-
InnoCORE Research Group Successfully Achieves AI Protein Design with Nobel Laureate David Baker
< (From left) Professor Gyu Rie Lee, Professor David Baker >
Under the foundation of research cooperation established through the Ministry of Science and ICT's InnoCORE (InnoCORE) project, KAIST InnoCORE researchers have derived meaningful research results. Following a visit by Professor David Baker (University of Washington, USA), the 2024 Nobel Laureate in Chemistry, KAIST has revealed research findings on designing proteins that accurately recognize desired compounds using AI through joint research.
KAIST announced on April 9th that Professor Gyu Rie Lee of the Department of Biological Sciences—a researcher participating in the AI-CRED Innovative Drug InnoCORE Research Group—successfully designed artificial proteins that selectively recognize specific compounds using AI through joint research with Professor David Baker.
This research is characterized by using AI to design proteins that recognize specific compounds from scratch (de novo) and implementing them as functional biosensors. While the conventional approach mainly involved searching natural proteins or modifying some of their functions, this research is highly significant in that it ‘custom-built’ proteins with desired functions through AI-based design and even completed experimental verification.
In particular, the research team successfully designed a protein that selectively recognizes the stress hormone cortisol and implemented an AI-designed biosensor based on it. This is evaluated as a case that extends beyond protein design to actual measurable sensor technology, solving the long-standing challenge of small-molecule recognition in the field of protein design.
These research results are expected to be utilized in various fields such as disease diagnosis, new drug development, and environmental monitoring in the future. It can precisely detect biomarkers in the blood to diagnose diseases early and contribute to the development of targeted therapies through the design of proteins that selectively recognize specific molecules. Furthermore, it is expected that the implementation of customized biosensor technology will become possible, such as real-time monitoring of air and water quality through the development of sensors that detect environmental pollutants.
Designing new proteins (de novo proteins) that recognize compounds has been considered a challenge in the field of protein design for a long time because it requires precise calculations at the atomic level. The research team developed an AI model that precisely reflects protein-ligand interactions and successfully designed binding proteins using it.
As a result, artificial binding proteins were designed for six types of compounds, including metabolites and small-molecule drugs, and their functions were verified through experiments. In particular, a cortisol biosensor was developed by designing a chemical-induced dimer based on a new protein that binds with cortisol. A provisional patent for the relevant design technology has been filed in the United States.
Professor Gyu Rie Lee stated, “This research experimentally proves that AI can be used to design proteins that precisely recognize specific compounds,” and added, “We plan to expand this into protein design technology that can be utilized in various fields such as disease diagnosis, new drug development, and environmental monitoring in the future.”
Professor Gyu Rie Lee of the KAIST Department of Biological Sciences participated in this research as the first author, and Professor David Baker as the corresponding author. The study was published in the international academic journal Nature Communications on March 28, 2026. ※ Paper Title: Small-molecule binding and sensing with a designed protein family DOI: https://doi.org/10.1038/s41467-026-70953-8 Authors: Gyu Rie Lee, Samuel J. Pellock, Christoffer Norn, Doug Tischer, Justas Dauparas, Ivan Anishchenko, Jaron A. M. Mercer, Alex Kang, Asim K. Bera, Hannah Nguyen, Evans Brackenbrough, Banumathi Sankaran, Inna Goreshnik, Dionne Vafeados, Nicole Roullier, Hannah L. Han, Brian Coventry, Hugh K. Haddox, David R. Liu, Andy Hsien-Wei Yeh & David Baker
< Image of Research Content Summary >
Professor Gyu Rie Lee is a new professor who joined KAIST in February 2025 and leads the Protein Design Laboratory. She possesses world-class expertise in the field of precise protein complex design at the atomic level and is performing various research projects such as AI-based protein design, artificial enzyme design, and RNA-recognizing protein development. She is also participating as a mentor professor in the AI-CRED Innovative Drug Research Group of the InnoCORE project, conducting research on enzyme and peptide drug design.
Professor Lee conducted research as a postdoctoral researcher and Staff Scientist in Professor David Baker’s laboratory (University of Washington, USA, Howard Hughes Medical Institute) from 2018 to 2024. Professor David Baker is a world-renowned scholar in the field of protein structure prediction and design and was awarded the Nobel Prize in Chemistry in 2024.
Director Do-Heon Lee, a mentor professor of the AI-CRED Innovative Drug Research Group, stated, “This achievement is a meaningful result derived through cooperation between InnoCORE researchers and a global scholar,” and added, “We will further strengthen our research capabilities based on active research collaboration with postdoctoral researchers recruited through the InnoCORE project to continue creating innovative results in the AI drug development and bio-fields.”
