Graduate
-
KAIST Uses AI to Discover Optimal New Material for Removing Radioactive Iodine Contamination
<(From the Right) Professor Ho Jin Ryu, Department of Nuclear and Quantum Engineering, Dr. Sujeong Lee, a graduate of the KAIST Department of Materials Science and Engineering, and Dr. Juhwan Noh of KRICT’s Digital Chemistry Research Center>
Managing radioactive waste is one of the core challenges in the use of nuclear energy. In particular, radioactive iodine poses serious environmental and health risks due to its long half-life (15.7 million years in the case of I-129), high mobility, and toxicity to living organisms. A Korean research team has successfully used artificial intelligence to discover a new material that can remove iodine for nuclear environmental remediation. The team plans to push forward with commercialization through various industry-academia collaborations, from iodine-adsorbing powders to contaminated water treatment filters.
KAIST (President Kwang Hyung Lee) announced on the 2of July that Professor Ho Jin Ryu's research team from the Department of Nuclear and Quantum Engineering, in collaboration with Dr. Juhwan Noh of the Digital Chemistry Research Center at the Korea Research Institute of Chemical Technology (KRICT, President Young Kook Lee), which operates under the National Research Council of Science & Technology (NST, Chairman Youngsik Kim), developed a technique using AI to discover new materials that effectively remove radioactive iodine contaminants.
Recent studies show that radioactive iodine primarily exists in aqueous environments in the form of iodate (IO₃⁻). However, existing silver-based adsorbents have weak chemical adsorption strength for iodate, making them inefficient. Therefore, it is imperative to develop new adsorbent materials that can effectively remove iodate.
Professor Ho Jin Ryu’s team used a machine learning-based experimental strategy to identify optimal iodate adsorbents among compounds called Layered Double Hydroxides (LDHs), which contain various metal elements.
The multi-metal LDH developed in this study – Cu₃(CrFeAl), based on copper, chromium, iron, and aluminum—showed exceptional adsorption performance, removing over 90% of iodate. This achievement was made possible by efficiently exploring a vast compositional space using AI-driven active learning, which would be difficult to search through conventional trial-and-error experiments.
<Picture2. Concept of Developed AI-Based Technology for Exploring New Materials for Radioactive Contamination Removal>
The research team focused on the fact that LDHs, like high-entropy materials, can incorporate a wide range of metal compositions and possess structures favorable for anion adsorption. However, due to the overwhelming number of possible metal combinations in multi-metal LDHs, identifying the optimal composition through traditional experimental methods has been nearly impossible.
To overcome this, the team employed AI (machine learning). Starting with experimental data from 24 binary and 96 ternary LDH compositions, they expanded their search to include quaternary and quinary candidates. As a result, they were able to discover the optimal material for iodate removal by testing only 16% of the total candidate materials.
Professor Ho Jin Ryu stated, “This study shows the potential of using artificial intelligence to efficiently identify radioactive decontamination materials from a vast pool of new material candidates, which is expected to accelerate research for developing new materials for nuclear environmental cleanup.”
The research team has filed a domestic patent application for the developed powder technology and is currently proceeding with an international patent application. They plan to enhance the material’s performance under various conditions and pursue commercialization through industry-academia cooperation in the development of filters for treating contaminated water.
Dr. Sujeong Lee, a graduate of the KAIST Department of Materials Science and Engineering, and Dr. Juhwan Noh of KRICT’s Digital Chemistry Research Center, participated as the co-first authors of the study. The results were published online on May 26 in the internationally renowned environmental publication Journal of Hazardous Materials.
※ Paper title: Discovery of multi-metal-layered double hydroxides for decontamination of iodate by machine learning-assisted experiments ※ DOI: https://doi.org/10.1016/j.jhazmat.2025.138735
This research was supported by the Nuclear Energy Research Infrastructure Program and the Nano-Materials Technology Development Program funded by the Ministry of Science and ICT and the National Research Foundation of Korea.
2025.07.03 View 99 -
2025 KAIST Global Entrepreneurship Summer School Concludes Successfully in Silicon Valley
< A group photo taken at the 2025 GESS Special Lecture.Vice President So Young Kim from the International Office, VC Jay Eum from GFT Ventures, Professor Byungchae Jin from the Impact MBA Program at the Business School, and Research Assistant Professor Sooa Lee from the Office of Global Initiative>
The “2025 KAIST Global Entrepreneurship Summer School (2025 KAIST GESS),” organized by the Office of Global Initiative of the KAIST International Office (Vice President So Young Kim), successfully concluded. Now in its fourth year, the program was designed to provide KAIST students with firsthand experience of the world’s leading startup ecosystem in Silicon Valley, USA, and to strengthen their practical capabilities to take on challenges on the global stage.
This year’s 2025 KAIST GESS welcomed approximately 40 participants, including 24 undergraduate and graduate students selected through document screening, interviews, team presentations, mentoring, and peer evaluations, as well as 16 Impact MBA students from the College of Business. The selected undergraduate and graduate participants underwent two months of pre-program training and received mentoring from experienced entrepreneurs to refine their business models and elevate their project ideas. Meanwhile, Impact MBA students joined the Silicon Valley program onsite, attending key lectures and networking sessions to broaden their understanding of the global startup ecosystem.
From June 22nd, participants spent seven days in Silicon Valley completing the global entrepreneurship curriculum. The program was operated in cooperation with major organizations including the KOTRA Silicon Valley IT Center, Korea-US AI Semiconductor Innovation Center (K-ASIC), and Plug and Play Tech Center. Local experts delivered lectures on topics such as “Startup Culture,” “Learning from Failures” and “Networks and Capital.”
Participants also had the opportunity to visit startups led by KAIST alumni and local entrepreneurs, gaining valuable insights from firsthand stories about global entrepreneurship. Companies visited included Medic Life Sciences (CEO Kyuho Han) and ImpriMed (CEO Sungwon Lim). Through these visits, participants received practical advice on market entry strategies and overcoming challenges in the global arena.
