International Affairs Team

Community

Professor Jae-Yon Lee Elected to Lead Global Digital Humanities Alliance

Jae-Yon Lee, Associate Professor in the School of Liberal Arts at UNIST, has been elected President-Elect of the Constituent Organizations Board (COB) of the Alliance of Digital Humanities Organizations (ADHO). He will serve alongside the current president for the coming year before assuming the presidency in 2027. The COB is the principal governing body of ADHO, which brings together digital humanities organizations representing regions and communities language around the world. As president, Professor Lee will help set the alliance's long-term direction, coordinate among its member organizations, and lead discussions on policy and international collaboration. Professor Lee has represented the Korean Association for Digital Humanities (KADH) on the COB since 2023, when KADH became an official constituent organization of ADHO. He currently serves as KADH vice president and chair of its research planning committee, connecting scholarship in Korea with the wider international digital humanities community. Korea's growing role in ADHO was also evident this summer, when KADH hosted Digital Humanities 2026 (DH2026), the alliance's 36th annual international conference, from July 27 to 31 at the Daejeon Convention Center. Under the theme “Engagement,” researchers from around the world presented nearly 490 studies spanning multilingual AI research, humanities research using smaller datasets, and data sovereignty and cultural memory. For the first time at an ADHO annual conference, real-time AI translation was used across the academic program to support presentations in English, Korean, Chinese, and Japanese, broadening participation across linguistic communities. “I hope to contribute to a global digital humanities community that better reflects the distinct cultures and languages of different regions, moving beyond a field historically centered in Europe and the United States,” Professor Lee said. “Drawing on my research and teaching at UNIST, I also hope to bring the humanities and engineering into closer conversation and broaden the intellectual possibilities available to the next generation of researchers.” Professor Lee studied Korean literature at Yonsei University, Harvard University, and the University of Chicago and has taught and conducted research at UNIST since 2012. His research spans 20th-century Korean fiction and criticism, colonial-era periodicals, the sociology of literature, and digital humanities. His work applies computational methods—including network and corpus analysis, word embeddings, and computational stylistics—to the study of Korean literature. More recently, he has expanded his research to narrative generation using AI language models and interdisciplinary education connecting literature and engineering.

Research

AI Personalization Adapts Answers to What Users Know

Abstract Large language models (LLMs) are increasingly used by end users, yet existing personalization methods relying on static profiles or text-only signals fail to capture query-specific expertise variation. We present ExPerT, a query-wise personalization framework that adapts LLM responses to users' query domain expertise by combining semantic and behavioral cues. ExPerT consists of two key components: (i) a semantic-behavioral expertise inference module that jointly interprets query text and keystroke dynamics via in-context LLM prompting, and (ii) an expertise-conditioned response generation that adapts the level of detail, terminology, and conceptual complexity. Our user study with 40 participants and 1270 queries demonstrated that ExPerT reduced expertise inference error by 65.7% compared to the strongest baseline (MAE = 0.398 vs. 1.162) and improved response satisfaction by 17.52% (from 3.71 to 4.36) on a 5-point Likert scale. A person's expertise is rarely the same across every subject. Someone deeply familiar with one field may know little about another, and even within the same field, expertise can vary from topic to topic. Yet, AI systems often personalize responses using relatively fixed information, such as user profiles or previous conversations. Led by Professor Taesik Gong of the Department of Computer Science and Engineering at UNIST, researchers developed ExPerT, an AI personalization framework that adapts large language model (LLM) responses to a user's expertise for each question. It combines what a user asks with patterns in how they type, then adjusts the detail, terminology, and complexity of the response. Existing personalization methods can capture general preferences or background but may miss how much someone knows about a particular topic. ExPerT instead assesses expertise for each query, drawing on both the wording of the question and typing patterns such as keystroke timing, speed, and corrections. These signals are used to estimate expertise on a five-level scale, from novice to expert. Typing behavior provided useful clues. Participants with greater expertise tended to type domain-specific terms faster and with more consistent timing. But neither language nor typing behavior was reliable on its own: an expert may ask a simple question, while someone less familiar with a subject may use technical terms fluently. Combining the two helped ExPerT distinguish between such cases. The team evaluated ExPerT with 40 participants across chemistry, computer science, and business, collecting 1,270 queries along with typing data and self-reported expertise. Adding typing behavior to query semantics reduced the average expertise-estimation error from 0.488 to 0.398 levels, an improvement of 18.4%. Compared with the strongest existing baseline, ExPerT reduced the error by 65.7%, from a mean absolute error of 1.162 to 0.398. Expertise-adapted responses also received higher satisfaction ratings, rising from 3.71 to 4.36 on a five-point scale, an increase of 17.52%. “Existing personalization methods often rely on fixed profiles or previous conversations, making it difficult to reflect how much a user knows about the topic at hand,” said Professor Gong. “By adapting to expertise at the level of each question, ExPerT could support AI systems that communicate more effectively with users of different backgrounds and levels of knowledge.” The approach could be particularly useful in areas where expertise varies widely among users, including education, professional customer support, and specialized services in medicine, law, and finance. Yeji Park, a graduate student in UNIST's Graduate School of Artificial Intelligence and first author of the study, presented the work at ACL 2026 in San Diego. The paper was selected for an oral presentation, placing it among the top 4% of submissions, and received a SAC Highlight Award , given to the top 2%. The dataset and source code are publicly available through theExPerT GitHub repository. The research was supported by the Ministry of Science and ICT (MSIT), the Institute of Information & Communications Technology Planning & Evaluation (IITP), and the National Research Foundation of Korea (NRF), through programs supporting AI research and talent development. Journal Reference Yeji Park, Jiwon Tark, and Taesik Gong, "ExPerT: Personalizing LLM Responses to Users' Domain Expertise via Query-Wise Semantic and Keystroke Behavioral Cues," ACL '26, (2026).