Meanwhile, KAIST will host a lecture on Thursday, April 9th at 4 PM in the KI Building Fusion Hall featuring Professor David Baker and Professor Hannele Ruohola-Baker (University of Washington, USA) under the theme of ‘Advances in AI-powered protein design and biomedical science’ to mark Professor David Baker’s visit to Korea. This event is held with the support of the KAIST International Scholar Invitation Program, KAI-X, the InnoCORE AI-CRED Innovative Drug Group, and the Ministry of Science and ICT’s Overseas Excellent Research Institute Cooperation Hub Construction Project.
< Poster for Professor David Baker’s Invited Lecture >
KAIST President Kwang Hyung Lee stated, “Through cooperation with Nobel Laureate Professor David Baker, we have derived a meaningful achievement in AI-based protein design,” and added, “This research is an example showing that KAIST is leading innovative research alongside world-class research institutions.”
Meanwhile, the KAIST InnoCORE Research Group aims to accelerate AI-based scientific and technological innovation and promote global joint research by supporting top-tier domestic and international postdoctoral researchers to devote themselves to the development of AI convergence technology in a cutting-edge collective research environment. As the lead institution, KAIST operates the ▲Hyper-scale Large Language Model Innovation Research Group ▲AI-based Intelligent Design-Manufacturing Integration Research Group ▲AI-CRED Innovative Drug Research Group and ▲AI-Transformed Aerospace Research Group.
2026.04.09 View 234 -
KAIST Presents Roadmap for AFM Utilization in Next-Generation Semiconductor and Energy Materials Research
<(From Left) Ph. D candidate Yeongyu Kim, Professor Seungbum Hong, Ph.D candidate Kunwoo Park>
For smartphones and computers to become smaller and faster, technologies capable of precisely controlling electrical properties at the nanoscale—beyond what is visible to the naked eye—are essential. In particular, ferroelectric materials, which can maintain their electrical state without external power, are gaining attention as key components for next-generation memory and sensor technologies. However, due to their extremely small size, there have been limitations in precisely observing the internal changes occurring within these materials.
KAIST (President Kwang Hyung Lee) announced on the 4th of April that a research team led by Professor Seungbum Hong from the Department of Materials Science and Engineering has published a review paper systematically outlining research strategies for ferroelectric materials based on atomic force microscopy (AFM), addressing these limitations.
The research team proposed new strategies for utilizing AFM to precisely control electrical properties at the nanoscale and presented a direction for next-generation materials research.
Ferroelectric materials possess electric polarization similar to magnetism, and this property enables the realization of memory devices that retain information even without power, as well as highly sensitive sensors. As semiconductor devices continue to shrink, nanoscale physical phenomena increasingly determine overall device performance, making technologies capable of precisely analyzing and controlling these phenomena more important than ever.
The team presented an integrated analytical framework that uses AFM to both observe and directly manipulate materials at the nanoscale. AFM is a device that scans surfaces using an extremely fine probe to obtain atomic-level information, effectively serving as both the “eye” and “hand” of the nanoscale world.
Based on AFM, which measures physical and electrical properties at the atomic scale by scanning surfaces with a fine probe, the researchers established a system that integrates various techniques—including piezoresponse force microscopy (PFM) for measuring electrical responses, Kelvin probe force microscopy (KPFM) for analyzing surface potential, and conductive atomic force microscopy (C-AFM) for measuring current flow—into a unified framework. This allows for a three-dimensional understanding of material structures and charge distributions.
This approach goes beyond simple observation and represents the evolution of AFM into a research platform capable of directly designing and manipulating data domains at the nanoscale by applying electrical stimuli through the probe.
Furthermore, AFM can apply electrical stimulation or mechanical pressure directly to extremely small nanoscale regions, enabling changes and control of material properties. In other words, it has evolved from a tool that merely observes to one that enables design and experimentation at the nanoscale. In particular, this study demonstrates applications in evaluating and improving the performance of next-generation semiconductor materials such as two-dimensional transition metal dichalcogenides like molybdenum disulfide (MoS₂) and ultrathin hafnium–zirconium oxide (HfZrO₂)-based materials.
The research team also proposed future directions involving the integration of high-speed AFM with artificial intelligence (AI), enabling rapid interpretation of complex nanoscale structures that are difficult for humans to analyze manually, as well as more efficient design of advanced materials.