As part of their first onsite schedule, KAIST students attended an interactive fireside chat titled “Global Entrepreneurship and AI,” where they engaged in in-depth discussions on the future of AI-driven global startups. The session featured three distinguished speakers: Jay Kim, Head of US Business Development at Hyper Accel; Chandra Shekhar Dhir, AI/ML Director at JPMorgan Chase’s Machine Learning Center of Excellence; and Taesu Kim, co-founder of AI voice synthesis startup Neosapience and KAIST alumnus. Taesu Kim shared, “Facing serious health issues made me reflect on my life, and after recovering, I wanted to pursue something that could create a real impact on society, which led me to start my own company.” He also advised students to “take time at important turning points in life to deeply think about what you truly want to do and how you can contribute to society.
In line with the core value of ‘paying it forward’—a fundamental principle of global entrepreneurship learned in Silicon Valley—GESS participants engaged in a community service project titled “Let’s Play with AI+Tech,” organized in collaboration with the Sunnyvale community and Foothill College. Leveraging their strong foundation in AI, KAIST students designed and led a hands-on ‘Doodle AI’ educational program to make foundational AI concepts accessible and engaging for underrepresented local elementary school children and their parents, fostering meaningful community interaction.
On the final day of the 2025 KAIST GESS, a pitch competition was held with participation from Silicon Valley venture capitalists and accelerators. Participants presented their business models, developed over the two-month program, to a panel of judges. The winning team was eaureco, and Si Li Sara Aow (Civil and Environmental Engineering) shared, “GESS was a valuable opportunity to test and hone practical entrepreneurship skills beyond mere networking.” She added, “At first, I lacked confidence, but challenging myself to pitch in the final presentation gave me the courage to take one step closer to global entrepreneurship. Pitching in Silicon Valley, the heart of global startups, was an invaluable experience that will shape my path as a global entrepreneur.”
The program concluded with a special lecture by Jay Eum, a seasoned Silicon Valley venture capitalist and a judging panel member for GESS over the past three years. He shared key insights on startup success from an investor’s perspective, advising, “The journey of entrepreneurship is never easy, but the sooner you start, the better.” He further encouraged participants to “focus on solving problems in local markets, but do not fear challenging global markets,” inspiring them with courage and actionable advice.
So Young Kim, Director of the KAIST Office of Global Initiative, said, “We hope the 2025 KAIST GESS serves as a stepping stone for KAIST students to grow into influential entrepreneurs on the global stage,” adding, “This program is also expected to further enhance KAIST’s international reputation.”
Byungchae Jin, Faculty Chair of the KAIST Impact MBA, College of Business, highlighted the program's educational benefits, stating, “Engaging directly with local entrepreneurs and gaining practical experience in Silicon Valley's startup environment provide students with hands-on learning and significant inspiration.”
The 2025 KAIST GESS was jointly hosted by the KAIST Office of Global Initiative, Impact MBA, and Startup KAIST. Moving forward, KAIST plans to continue expanding its field-based global entrepreneurship education by linking with key global hubs like Silicon Valley, fostering next-generation global leaders who will lead innovation and challenge the status quo.
2025.07.01 View 148 -
KAIST Develops Customized Tactile Sensor That Can Detect Light Breath, Pressure and Sound
< Photo 1. (From left) Professor Inkyu Park of KAIST Department of Mechanical Engineering (ME), Dr. Jungrak Choi of ETRI, Ph.D. Candidate Donho Lee and M.S. Graduate Chankyu Han of KAIST ME >
When a robot grabs an object or a medical device detects a pulse, the tactile sensor is the technology that senses pressure like a fingertip. Existing sensors had disadvantages, such as slow responses or declining accuracy after repeated use, but Korean researchers have succeeded in developing a sensor that can quickly and accurately detect even light breath, pressure, and sound. This sensor can be used across a broad range — from everyday movements to medical diagnostics.
KAIST (represented by President Kwang Hyung Lee) announced on the 23rd of June that Professor Inkyu Park’s team from the Department of Mechanical Engineering, through a collaborative research project with the Electronics and Telecommunications Research Institute (ETRI, President Seung Chan Bang ) under the National Research Council of Science & Technology (NST, Chairman Young Sik Kim), has developed an innovative technology that overcomes the structural limitations of existing tactile sensors.
The core of this joint research is the implementation of a customized tactile sensor that simultaneously achieves flexibility, precision, and repeatable durability by applying Thermoformed 3D Electronics (T3DE).
< Figure 1. Comparative evaluation of soft elastomer–based 3D structure versus thermoforming-based 3D structure in terms of mechanical properties. >
In particular, soft elastomer-based sensors (rubber, silicone, etc. — materials that stretch and return to their original shape) have structural problems such as slow response times, high hysteresis*, and creep**, but this new platform operates precisely in diverse environments and overcomes these limitations.
*Hysteresis: A phenomenon where the previously applied force or change is retained like a “memory,” so that the same stimulus does not always produce the same result.
**Creep: The phenomenon where a material slowly deforms when a force is continuously applied.
T3DE sensors are manufactured by precisely forming electrodes on a 2D film, then thermoforming them into a 3D structure under heat and pressure. Specifically, the top electrodes and supporting pillar structures of the sensor are designed to allow the fine-tuning of the mechanical properties for different purposes. By adjusting microstructural parameters — such as the thickness, length, and number of support pillars — the sensor’s Young’s modulus* can be tuned across a broad range of 10 Pa to 1 MPa. This matches the stiffness of biological tissues like skin, muscle, and tendons, making them highly suitable as bio-interface sensors.
*Young’s modulus: An index representing a material's stiffness; this research can control this index to match various biological tissues.
The newly developed T3DE sensor uses air as a dielectric material to reduce power consumption and demonstrates outstanding performance in sensitivity, response time, thermal stability, and repeatable accuracy.
Experimental results showed that the sensor achieved △sensitivity of 5,884 kPa⁻¹, △response time of 0.1 ms (less than one-thousandth of a second), △hysteresis of less than 0.5%, and maintained a repeatable precision of 99.9% or higher even after 5,000 repeated measurements.
