. Results; Eventually, final QIs ranging from a minimum of 18 to a maximum of 28 were selected by making an assumption about user classes and using it as criteria. Conclusions; The QI selection method presented by the current investigators can be used by researchers at the final checkup stage before they de-identify the selected QIs. Therefore, clinical data users can securely and efficiently use clinical data containing personal information by objectively selecting QIs using the method proposed in the present study.