< Research Image (AI-Generated Image) >
Professor Seungbum Hong stated, “This review shows that atomic force microscopy has evolved beyond a simple observation tool into a key process technology for designing and precisely controlling advanced materials,” adding, “Analytical techniques combined with artificial intelligence will play a critical role in securing technological competitiveness in next-generation semiconductor and energy materials.”
This review was led by Yeongyu Kim (Doctoral student) and Kunwoo Park (integrated MS–PhD program student), both from the Department of Materials Science and Engineering at KAIST, as co-first authors. The research was recognized for its excellence and published as a front cover article in the international journal Journal of Materials Chemistry C, published by the Royal Society of Chemistry, on February 26.
※ Paper title: “Atomic Force Microscopy for Ferroelectric Materials Research”
DOI: https://pubs.rsc.org/en/content/articlehtml/2026/tc/d5tc03998c
< Front Cover Selection Image for Journal of Materials Chemistry C (JMCC) >
This work was supported by the Ministry of Science and ICT and the National Research Foundation of Korea through the project on developing an AI platform for multi-scale data-integrated lithium secondary battery design, and has been recognized as establishing a new milestone in the field of nanomaterials.
2026.04.08 View 149 -
Era of Ultra-Slim, Wide Field-of-View and , High-Resolution Cameras Opens with Natural Vision Principles
<(From left) Young-Gil Cha, Hyun-Kyung Kim, Jae-Myeong Kwon, Professor Ki-Hun Jeong, (Top right) Professor Min H. Kim>
A breakthrough technology has emerged to fundamentally solve the "camera protrusion/thickness issue," which has been a persistent limitation as smart devices become thinner. KAIST research team has developed an ultra-thin camera that achieves a wide 140-degree field of view (FOV) without any lens protrusion. This technology is expected to be applied across various fields, including medical endoscopes, wearable devices, and micro-robots.
On the 7th, a joint research team led by Professor Ki-Hun Jeong from the Department of Bio and Brain Engineering and Professor Min H. Kim from the School of Computing announced the development of a "wide-angle biomimetic camera." Inspired by insect vision, the camera is exceptionally thin yet boasts a vast field of view. The team successfully secured a diagonal FOV of 140 degrees—surpassing human peripheral vision—within an ultra-thin structure of less than 1 mm, roughly the thickness of a coin.
High-performance wide-angle cameras typically require multiple stacked lenses, inevitably leading to increased thickness. To overcome this, the research team focused on the visual structure of the parasitic insect Xenos peckii.
<Conceptual diagram of the camera structure mimicking insect compound eye principles and photos of the manufactured ultra-thin camera>
While typical insect compound eyes offer a wide FOV, they suffer from low resolution. Conversely, single-lens cameras provide high resolution but limited FOV. Xenos peckii, however, possesses a unique visual system where multiple eyes capture partial segments of a scene, which the brain then integrates into a single high-resolution image. By introducing this "split-capture and integration" principle into the camera architecture, the team simultaneously achieved both thinness and high image quality. This overcomes the low-resolution issues of conventional compound eye cameras and the narrow FOV limits of single-lens systems.
<Result of reconstructing a single scene by combining partial images captured via a microlens array>
The team implemented a method where several micro-lenses with ellipsoidal shape capture different directions simultaneously, merging them into one sharp image without optical aberration. Notably, by precisely adjusting the lens shape and light entry points, they prevented blurring at the edges of the frame. As a result, uniform clarity is maintained from the center to the periphery, enabling stable imaging even at very close ranges.
With a thickness of only 0.94 mm, this ultra-thin camera is expected to bring innovation to space-constrained fields. It can significantly enhance image acquisition efficiency for medical endoscopes requiring precise observation of narrow areas, as well as for micro-robots and wearable healthcare equipment. This technology shifts the design paradigm from increasing device size for better performance to enabling high-performance imaging in ultra-small form factors.
<Results of photographing actual subjects at close range: microfluidic channels (20 mm distance), oral models (30 mm), and human faces (50 mm)>
Furthermore, the research team has completed a technology transfer to MicroPix Co., Ltd., a specialist in optical imaging, with the goal of full-scale commercialization by next year.
"Conventional wide-angle cameras faced a trade-off where reducing size lowered resolution, and increasing resolution enlarged the device," explained Professor Ki-Hun Jeong. "By applying visual principles from nature, we have secured both a wide FOV and stable image quality in an ultra-compact structure. This is a new image acquisition method usable even in extreme space-constrained environments."