< Figure 2. Graphic Overview of thermoformed 3D electronics (T3DE) >
The research team also constructed a high-resolution 40×70 array, comprising a total of 2,800 densely packed sensors, to visualize the pressure distribution on the sole of the foot in real time during exercise and confirmed the possibility of using the sensor for wrist pulse measurement to assess vascular health. Furthermore, successful results were also achieved in sound-detection experiments at a level comparable to commercial acoustic sensors. In short, the sensor can precisely and quickly measure foot pressure, pulse, and sound, allowing it to be applied in areas such as sports, health, and sound sensing.
The T3DE technology was also applied to an augmented-reality(AR)-based surgical training system. By adjusting the stiffness of each sensor element to match that of biological tissues, the system provided real-time visual and tactile feedback according to the pressure applied during surgical incisions. It also offered real-time warnings if an incision was too deep or approached a risky area, making it a promising technology for enhancing immersion and accuracy in medical training.
KAIST Professor Inkyu Park stated, “Because this sensor can be precisely tuned from the design stage and operates reliably across diverse environments, it can be used not only in everyday life, but also in a variety of fields such as healthcare, rehabilitation, and virtual reality.”
The research was co-led as first authors by Dr. Jungrak Choi of ETRI, KAIST master’s student Chankyu Han, and Ph.D. candidate Donho Lee, under the overall guidance of Professor Inkyu Park. The research results were published in the May 2025 issue of ‘Science Advances’ and introduced to the global research community through the journal’s official SNS channels (Facebook, Twitter).
※ Thesis Title: Thermoforming 2D films into 3D electronics for high-performance, customizable tactile sensing
※ DOI: 10.1126/sciadv.adv0057
< Figure 3. The introduction of the study on the official SNS posting by Science Advances >
This research was supported by the Ministry of Trade, Industry and Energy, the National Research Foundation of Korea, and the Korea Institute for Advancement of Technology.
2025.06.23 View 547 -
KAIST Researchers Unveil an AI that Generates "Unexpectedly Original" Designs
< Photo 1. Professor Jaesik Choi, KAIST Kim Jaechul Graduate School of AI >
Recently, text-based image generation models can automatically create high-resolution, high-quality images solely from natural language descriptions. However, when a typical example like the Stable Diffusion model is given the text "creative," its ability to generate truly creative images remains limited. KAIST researchers have developed a technology that can enhance the creativity of text-based image generation models such as Stable Diffusion without additional training, allowing AI to draw creative chair designs that are far from ordinary.
Professor Jaesik Choi's research team at KAIST Kim Jaechul Graduate School of AI, in collaboration with NAVER AI Lab, developed this technology to enhance the creative generation of AI generative models without the need for additional training.
< Photo 2. Gayoung Lee, Researcher at NAVER AI Lab; Dahee Kwon, Ph.D. Candidate at KAIST Kim Jaechul Graduate School of AI; Jiyeon Han, Ph.D. Candidate at KAIST Kim Jaechul Graduate School of AI; Junho Kim, Researcher at NAVER AI Lab >
Professor Choi's research team developed a technology to enhance creative generation by amplifying the internal feature maps of text-based image generation models. They also discovered that shallow blocks within the model play a crucial role in creative generation. They confirmed that amplifying values in the high-frequency region after converting feature maps to the frequency domain can lead to noise or fragmented color patterns. Accordingly, the research team demonstrated that amplifying the low-frequency region of shallow blocks can effectively enhance creative generation.
Considering originality and usefulness as two key elements defining creativity, the research team proposed an algorithm that automatically selects the optimal amplification value for each block within the generative model.
Through the developed algorithm, appropriate amplification of the internal feature maps of a pre-trained Stable Diffusion model was able to enhance creative generation without additional classification data or training.
< Figure 1. Overview of the methodology researched by the development team. After converting the internal feature map of a pre-trained generative model into the frequency domain through Fast Fourier Transform, the low-frequency region of the feature map is amplified, then re-transformed into the feature space via Inverse Fast Fourier Transform to generate an image. >
The research team quantitatively proved, using various metrics, that their developed algorithm can generate images that are more novel than those from existing models, without significantly compromising utility.
In particular, they confirmed an increase in image diversity by mitigating the mode collapse problem that occurs in the SDXL-Turbo model, which was developed to significantly improve the image generation speed of the Stable Diffusion XL (SDXL) model. Furthermore, user studies showed that human evaluation also confirmed a significant improvement in novelty relative to utility compared to existing methods.
Jiyeon Han and Dahee Kwon, Ph.D. candidates at KAIST and co-first authors of the paper, stated, "This is the first methodology to enhance the creative generation of generative models without new training or fine-tuning. We have shown that the latent creativity within trained AI generative models can be enhanced through feature map manipulation."
They added, "This research makes it easy to generate creative images using only text from existing trained models. It is expected to provide new inspiration in various fields, such as creative product design, and contribute to the practical and useful application of AI models in the creative ecosystem."
< Figure 2. Application examples of the methodology researched by the development team. Various Stable Diffusion models generate novel images compared to existing generations while maintaining the meaning of the generated object. >
This research, co-authored by Jiyeon Han and Dahee Kwon, Ph.D. candidates at KAIST Kim Jaechul Graduate School of AI, was presented on June 16 at the International Conference on Computer Vision and Pattern Recognition (CVPR), an international academic conference.* Paper Title: Enhancing Creative Generation on Stable Diffusion-based Models* DOI: https://doi.org/10.48550/arXiv.2503.23538
This research was supported by the KAIST-NAVER Ultra-creative AI Research Center, the Innovation Growth Engine Project Explainable AI, the AI Research Hub Project, and research on flexible evolving AI technology development in line with increasingly strengthened ethical policies, all funded by the Ministry of Science and ICT through the Institute for Information & Communications Technology Promotion. It also received support from the KAIST AI Graduate School Program and was carried out at the KAIST Future Defense AI Specialized Research Center with support from the Defense Acquisition Program Administration and the Agency for Defense Development.