Community

UNIST Targets Cancer Metastasis with Blood Purification

UNIST researchers are looking to the bloodstream for a new way to intervene in cancer metastasis. Their approach would filter out factors that help colorectal cancer spread before returning purified blood to the patient. Led by Professor Joo Hun Kang of the Department of Biomedical Engineering at UNIST, the group has been selected for the Korean ARPA-H Project to develop the approach. Through the project, the group will receive approximately KRW 8 billion in government funding over four and a half years, with Professors Jinmyoung Joo and Semin Lee participating in the research. The approach addresses a major challenge in colorectal cancer treatment. Once cancer spreads to other organs, treatment becomes considerably more difficult and survival declines sharply. Existing therapies largely focus on removing the primary tumor or attacking cancer cells that have already spread. The group is investigating whether the bloodstream itself can provide another point of intervention. The proposed system would circulate a patient's blood outside the body and selectively remove factors and molecular signals that promote metastasis. The purified blood would then be returned to the patient. The aim is to disrupt the conditions that help cancer cells establish themselves in other organs, complementing treatments that target tumors directly. The technology builds on blood purification methods Professor Kang's group has been developing for sepsis. Designed to selectively remove pathogens and inflammatory substances from circulating blood, the approach has demonstrated efficacy in preclinical large-animal models of sepsis. The new project will adapt the underlying technology to target factors associated with cancer metastasis. The researchers will initially focus on colorectal cancer patients at high risk of recurrence or metastasis after surgery. They will also examine whether combining blood purification with conventional cancer treatment can suppress new metastases and limit further growth of tumors that have already spread. Ultimately, the team aims to develop a blood purification medical device that could be applied to other metastatic cancers and advance the technology toward an exploratory clinical study. The project brings together academic, clinical, and industry partners in cancer research and medical-device development. Yonsei University College of Medicine and Seoul National University Bundang Hospital (SNUBH) will investigate mechanisms of cancer metastasis and clinical applications. ArtBlood Inc. and Cebika Inc. will support production of the blood purification device, while EverTri Inc. will contribute to clinical study planning and regulatory approval. The Korea Testing & Research Institute (KTR) will support safety and performance evaluation. “The bloodstream is not only a route through which cancer cells travel; it also carries factors that can promote metastasis,” Professor Kang said. “By purifying the blood, we aim to disrupt that process and establish a new therapeutic approach to cancer metastasis.” “Our first goal is to demonstrate the approach in colorectal cancer and then expand it to other metastatic cancers,” he added. “Ultimately, we aim to develop a blood purification device that can move beyond the laboratory and toward clinical application.”

Research

AI Model Maps Seismic Responses Across Nuclear Power Plants

A research team, led by Professor Young-Joo Lee of the Department of Civil, Urban, and Environmental Engineering at UNIST and Senior Research Scientist Jaebeom Lee of the Korea Research Institute of Standards and Science (KRISS) has developed a deep-learning model for post-earthquake assessment of nuclear power plants. The model predicts seismic responses across the structure and estimates which locations may require priority inspection. Post-earthquake assessment can be challenging when sensors are installed at only a limited number of locations. Expanding sensor coverage throughout a nuclear power plant is difficult because of cabling, regulatory, and maintenance constraints. Numerical simulations can fill these gaps, but repeated finite element analyzes become computationally expensive when uncertainties in structural properties are taken into account. The researchers developed a deep-learning surrogate model that combines seismic ground motion with structural parameters to predict acceleration responses at 139 locations. This allows responses to be estimated at locations without physical sensors while reducing the computational cost of conventional analysis. The model also accounts for uncertainty in structural properties. Rather than providing only a binary assessment, it calculates the probability that the response at each location will exceed a predefined equipment-level threshold. These probabilities can help engineers prioritize locations for further inspection. Experimental validation showed an average maximum mean absolute percentage error of 1.37%, with R² values above 0.98. The model generates full acceleration time histories across multiple locations, allowing probabilistic responses to be assessed without repeatedly running computationally intensive finite element simulations. The team also developed a method for configuring the AI architecture according to a structure's natural frequencies. The resulting model achieved accuracy comparable to a deep-learning model with more than 200 times as many parameters, while requiring substantially fewer computational resources. The researchers expect the approach could also be adapted to other facilities that require rapid post-earthquake assessment, including semiconductor plants, data centers, and industrial facilities. “For safety applications, accurate prediction alone is not enough; it is also important to understand the uncertainty in those predictions,” the researchers said. “By quantifying that uncertainty, the framework can provide additional information for experts deciding where further inspection is needed.” The research was conducted jointly by the teams of Senior Research Scientist Jaebeom Lee at KRISS, with Jingoo Lee as first author. The work was supported by the National Research Foundation of Korea and KRISS. The findings have been reported in three papers, including a study published in Reliability Engineering & System Safety. The study was conducted jointly by the UNIST and KRISS research teams, with Jingoo Lee as first author. The work was supported by the National Research Foundation of Korea (NRF) and KRISS. The findings have been reported in three papers, including a study published in Reliability Engineering & System Safety (IF: 13.7). Journal Reference Jingoo Lee, Seungjun Lee, Young-Joo Lee, and Jaebeom Lee, “Predicting seismic floor response for nuclear power plant structures with time-series uncertainty propagation using attention-enhanced multimodal deep learning,” Reliab. Eng. Syst. Saf., (2026).