Jae-Myeong Kwon, Ph.D candidate at KAIST, participated as the lead author. The study was published on March 23 in the world-renowned academic journal Nature Communications.
Paper Title: Biologically inspired microlens array camera for high-resolution wide field-of-view imaging
DOI: https://doi.org/10.1038/s41467-026-70967-2
Authors: Jae-Myeong Kwon, Yejoon Kwon, Young-Gil Cha, Dong Hyun Han, Hyun-Kyung Kim, Je-Kyun Park, Min H. Kim & Ki-Hun Jeong
This research was conducted with support from the Mid-Career Researcher Program of the National Research Foundation of Korea (Ministry of Science and ICT), the Korean ARPA-H Project (Ministry of Health and Welfare), and the Materials and Components Technology Development Program (Ministry of Trade, Industry and Energy).
2026.04.07 View 273 -
KAIST Develops Electrode Technology Achieving 86% Efficiency for Converting CO₂ into Plastic Precursors
<(From Left) Dr. Jonghyeok Park, Ph.D candidate Yunkyoung Han, Professor Hyunjoon Song, Dr. Sungjoo Kim>
KAIST Develops Electrode Technology Achieving 86% Efficiency for Converting CO₂ into Plastic Precursors
In the process of converting carbon dioxide into useful chemicals such as ethylene—a key precursor for plastics—a major challenge has been the flooding of electrodes, where electrolyte penetrates the electrode structure and reduces performance. KAIST researchers have developed a new electrode design that blocks water while maintaining efficient electrical conduction and catalytic reactions, thereby improving both efficiency and stability.
KAIST (President Kwang Hyung Lee) announced on the 6th of April that a research team led by Professor Hyunjoon Song from the Department of Chemistry has developed a novel electrode structure utilizing silver nanowire networks—ultrafine silver wires arranged like a spiderweb—to significantly enhance the efficiency of electrochemical CO₂ conversion to useful chemical products.
In electrochemical CO₂ conversion processes, a long-standing issue has been flooding, where the electrode becomes saturated with electrolyte, reducing the space available for CO₂ to react. While hydrophobic materials can prevent water intrusion, they typically suffer from low electrical conductivity, requiring additional components and complicating the system.
To overcome this, the research team designed a three-layer electrode architecture that simultaneously repels water and enables efficient charge transport. The structure consists of a hydrophobic substrate, a catalyst layer, and an overlaid silver nanowire (Ag NW) network, which acts as an efficient current collector while preventing electrolyte flooding.
< Schematic diagram of a porous polymer–copper oxide catalyst silver nanowire network electrode structure >
A key finding of this study is that the silver nanowires do more than just conduct electricity—they actively participate in the chemical reaction. During CO₂ reduction, the silver nanowires generate carbon monoxide (CO), which is then transferred to adjacent copper-based catalysts, where further reactions occur. This creates a tandem catalytic system, in which two catalysts cooperate sequentially, significantly enhancing the production of multi-carbon compounds such as ethylene.
The electrode demonstrated outstanding performance. It achieved 79% selectivity toward C₂₊ products in alkaline electrolytes and 86% selectivity in neutral electrolytes, representing a world-leading level. It also maintained stable operation for more than 50 hours without performance degradation. These results indicate that most of the converted products are the desired chemicals, while also overcoming the durability limitations of conventional systems.
< Conceptual diagram of a CO₂ electrolysis electrode utilizing a stacked silver nanowire structure (AI-generated image) >
Professor Hyunjoon Song stated, “This study is significant in showing that silver nanowires not only serve as electrical conductors but also directly participate in chemical reactions,” adding, “This approach provides a new design strategy that can be extended to converting CO₂ into a wide range of valuable products such as ethanol and fuels.”
This research, led by Jonghyeok Park (KAIST, first author), was published on March 24, 2026, in the international journal Advanced Science.
※ Paper title: “Overlaid Conductive Silver Nanowire Networks on Gas Diffusion Electrodes for High-Performance Electrochemical CO₂-to-C₂₊ Conversion,” DOI: https://doi.org/10.1002/advs.75003
2026.04.07 View 164 -
KAIST Achieves 3-fold Increase in Hydrogen Production Using “High-Entropy” Design—More Mixing, More Strength
<(From Left) Professor Kang Taek Lee, Ph.D candidate Seeun Oh, Researcher Incheol Jeong, Dr. Dongyeon Kim, Ph.D candidate Hyeonggeun Kim>
While mixing materials typically leads to instability, there exists a phenomenon known as “high entropy,” where increasing compositional complexity can actually enhance stability. KAIST researchers leveraged this principle to enable faster proton transport and more efficient reactions within electrochemical cells, developing a technology that significantly improves hydrogen production efficiency. This breakthrough is expected to reduce hydrogen costs and accelerate the transition to clean energy.