2025.06.20 View 768 -
KAIST Holds a Ceremony to Declare their Renewed Commitment for Ethical Management
KAIST held a ceremony to declare their renewed "Commitment for Ethical Management" to raise awareness and solidify the commitment its members to faithfully fulfill ethical responsibilities and duties.
Last March, the university established the 'Special Committee for Ethical Management,' chaired by the Provost, and under the leadership of this committee, a new 'Code of Ethics' and 'Code of Conduct' were prepared, containing ethical standards that members must adhere to across all areas of education, research, and administration.
< Photo 1. Attendees pledge to practice ethics during the declaration for the ethical management. >
This ceremony was arranged as an occasion for the president, key executives, and representatives from each university constituent to share the purpose and direction of the newly established ethical standards and to pledge their commitment to practicing them.
The Ethical Management Declaration consisted of: ▲ a progress report by the KAIST Special Committee for Ethical Management, ▲ a commemorative address by the president, ▲ an oath of the Code of Ethics and Code of Conduct, and ▲ the presentation of the 'Excellent Ethics Professor Award' organized by the Graduate Student Human Rights Center. Attendees shared the values and meaning of ethical management pursued by KAIST.
Particularly at this ceremony, six representatives – faculty, staff, and students – selected to reflect KAIST's values encompassing diversity in position, role, gender, and future generations, took the oath for the Code of Ethics and Code of Conduct.
< Photo 2. Attendees pledge to practice ethics during the Ethical Management Declaration. >
Also introduced at the ceremony was the "Ethical Excellence Award for Professors". It is an award that was organized by the Graduate Student Human Rights Center under the KAIST Student Council to recognize the faculty members for their outstanding ethical conduct in the laboratory setting. The 2025 recipients of the newly established award were the honored at the declaration ceremony for added significance.
Taking this declaration ceremony as an example, KAIST plans to actively encourage each departments, divisions and offices to also hold ethical management declarations of their own to establish a trustworthy, healthy, and transparent organizational culture through the daily practice of ethical responsibilities, and to continuously spread the practice of ethical management among all members.
President Kwang Hyung Lee emphasized, "Adhering to research and social ethics must be the foundation for KAIST to become a university trusted globally," and expressed, "I hope this ceremony serves as a turning point for all members to more faithfully practice their ethical responsibilities and duties."
2025.06.16 View 708 -
“One Experiment Is All It Takes”: KAIST Team Revolutionizes Drug Interaction Testing, Replacing 60,000 Studies
A groundbreaking new method developed by researchers at KAIST and Chungnam National University could drastically streamline drug interaction testing — replacing dozens of traditional experiments with just one.
The research, led by Professor Jae Kyoung Kim of KAIST Department of Mathematical Sciences & IBS Biomedical Mathematics Group and Professor Sang Kyum Kim of Chungnam National University's College of Pharmacy, introduces a novel analysis technique called 50-BOA, published in Nature Communications on June 5, 2025.
< Photo 1. (From left) Professor Sang Kyum Kim (Chungnam National University College of Pharmacy, co-corresponding author), Dr. Yun Min Song (IBS Biomedical Mathematics Group, formerly KAIST Department of Mathematical Sciences, co-first author), undergraduate student Hyeong Jun Jang (KAIST, co-first author), Professor Jae Kyoung Kim (KAIST and IBS Biomedical Mathematics Group, co-corresponding author) (Top left in the bubble) Professor Hwi-yeol Yun (Chungnam National University College of Pharmacy, co-author) >
For decades, scientists have had to repeat drug inhibition experiments across a wide range of concentrations to estimate inhibition constants — a process seen in over 60,000 scientific publications. But the KAIST-led team discovered that a single, well-chosen inhibitor concentration can yield even more accurate results.
< Figure 1. Graphical summary of 50-BOA. 50-BOA improves the accuracy and efficiency of inhibition constant estimation by using only a single inhibitor concentration instead of the traditionally used method of employing multiple inhibitor concentrations. >
“This approach challenges long-standing assumptions in experimental pharmacology,” says Prof. Kim. “It shows how mathematics can fundamentally redesign life science experiments.”
By mathematically analyzing the sources of error in conventional methods, the team found that over half the data typically collected adds no value or even skews results. Their new method not only cuts experimental effort by over 75%, but also enhances reproducibility and accuracy.
To help researchers adopt the method quickly, the team developed a user-friendly tool that takes simple Excel files as input, now freely available on GitHub:
☞ https://github.com/Mathbiomed/50-BOA
< Figure 2. The MATLAB and R package of 50-BOA at GitHub >
The work holds promise for faster and more reliable drug development, especially in assessing potential interactions in combination therapies. The U.S. FDA already emphasizes the importance of accurate enzyme inhibition assessment during early-stage drug evaluation — and this method could soon become a new gold standard.
2025.06.16 View 1473 -
KAIST Predicts Diseases by Early Detection of Aging Signals in Liver Tissue
- KAIST-KRIBB Develops ‘FiNi-seq’ Technology to Capture Characteristics of Fibrotic Microenvironments Accumulated in Liver Tissue and Dynamic Changes of Early Aging Cells
- Elucidation of the Spatial Ecosystem of Aged Liver Tissue, where Reprogramming of Senescent Cells and Immune Exhaustion Progresses, at the Single-Cell Genome and Epigenome Levels
< (From left) Professor Jong-Eun Park of KAIST Graduate School of Medical Science and Engineering (GSMSE), Dr. Chuna Kim of KRIBB, Dr. Kwon Yong Tak of KAIST GSMSE, Ph.D. Candidate Juyeon Kim of KRIBB, Ph.D. Candidate Myungsun Park of KAIST GSMSE >
Aging and chronic diseases involve the gradual accumulation of subtle tissue changes over a long period. Therefore, there are still limitations in quantitatively understanding these changes within organs and linking them to early signs of disease onset. In response, Korean researchers have successfully developed a platform technology that accurately captures localized changes that first occur within tissue, significantly aiding in faster disease discovery and prediction, and in setting personalized treatment targets.