Research

Reducing Charge Loss in Organic Photoanodes for Solar Water Splitting

Abstract Organic photoelectrochemical (PEC) cells for solar water splitting typically utilize bulk heterojunction (BHJ) structures to circumvent the intrinsically short exciton diffusion lengths of organic semiconductors. However, stochastic donor/acceptor networks in BHJs often result in disordered interfacial contacts, leading to severe charge recombination. Herein, we report a pseudo-bilayer (PS-Bi) organic photoanode featuring a vertically ordered donor–acceptor configuration established via sequential deposition. Our systematic investigation reveals that this PS-Bi structure promotes selective charge transport and suppresses recombination due to its high domain purity, thereby facilitating efficient charge transfer at the interface. Consequently, the optimized PS-Bi photoanodes deliver an enhanced average photocurrent density (Jph) of 1.75 ± 0.03 mA cm−2 at 1.23 V versus the reversible hydrogen electrode for solar water oxidation, while simultaneously exhibiting a significant cathodic onset shift and extended operational stability compared to their BHJ counterparts (Jph = 1.44 ± 0.07 mA cm−2). This study demonstrates that employing the PS-Bi structure is a promising strategy for achieving high-performance and stable organic PEC systems for sustainable solar fuel production. Producing hydrogen from sunlight depends in part on how efficiently a photoelectrode can separate and move electrical charges. In organic photoelectrodes, however, the conventional practice of mixing semiconductor materials can create disordered pathways that allow those charges to recombine, reducing both performance and stability. A research team, led by Professors Han Hee Cho, Moon Kee Choi, and Myung Hoon Song of the Department of Materials Science and Engineering at UNIST, working with researchers at École Polytechnique Fédérale de Lausanne (EPFL), has developed an organic photoanode with a more ordered internal structure. The new design improved photocurrent by about 22% while extending operational stability. The team created what is known as a pseudo-bilayer (PS-Bi) structure by depositing two organic semiconductor materials in sequence. As the second layer is applied, it partially penetrates the first, forming a mixed region at the interface while preserving more distinct layers above and below. Conventional organic photoelectrodes typically use a bulk heterojunction (BHJ), in which donor and acceptor materials are mixed throughout the film. This arrangement helps generate and separate charges, but its irregular internal pathways can also bring electrons and holes back together before they contribute to the chemical reaction. The PS-Bi combines the advantages of both approaches. Charges are generated and separated in the mixed region, while the more ordered layers guide electrons and holes in different directions. This reduces recombination and allows more of the generated charge to drive water oxidation. In tests, the PS-Bi photoanodes achieved an average photocurrent density of 1.75 mA cm⁻², compared with 1.44 mA cm⁻² for conventional BHJ photoanodes, an increase of about 22%. The voltage required to initiate water oxidation also fell from 0.35 V to 0.15 V, allowing the reaction to begin with less external electrical input. The structural change also improved durability. Based on the time required for photocurrent density to fall to 0.5 mA cm⁻², the pseudo-bilayer photoanodes remained operational substantially longer than their BHJ counterparts. The researchers also found that the two structures degrade differently. In BHJ photoanodes, highly reactive holes can damage the organic semiconductor within the intermixed structure. The more ordered pseudo-bilayer reduces damage within the donor–acceptor region, helping the photoanode maintain its performance for longer. “Conventional organic photoelectrodes mix donor and acceptor materials throughout the film, which can lead to charge losses and faster degradation,” said Professor Cho. “By controlling how the two materials are arranged, we were able to improve both charge transport and operational stability.” He further added, “The lower operating voltage could also help in the development of systems that ultimately produce hydrogen using sunlight without an external electrical bias.” The study was published online in Chemical Engineering Journal on July 16, 2026. The research was supported by the National Research Foundation of Korea (NRF), funded by the Ministry of Science and ICT (MSIT), and the InnoCORE program. Journal Reference Gyu Won Chae, Seong Rae Kang, Jin Su Park, et al. , “A pseudo-bilayer organic photoanode for solar water oxidation,” Chem. Eng. J., (2026).