KAIST (President Kwang Hyung Lee) announced on the 5th of April that a research team led by Professor Kang Taek Lee from the Department of Mechanical Engineering has developed a novel oxygen electrode material that dramatically improves reaction kinetics and power performance through entropy-maximized design. The oxygen electrode is a key component in electrochemical cells where oxygen evolution occurs during hydrogen production.
Green hydrogen—produced from water without carbon emissions—is considered a cornerstone of future clean energy systems. In particular, protonic ceramic electrochemical cells (PCECs), which generate hydrogen by splitting water using electrical energy while protons migrate through the cell, have attracted attention for their high efficiency. However, their performance has been limited by slow reaction kinetics at the oxygen electrode.
To address this issue, the research team adopted a high-entropy strategy, introducing multiple metal elements simultaneously to increase configurational disorder. Although mixing many elements typically destabilizes structures, under certain compositions, maximizing entropy can instead stabilize a single-phase structure.
<Structural and chemical characterization of PBSCF and PLNNCBSCF. XRD patterns of a) the synthesized PBSCF and PLNNCBSCF and b) enlarged view of the XRD patterns from 31.5 to 33.5°. c) Rietveld refinement results of the XRD profile for PLNNCBSCF, with the inset showing the idealized structure. d) HR-TEM image of PLNNCBSCF with the inset showing lattice fringes. e) Corresponding EDS mappings of the PLNNCBSCF elements. XPS of F) survey peak, G) Pr 3d, and H) O 1s spectra for PBSCF and PLNNCBSCF>
Based on this concept, the researchers designed a high-entropy double perovskite oxygen electrode by incorporating seven different metal elements (Pr, La, Na, Nd, Ca, Ba, Sr) into the A-site of the electrode structure. This material combines a perovskite crystal framework with a double perovskite structure, further enhanced by high-entropy design.
The presence of multiple mixed metal elements improves charge transport and oxygen-related reactions within the electrode, resulting in significantly faster electrochemical reactions for both electricity generation and hydrogen production.
Notably, density functional theory (DFT) calculations revealed that the energy required to form oxygen vacancies—active sites where reactions occur—was reduced by more than 60% compared to conventional materials. This indicates that reactive sites can form more easily and in greater abundance.
Additionally, time-of-flight secondary ion mass spectrometry (TOF-SIMS) analysis showed that proton transport speed increased by more than sevenfold, demonstrating that hydrogen generation processes proceed much more efficiently within the electrode.
The performance improvements were substantial. Cells incorporating the new electrode achieved a power density of 1.77 W cm⁻² at 650°C, approximately 2.6 times higher than conventional systems. Hydrogen production performance also improved by approximately threefold (4.42 A cm⁻²) under the same conditions.
Moreover, in long-term testing under steam conditions for 500 hours, performance degradation was only 0.76%, confirming excellent durability and stability over extended operation.
Professor Kang Taek Lee stated, “This study demonstrates that the thermodynamic concept of entropy can be used to control electrode reactivity,” adding, “It has the potential to significantly enhance green hydrogen production efficiency and accelerate the commercialization of the hydrogen economy.”
This study was co-led by Seeun Oh of the Department of Mechanical Engineering at KAIST and Incheol Jeong of the Korea Institute of Geoscience and Mineral Resources. The findings were published on December 16, 2025, in the international journal Advanced Energy Materials (IF: 26.0) and were selected as a front cover article, highlighting their scientific impact.
※ Paper title: “Unveiling Entropy-Driven Performance Enhancement in Double Perovskite Oxygen Electrodes for Protonic Ceramic Electrochemical Cells,” DOI: https://doi.org/10.1002/aenm.202503176※ Authors: Seeun Oh (KAIST, first author), Incheol Jeong (Korea Institute of Geoscience and Mineral Resources, first author), Dongyeon Kim (second author), Hyeonggeun Kim (second author), Kang Taek Lee (corresponding author)
This research was supported by the Mid-Career Researcher Program and the Global Basic Research Laboratory Program funded by the Ministry of Science and ICT (MSIT), Korea.