KAIST (President Kwang Hyung Lee) announced on June 12th that a joint research team led by Professor Jong-Eun Park of the Graduate School of Medical Science and Engineering at KAIST and Dr. Chuna Kim of the Aging Convergence Research Center at the Korea Research Institute of Bioscience and Biotechnology (KRIBB, President Seok-Yoon Kwon) has developed ‘FiNi-seq (Fibrotic Niche enrichment sequencing)’ technology. This technology captures fibrotic microenvironments locally occurring in aged liver tissue and enables precise analysis at the single-cell transcriptome level*.
*Single-cell transcriptome analysis: A method to measure how actively each cell uses which genes, allowing identification and function of individual diseased cells.
The researchers developed a method to selectively enrich early aging microenvironments where regeneration is delayed and fibrosis accumulates, by physically selecting regions with high tissue degradation resistance in aged liver tissue.
In this process, high-resolution identification of fibrosis-related endothelial cells, fibroblasts interacting with the immune system, and immune-exhausted cells such as PD-1 highly expressing CD8 T cells, which were difficult to capture with existing single-cell analysis technologies, was possible.
In particular, the research team confirmed through ‘FiNi-seq’ technology that specific cells observed in fibrotic areas within aged liver tissue secondarily age the surrounding environment through secreted factors, and that this leads to the expansion of the aged environment.
Furthermore, they also elucidated the mechanism by which endothelial cells lose their tissue-specific identity and induce innate immune responses, promoting immune cell infiltration. Through spatial transcriptome analysis, the spatial distribution of fibroblasts interacting with immune cells was quantified, revealing their involvement in tissue regeneration, induction of inflammatory responses, and progression to chronic fibrosis.
The research team performed integrated analysis of multi-omics\* data to obtain transcriptome and epigenome information, precisely interpreting the microenvironment of aged liver tissue and its spatial heterogeneity, and confirming how these changes are connected to the intrahepatic vascular structure.
*Multi-omics: An integrated analysis method for various biological information within an organism, such as genes, proteins, metabolites, and cell information.
The newly developed ‘FiNi-seq’ technology is expected to be a useful platform for high-resolution capture of pathophysiological signals in most chronic liver diseases, including the aging process that causes fibrosis.
< Figure 1. Isolation of fibrotic regions from aged liver tissue, followed by single-cell transcriptome analysis and validation in a fibrosis model. >
The first author, Dr. Kwon Yong Tak of KAIST Graduate School of Medical Science and Engineering (GSMSE), a hepatologist at Seoul St. Mary's Hospital, designed this study to lay the groundwork for early diagnosis and treatment of fibrosis progression, the most important clinical prognostic indicator in chronic liver disease, while pursuing his Ph.D. at KAIST KAIST GSMSE with support from the physician-scientist training program. Co-first author Myungsun Park, a Ph.D. candidate at KAIST KAIST GSMSE, was responsible for the technical implementation of FiNi-seq technology, and Juyeon Kim, a Ph.D. candidate at KRIBB's Aging Convergence Research Center, was responsible for imaging analysis of aged tissue, playing a key role in the research.
Dr. Chuna Kim of KRIBB stated, “Through this study, we were able to precisely elucidate the cellular composition and spatial characteristics of the fibrotic microenvironment observed in aged liver tissue at the single-cell level.”
< Figure 2. Spatially defined stepwise progression patterns of aging-related regions within the liver and identification of regulatory factors inducing them. >
Professor Jong-Eun Park of the Graduate School of Medical Science and Engineering said, “As an analytical technology that can capture subtle changes occurring in the early stages of aging and chronic diseases, it is expected to play a significant role in finding effective treatment targets in the future. Also, we plan to expand this research to chronic diseases in other organs such as the lungs and kidneys, as well as various liver disease models.”
This research was published in the international journal ‘Nature Aging’ on May 5, 2025, with Dr. Kwon Yong Tak of KAIST KAIST GSMSE, Ph.D. Candidate Juyeon Kim of KRIBB, and Ph.D. Candidate Myungsun Park of KAIST as co-first authors.
*Paper Title: Quasi-spatial single-cell transcriptome based on physical tissue properties defines early aging associated niche in liver
*DOI: https://doi.org/10.1038/s43587-025-00857-7
This research was supported by several domestic institutions, including the National Research Foundation of Korea, the Korea Health Industry Development Institute (KHIDI), the Korea Research Institute of Bioscience and Biotechnology (KRIBB), KIST, POSCO Science Fellowship, and the Convergence Medical Scientist Training Program.
2025.06.12 View 1180 -
KAIST Introduces ‘Virtual Teaching Assistant’ That can Answer Even in the Middle of the Night – Successful First Deployment in Classroom
- Research teams led by Prof. Yoonjae Choi (Kim Jaechul Graduate School of AI) and Prof. Hwajeong Hong (Department of Industrial Design) at KAIST developed a Virtual Teaching Assistant (VTA) to support learning and class operations for a course with 477 students.
- The VTA responds 24/7 to students’ questions related to theory and practice by referencing lecture slides, coding assignments, and lecture videos.
- The system’s source code has been released to support future development of personalized learning support systems and their application in educational settings.
< Photo 1. (From left) PhD candidate Sunjun Kweon, Master's candidate Sooyohn Nam, PhD candidate Hyunseung Lim, Professor Hwajung Hong, Professor Yoonjae Choi >
“At first, I didn’t have high expectations for the Virtual Teaching Assistant (VTA), but it turned out to be extremely helpful—especially when I had sudden questions late at night, I could get immediate answers,” said Jiwon Yang, a Ph.D. student at KAIST. “I was also able to ask questions I would’ve hesitated to bring up with a human TA, which led me to ask even more and ultimately improved my understanding of the course.”
KAIST (President Kwang Hyung Lee) announced on June 5th that a joint research team led by Prof. Yoonjae Choi of the Kim Jaechul Graduate School of AI and Prof. Hwajeong Hong of the Department of Industrial Design has successfully developed and deployed a Virtual Teaching Assistant (VTA) that provides personalized feedback to individual students even in large-scale classes.