2026.04.06 View 149 -
Undergraduate Rover Team (MR2) Advances to Finals of 'URC 2026', the World’s Largest Mars Rover Competition
<Photo: KAIST Undergraduate Club MR2 Team Members>
Undergraduate students from KAIST are set to take on the world stage with an exploration rover—a robotic vehicle designed to explore in place of humans—that they built themselves. The team has secured a spot in the finals of the world’s largest Mars rover competition, marking a first-ever achievement for KAIST.
KAIST announced on the 3rd that 'MR2' (Advised by Professor Yong-Hwa Park, Department of Mechanical Engineering), a rover team from the undergraduate robotics club MR (Microrobot Research), has earned a seed in the finals of the '2026 University Rover Challenge (URC)', the premier international Mars rover competition for university students.
The URC is organized by The Mars Society and takes place at the Mars Desert Research Station (MDRS) in Utah, USA, an environment that closely mimics the Martian surface. Participating teams compete in four key missions using rovers they developed: ▲Science Mission, ▲Delivery Mission, ▲Equipment Servicing Mission, and ▲Autonomous Navigation Mission.
This year’s competition saw 116 university teams from 18 countries engage in a fierce preliminary round. Team MR2 secured its place in the top 38 finalists by scoring 95.38 out of 100. This milestone is particularly significant as it is the first time a KAIST team has ever reached the URC finals, proving the excellence of KAIST undergraduates in robot design and control on a global scale.
The next-generation exploration rover 'GAP-1000', independently developed by MR2, is a modular rover designed for stable operation in extreme environments. It features a 6-DOF (Degrees of Freedom) robotic arm capable of precisely controlling objects over 5kg, allowing it to perform complex equipment manipulation tasks.
<Photo: Operation of GAP-1000's Manipulator and Science Module Integration>
The rover also boasts strong autonomous driving capabilities. By combining RTK-GNSS (precision satellite positioning), IMU (Inertial Measurement Units) for motion sensing, and odometry based on wheel rotation, it can autonomously navigate optimal paths through complex terrain. Additionally, a drone relay system has been integrated to ensure stable exploration even in areas with communication dead zones.
For the science mission, the rover can collect soil from 10cm underground, remove impurities via centrifugation, and analyze traces of life using protein detection reagents such as Biuret and Bradford. This is paired with spectroscopic analysis technology that identifies material composition by analyzing light wavelengths, creating an integrated system for real-time life detection.
"We experienced a lot of trial and error while managing everything from design to production ourselves, but I am thrilled that we achieved KAIST’s first-ever advancement to the finals," said Myung-woo Jung (Department of Mechanical Engineering), the team leader of MR2. "We will prepare thoroughly in the remaining time to achieve a great result on-site."
<Photo: Scenery of MDRS in Utah, USA, where the competition will be held (Photo Credit: The Mars Society)>
Advising Professor Yong-Hwa Park noted, "It is impressive that the students independently implemented a rover for extreme environments. This competition will serve as an opportunity to showcase KAIST’s technological prowess to the world."
KAIST President Kwang-Hyung Lee added, "It is a very meaningful achievement for our undergraduates to reach the finals of the world’s largest competition with a rover they designed and built themselves. I hope this experience serves as a catalyst for our students to challenge themselves and grow on the global stage."
Team MR2 consists of 13 undergraduate students from various majors, including Mechanical Engineering, Electrical Engineering, and Industrial Design. Having completed long-distance operation tests in outdoor environments, they are currently conducting final checks for the finals. The main competition will be held from May 27th to 30th at the MDRS in Utah, USA.
※ Related Links
MR2 Official Website: https://urc-kaist.github.io/
MR2 Instagram: https://www.instagram.com/urc_mr2/
MR2 YouTube: https://www.youtube.com/@MR2KAISTRoverTeam
2026.04.03 View 255 -
KAIST, Developing National Positioning Infrastructure with Wi-Fi-Based Precision Technology… A Step Toward “Location Sovereignty”
<(From Left) Prof. Dong-Soo Han, Dr. Kyuho Son, Dr. Byeongcheol Moon, Dr. Sumin Ahn, Ph.D candidate Seungwoo Chae>
A Korean research team has developed a technology that enables precise indoor positioning using only a smartphone. Developed over eight years by KAIST researchers, this technology is expected to help secure critical time in missing-person searches and is being recognized as a “location sovereignty” solution that could reshape the current location service ecosystem dominated by global big tech companies such as Google and Apple.
KAIST (President Kwang Hyung Lee) announced on the 2nd pf April that a research team led by Professor Dongsoo Han of the School of Computing has developed a core technology that can build a nationwide high-precision positioning infrastructure in a short time and at low cost by combining smartphone Wi-Fi signals with real-world address data. This achievement is the result of eight years of research, during which the team filed around ten patents to enhance the technology’s completeness.
The key feature of this technology is its use of Wi-Fi signals collected by smartphones in everyday life. It can provide precise location information anywhere in the country without requiring large-scale equipment or additional infrastructure. It also maintains high accuracy in environments where GPS is weak, such as indoors, underground, or in dense high-rise areas.
In particular, this research is seen as a challenge to the location service ecosystem currently led by global platform companies. Today, most location data worldwide is accumulated and managed by a small number of big tech firms, and Korea also relies heavily on these platforms.
Most importantly, this research establishes a foundation for independently building and managing location data generated domestically. Amid ongoing debates over exporting high-resolution national maps (1:5,000 scale spatial data detailing buildings and roads), the importance of data sovereignty is growing. This technology is drawing attention as an alternative that could reduce dependence on global big tech and realize “location sovereignty.”
The research team proposed a method that automatically combines Wi-Fi signals collected during smartphone app usage with the actual address of the location. This allows the construction of a unique “signal pattern map” (signal fingerprint) for each place, with accuracy improving as more data accumulates.
In a real-world demonstration in Daejeon, using a gas meter reading app, an average of about 30 Wi-Fi signals were detected per household in apartment complexes. This confirmed that city-scale location data can be rapidly built using this approach.
<Status of Radio Map Construction in Daejeon Using a Gas Meter Reader App>
<Address-Based Automation of Wireless Signal Collection and AI-Based Location Labeling Techniques for Collected Wireless Signals>
This technology is expected to significantly reduce location errors—previously up to hundreds of meters—in emergency situations such as missing-person searches, helping secure critical response time. It can also be applied to “location-based authentication,” allowing payments only at specific locations, thereby helping prevent financial crimes such as identity theft or unauthorized remote transactions.
Furthermore, precise location data is a key infrastructure for future AI industries, including autonomous driving, robotics, and logistics. This achievement is expected to enhance competitiveness across these sectors.
<Research Use Image (AI-Generated Image)>
Professor Dongsoo Han stated, “Positioning infrastructure is not just a convenience technology but a core asset directly linked to national data sovereignty,” adding, “It is time for the government, telecom companies, and platform providers to collaborate in building an independent national positioning infrastructure.”
This research was supported by the Ministry of Science and ICT, the National Research Foundation of Korea, the National Fire Agency, and the Korea Evaluation Institute of Industrial Technology (KEIT) (Grant No. RS-2025-02313957).
2026.04.03 View 316 -
KAIST Reconstructs the Power Map Behind Gyeyu Coup, Revealing the Dynamics of Joseon Bureaucracy
<(From Left) Professor Juyoung M. Park, Dr. Donghyeok Choi>
With the recent popularity of the film The King’s Warden, public interest has grown in the tragic history of King Danjong and Prince Suyang (later King Sejo), particularly surrounding Suyang’s Revolt of 1453 (the Gyeyu Coup). While the film dramatizes the political conflict, how did the fates of the real historical figures diverge? A joint team of KAIST and Hong Kong-based researchers has scientifically uncovered the patterns of success and downfall in Joseon’s bureaucratic society by analyzing data from the Annals of the Joseon Dynasty and Mungwa Bangmok, the higher civil service examination (gwageo) records.
KAIST (President Kwang Hyung Lee) announced on the 1st of April that a research team led by Professor Juyong M. Park of the Graduate School of Culture Technology, in collaboration with Dr. Donghyeok Choi (a KAIST alumnus) of Hong Kong Baptist University and the University of Hong Kong, analyzed the Annals of the Joseon Dynasty and Mungwa Bangmok using digital humanities and complex systems science methodologies. From these they were able to characterize the career patterns of over 14,600 Joseon officials.
<The original text of the Annals of the Joseon Dynasty from the time of the Gyeyu Jeongnan (left) and its online Korean translation (right)>
The team found that when Joseon’s recruitment system through gwageo was functional, its bureaucracy exhibited stability. When power became concentrated in oligarch families in the later period through abnormal means, however, inequality and stratification in the bureaucratic system intensified, ultimately leading to a national decline. In other words, the fall of Joseon was not the result of a single isolated event but can be seen as a consequence of a ‘systemic collapse,’ as demonstrated through data.