This study marks one of the first large-scale, real-world deployments in Korea, where the VTA was introduced in the “Programming for Artificial Intelligence” course at the KAIST Kim Jaechul Graduate School of AI, taken by 477 master’s and Ph.D. students during the Fall 2024 semester, to evaluate its effectiveness and practical applicability in an actual educational setting.
The AI teaching assistant developed in this study is a course-specialized agent, distinct from general-purpose tools like ChatGPT or conventional chatbots. The research team implemented a Retrieval-Augmented Generation (RAG) architecture, which automatically vectorizes a large volume of course materials—including lecture slides, coding assignments, and video lectures—and uses them as the basis for answering students’ questions.
< Photo 2. Teaching Assistant demonstrating to the student how the Virtual Teaching Assistant works>
When a student asks a question, the system searches for the most relevant course materials in real time based on the context of the query, and then generates a response. This process is not merely a simple call to a large language model (LLM), but rather a material-grounded question answering system tailored to the course content—ensuring both high reliability and accuracy in learning support.
Sunjun Kweon, the first author of the study and head teaching assistant for the course, explained, “Previously, TAs were overwhelmed with repetitive and basic questions—such as concepts already covered in class or simple definitions—which made it difficult to focus on more meaningful inquiries.” He added, “After introducing the VTA, students began to reduce repeated questions and focus on more essential ones. As a result, the burden on TAs was significantly reduced, allowing us to concentrate on providing more advanced learning support.”
In fact, compared to the previous year’s course, the number of questions that required direct responses from human TAs decreased by approximately 40%.
< Photo 3. A student working with VTA. >
The VTA, which was operated over a 14-week period, was actively used by more than half of the enrolled students, with a total of 3,869 Q&A interactions recorded. Notably, students without a background in AI or with limited prior knowledge tended to use the VTA more frequently, indicating that the system provided practical support as a learning aid, especially for those who needed it most.
The analysis also showed that students tended to ask the VTA more frequently about theoretical concepts than they did with human TAs. This suggests that the AI teaching assistant created an environment where students felt free to ask questions without fear of judgment or discomfort, thereby encouraging more active engagement in the learning process.
According to surveys conducted before, during, and after the course, students reported increased trust, response relevance, and comfort with the VTA over time. In particular, students who had previously hesitated to ask human TAs questions showed higher levels of satisfaction when interacting with the AI teaching assistant.
< Figure 1. Internal structure of the AI Teaching Assistant (VTA) applied in this course. It follows a Retrieval-Augmented Generation (RAG) structure that builds a vector database from course materials (PDFs, recorded lectures, coding practice materials, etc.), searches for relevant documents based on student questions and conversation history, and then generates responses based on them. >
Professor Yoonjae Choi, the lead instructor of the course and principal investigator of the study, stated, “The significance of this research lies in demonstrating that AI technology can provide practical support to both students and instructors. We hope to see this technology expanded to a wider range of courses in the future.”
The research team has released the system’s source code on GitHub, enabling other educational institutions and researchers to develop their own customized learning support systems and apply them in real-world classroom settings.
< Figure 2. Initial screen of the AI Teaching Assistant (VTA) introduced in the "Programming for AI" course. It asks for student ID input along with simple guidelines, a mechanism to ensure that only registered students can use it, blocking indiscriminate external access and ensuring limited use based on students. >
The related paper, titled “A Large-Scale Real-World Evaluation of an LLM-Based Virtual Teaching Assistant,” was accepted on May 9, 2025, to the Industry Track of ACL 2025, one of the most prestigious international conferences in the field of Natural Language Processing (NLP), recognizing the excellence of the research.
< Figure 3. Example conversation with the AI Teaching Assistant (VTA). When a student inputs a class-related question, the system internally searches for relevant class materials and then generates an answer based on them. In this way, VTA provides learning support by reflecting class content in context. >
This research was conducted with the support of the KAIST Center for Teaching and Learning Innovation, the National Research Foundation of Korea, and the National IT Industry Promotion Agency.
2025.06.05 View 1508 -
KAIST-UIUC researchers develop a treatment platform to disable the ‘biofilm’ shield of superbugs
< (From left) Ph.D. Candidate Joo Hun Lee (co-author), Professor Hyunjoon Kong (co-corresponding author) and Postdoctoral Researcher Yujin Ahn (co-first author) from the Department of Chemical and Biomolecular Engineering of the University of Illinois at Urbana-Champaign and Ju Yeon Chung (co-first author) from the Integrated Master's and Doctoral Program, and Professor Hyun Jung Chung (co-corresponding author) from the Department of Biological Sciences of KAIST >
A major cause of hospital-acquired infections, the super bacteria Methicillin-resistant Staphylococcus aureus (MRSA), not only exhibits strong resistance to existing antibiotics but also forms a dense biofilm that blocks the effects of external treatments. To meet this challenge, KAIST researchers, in collaboration with an international team, successfully developed a platform that utilizes microbubbles to deliver gene-targeted nanoparticles capable of break ing down the biofilms, offering an innovative solution for treating infections resistant to conventional antibiotics.
KAIST (represented by President Kwang Hyung Lee) announced on May 29 that a research team led by Professor Hyun Jung Chung from the Department of Biological Sciences, in collaboration with Professor Hyunjoon Kong's team at the University of Illinois, has developed a microbubble-based nano-gene delivery platform (BTN MB) that precisely delivers gene suppressors into bacteria to effectively remove biofilms formed by MRSA.
The research team first designed short DNA oligonucleotides that simultaneously suppress three major MRSA genes, related to—biofilm formation (icaA), cell division (ftsZ), and antibiotic resistance (mecA)—and engineered nanoparticles (BTN) to effectively deliver them into the bacteria.
< Figure 1. Effective biofilm treatment using biofilm-targeting nanoparticles controlled by microbubbler system. Schematic illustration of BTN delivery with microbubbles (MB), enabling effective permeation of ASOs targeting bacterial genes within biofilms infecting skin wounds. Gene silencing of targets involved in biofilm formation, bacterial proliferation, and antibiotic resistance leads to effective biofilm removal and antibacterial efficacy in vivo. >
In addition, microbubbles (MB) were used to increase the permeability of the microbial membrane, specifically the biofilm formed by MRSA. By combining these two technologies, the team implemented a dual-strike strategy that fundamentally blocks bacterial growth and prevents resistance acquisition.
This treatment system operates in two stages. First, the MBs induce pressure changes within the bacterial biofilm, allowing the BTNs to penetrate. Then, the BTNs slip through the gaps in the biofilm and enter the bacteria, delivering the gene suppressors precisely. This leads to gene regulation within MRSA, simultaneously blocking biofilm regeneration, cell proliferation, and antibiotic resistance expression.
In experiments conducted in a porcine skin model and a mouse wound model infected with MRSA biofilm, the BTN MB treatment group showed a significant reduction in biofilm thickness, as well as remarkable decreases in bacterial count and inflammatory responses.
< Figure 2. (a) Schematic illustration on the evaluation of treatment efficacy of BTN-MB gene therapy. (b) Reduction in MRSA biofilm mass via simultaneous inhibition of multiple genes. (c, d) Antibacterial efficacy of BTN-MB over time in a porcine skin infection biofilm model. (e) Schematic of the experimental setup to verify antibacterial efficacy in a mouse skin wound infection model. (f) Wound healing effects in mice. (g) Antibacterial effects at the wound site. (h) Histological analysis results. >
These results are difficult to achieve with conventional antibiotic monotherapy and demonstrate the potential for treating a wide range of resistant bacterial infections.
Professor Hyun Jung Chung of KAIST, who led the research, stated, “This study presents a new therapeutic solution that combines nanotechnology, gene suppression, and physical delivery strategies to address superbug infections that existing antibiotics cannot resolve. We will continue our research with the aim of expanding its application to systemic infections and various other infectious diseases.”
< (From left) Ju Yeon Chung from the Integrated Master's and Doctoral Program, and Professor Hyun Jung Chung from the Department of Biological Sciences >
The study was co-first authored by Ju Yeon Chung, a graduate student in the Department of Biological Sciences at KAIST, and Dr. Yujin Ahn from the University of Illinois. The study was published online on May 19 in the journal, Advanced Functional Materials.
※ Paper Title: Microbubble-Controlled Delivery of Biofilm-Targeting Nanoparticles to Treat MRSA Infection ※ DOI: https://doi.org/10.1002/adfm.202508291
This study was supported by the National Research Foundation and the Ministry of Health and Welfare, Republic of Korea; and the National Science Foundation and National Institutes of Health, USA.
2025.05.29 View 1899 -
KAIST Hosts 2025 Integrity Week: In Commitment to Moral Excellence with Programs like "Integrity Consultation on Call" - Promoting Ethical Conduct and Rebuilding Trust
KAIST announced on May 26th that it hosted the "2025 KAIST Integrity Week." The goal was to enhance the integrity and anti-corruption awareness of its members and foster a culture of responsibility and trust within the organization. This initiative included participatory programs such as consultations, education, and campaigns on research and academic integrity.
Under the theme "KAIST Practicing Responsibility and Trust," this Integrity Week featured diverse programs designed for both faculty, staff, and students.
< The Integrity Week Poster >
On the first day of Integrity Week, President Kwang Hyung Lee sent a letter to all members, proclaiming KAIST's commitment to integrity and emphasizing its importance.
Key programs include:
• "Integrity Consultations on Call" to enhance the culture of ethical conduct.
• A program in a quiz show format, the “Integrity Golden Bell,"
• Integrity and Anti-Corruption Education Day.
• Integrity Campaigns aimed at improving internal culture of observing the code of conduct.
These events are designed to encourage participation from both faculty, staff, and students.
In particular, the " Integrity Consultations on Call" were held for graduate student council executives, departmental graduate student representatives, and research support personnel. This was a forum to discuss integrity issues and improvement measures that may arise during research and administrative tasks. It will also serve to share effective integrity policies, such as conflict of interest prevention systems and anonymous reporting legal counsel services.
The "Integrity Golden Bell" event was aimed to enhance faculty and staff's understanding of anti-corruption laws, including the Improper Solicitation and Graft Act and the Conflict of Interest Prevention Act, and to encourage their voluntary commitment to these principles.
< The Integrity Week Poster >
The goals KAIST was targeting to achieve through this Integrity Week, was to integrate the value of ethical practices in daily routines and cultivate a healthy culture within the working environment in which its working colleagues can trust each other. Furthermore, KAIST aims to make integrity a core value that can bolster sustainable development, encouraging all members to actively participate in practicing honest and responsible research and academic work.
President Kwang Hyung Lee stated, "Ethical conduct and honesty is at the essence of science and technology that people of the community must uphold conscientiously, and it should be the foundation for KAIST to regain and maintain global trust. We hope that through this Integrity Week, the value of integrity will take deeper root within our research culture and daily lives."
2025.05.26 View 1405 -
KAIST to Develop a Korean-style ChatGPT Platform Specifically Geared Toward Medical Diagnosis and Drug Discovery
On May 23rd, KAIST (President Kwang-Hyung Lee) announced that its Digital Bio-Health AI Research Center (Director: Professor JongChul Ye of KAIST Kim Jaechul Graduate School of AI) has been selected for the Ministry of Science and ICT's 'AI Top-Tier Young Researcher Support Program (AI Star Fellowship Project).' With a total investment of ₩11.5 billion from May 2025 to December 2030, the center will embark on the full-scale development of AI technology and a platform capable of independently inferring and determining the kinds of diseases, and discovering new drugs.
< Photo. On May 20th, a kick-off meeting for the AI Star Fellowship Project was held at KAIST Kim Jaechul Graduate School of AI’s Yangjae Research Center with the KAIST research team and participating organizations of Samsung Medical Center, NAVER Cloud, and HITS. [From left to right in the front row] Professor Jaegul Joo (KAIST), Professor Yoonjae Choi (KAIST), Professor Woo Youn Kim (KAIST/HITS), Professor JongChul Ye (KAIST), Professor Sungsoo Ahn (KAIST), Dr. Haanju Yoo (NAVER Cloud), Yoonho Lee (KAIST), HyeYoon Moon (Samsung Medical Center), Dr. Su Min Kim (Samsung Medical Center) >
This project aims to foster an innovative AI research ecosystem centered on young researchers and develop an inferential AI agent that can utilize and automatically expand specialized knowledge systems in the bio and medical fields.
Professor JongChul Ye of the Kim Jaechul Graduate School of AI will serve as the lead researcher, with young researchers from KAIST including Professors Yoonjae Choi, Kimin Lee, Sungsoo Ahn, and Chanyoung Park, along with mid-career researchers like Professors Jaegul Joo and Woo Youn Kim, jointly undertaking the project. They will collaborate with various laboratories within KAIST to conduct comprehensive research covering the entire cycle from the theoretical foundations of AI inference to its practical application.
Specifically, the main goals include: - Building high-performance inference models that integrate diverse medical knowledge systems to enhance the precision and reliability of diagnosis and treatment. - Developing a convergence inference platform that efficiently combines symbol-based inference with neural network models. - Securing AI technology for new drug development and biomarker discovery based on 'cell ontology.'
Furthermore, through close collaboration with industry and medical institutions such as Samsung Medical Center, NAVER Cloud, and HITS Co., Ltd., the project aims to achieve: - Clinical diagnostic AI utilizing medical knowledge systems. - AI-based molecular target exploration for new drug development. - Commercialization of an extendible AI inference platform.
Professor JongChul Ye, Director of KAIST's Digital Bio-Health AI Research Center, stated, "At a time when competition in AI inference model development is intensifying, it is a great honor for KAIST to lead the development of AI technology specialized in the bio and medical fields with world-class young researchers." He added, "We will do our best to ensure that the participating young researchers reach a world-leading level in terms of research achievements after the completion of this seven-year project starting in 2025."
The AI Star Fellowship is a newly established program where post-doctoral researchers and faculty members within seven years of appointment participate as project leaders (PLs) to independently lead research. Multiple laboratories within a university and demand-side companies form a consortium to operate the program.
Through this initiative, KAIST plans to nurture bio-medical convergence AI talent and simultaneously promote the commercialization of core technologies in collaboration with Samsung Medical Center, NAVER Cloud, and HITS.
2025.05.26 View 3312 -
Hyung Kyu Lim, Former KAIST Alumni Association President, Donates 100 Million Won for a Challenge to Follow “I am a KAIST”
Hyung Kyu Lim, a former President of the KAIST Alumni Association, has donated 100 million won as the prize money for the School Song and National Anthem Challenge. This donation will be used as prize money starting from the 2026 competition and is expected to play a significant role in spreading KAIST's educational culture and fostering a sense of community.
< Photo 1. KAIST President Kwang-Hyung Lee (left) and the former Alumni Association President Hyung Kyu Lim at the ceremony for the signing of the pledge for Dr. Lim's donation. >
The School Song and National Anthem Challenge was first conceived in 2024 at the suggestion of President Kwang-Hyung Lee to enhance consensus on KAIST's values and educational philosophy and to inspire patriotism and school spirit. Participants express their sense of belonging and pride in KAIST by singing the KAIST school song, the national anthem, or the 'I'm a KAIST,' dedicated by Professor Sumi Jo, a visiting scholar at the Graduate School of Culture Technology. Notably, this year, a new category has been added where participants sing their self-composed 'My Own School Song,' making the stage more diverse.
The grand prize-winning team receives the President's Award and a prize of 1 million won. The top excellence award and participating teams also receive prizes and awards totaling 2 million won.
< Photo 2. At the ceremony for the signing of the donation pledge, KAIST President Kwang-Hyung Lee (left) is relaying a bouquet of flower and the plaque of appreciation to the former Alumni Association President Hyung Kyu Lim. >
Former Alumni Association President Hyung Kyu Lim stated, Love for the national community is the foundation of a sound global citizen consciousness. For me, love for this national community, along with family love, has been a great source of energy for growth.
He added, I hope this challenge of singing the national anthem and school song becomes a good nourishment for KAIST members to grow into global citizens with roots, expressing his thoughts on the donation.
President Kwang-Hyung Lee said, “I am grateful to former Alumni Association President Hyung Kyu Lim for his generous support of this meaningful program, which fosters pride in the school and raises interest in loving the country through the national anthem.” He added, “This donation will serve as an opportunity for KAIST members to cultivate a sense of belonging to the school and a sense of responsibility to the national community.”
Since 2018, former President Lim has annually donated prize money for the 'Linkgenesis Best Teacher Award,' encouraging faculty members who embody the values of creativity, challenge, and consideration. Furthermore, he has consistently contributed to KAIST's talent development and advancement by continuing to provide funds totaling 1 billion won, including scholarship funds for the Department of Electrical Engineering and the Alumni Academic Scholarship Foundation.
< Photo 3. Grand prize-winning team of the School Song and National Anthem Challenge >
Meanwhile, the '2nd School Song and National Anthem Challenge' was successfully held on May 21st at the main auditorium of KAIST, with over 150 spectators participating. Eight teams performed in the finals, and the final winning team was selected based on audience evaluation (10%) and judges' scores (90%).
< Photo 4. Grand prize-winning team of the School Song and National Anthem Challenge, Aeguk-Rock in performance >
The grand prize was awarded to the 'Aeguk-Rock' team, who arranged the national anthem into a rock version and performed it as a band. The top excellence award went to the 'Form of the Conductor' team, who sang the school song a cappella. The excellence award was given to Eun-Jin Choi, a student from the Graduate School of Culture Technology, who performed her self-composed school song written with an AI tool, 'Radiant You – You Are KAIST.' The 'Aeguk-Rock’ team also won the audience popularity award, and five other teams received participation awards.
< Photo 5. Group photo of the winners of the School Song and National Anthem Challenge >
2025.05.23 View 1878