The Annals of the Joseon Dynasty, a globally recognized historical record spanning over 600 years, provides extensive data that allows for the precise reconstruction of political and social structures of the time. The researchers first conducted a quantitative analysis of the 1453 Revolt of Suyang, a dramatic event in early Joseon’s power structure. By constructing a network of officials connected to King Danjong, Prince Suyang (later King Sejo), and Prince Anpyeong during the event, they found data-driven findings that those closely aligned with Sejo were decorated, while those aligned with Anpyeong were purged.
<A network of connections among key royal figures of the Gyeyu Jeongnan—King Danjong, Grand Prince Suyang (later King Sejo), Grand Prince Anpyeong—and government officials, reconstructed from the records of the Annals>
But considering such a forced dethronement of a king was rare in Joseon’s history, the team turned to characterizing the more long-term features of the bureaucracy. To do this they developed a metric called “Total Success Index” that combines the rank of official positions held and the duration of service. The analysis then revealed that for approximately 400 years after the founding of Joseon, some positive correlation existed between individual background (family, regional origin, etc.) and individual success, but the correlation remained relatively stable, suggesting a certain degree of fairness and social mobility persisted.
<A Method for Defining a Bureaucrat’s Total Success Index Based on the Sum of Ranks Recorded in the Annals>
However, this stability began to disappear in the later Joseon period as powerful oligarch families such as the Andong Gims and Pungyang Jos passed higher civil service exams and assumed official positions through influence and power rather than competition, leading to a rapid intensification of inequality and stratification within the bureaucracy, indicating the breakdown of the traditional recruitment system. The researchers observed that Joseon society, unable to resolve these issues, ultimately declined and collapsed.
<A Correlation Between the Total Success Index Calculated from the Annals and the Region and Family Background Recorded in the Civil Service Examination Rosters>
Professor Juyong M. Park stated, “This study tries to go beyond the limitations of focusing on short-term historical events, examining the long-term structural changes across the entire history of a nation,” adding, “Understanding how individual and group actions influence the rise and fall of a state provides important insights into issues of fairness and talent recruitment, relevant to this modern day.”
<A Diagram Illustrating the Domination of the Bureaucracy by Specific Families (the Andong Kim, Pungyang Jo, Yeoheung Min, and Bannam Park Clans) in the Late Joseon Period>
He further added, “The integration of digitized historical data and scientific data analysis will become a key tool not only for understanding the past but also for guiding the future of society.”
The research team now plans to expand the Joseon historical database using artificial intelligence (AI), compare Joseon’s bureaucratic system with other countries’, and analyze the records of international interactions to further explore the global historical significance of Joseon.
This study was conducted with Dr. Donghyeok Choi (Ph.D. graduate of KAIST’s Graduate School of Culture Technology) as the first author, published in the April issue of Physica A: Statistical Mechanics and Its Applications.
※ Paper title: “Total Success Index and the Longitudinal Dynamics of Bureaucratic Stratification in Joseon Korea” (https://shm.to/bYJ0SBo) / DOI: 10.1016/j.physa.2026.131353
This research was supported by the National Research Foundation of Korea’s interdisciplinary research program, the Humanities and Social Science Research Institute Support Program, the BK21 Phase 4 Program, the Korea Creative Content Agency’s R&D program for copyright service innovation, KAIST’s Post-AI program, and the Korea Institute for Advanced Study (KIAS).
2026.04.02 View 218 -
Excellence Award at the 4th Wonik Next-Generation Engineering Award
< 4th Wonik Next-Generation Engineering Award hosted by the National Academy of Engineering of Korea (NAEK)>
At the 4th Wonik Next-Generation Engineering Award hosted by the National Academy of Engineering of Korea (NAEK), KAIST Ph.D candidate Yehhyun Jo from the Department of Electrical Engineering(Advisor: Professor Hyunjoo J. Lee) and Ph.D candidate Seokjoo Cho from the Department of Mechanical Engineering(Advisor: Prof. Inkyu Park) received Excellence Awards.
Yehhyun Jo was selected in recognition of the development of a system that enables the precise modulation and observation of brain functions by integrating ultrasound neuromodulation technology, MEMS, and biosignal measurement technology. As a leading researcher in ultrasound brain stimulation in Korea, Yehhyun has contributed to the advancement of next-generation neuroengineering research by publishing six SCI(E)-indexed first-author papers.
In acceptance speech, Yehhyun Jo remakred, “It is a great honor to receive the Excellence Award at the Wonik Next-Generation Engineering Award hosted by the National Academy of Engineering of Korea. I believe this award represents not only my personal achievements, but also the collective efforts of my advisor, fellow researchers, and my parents and brother, who have supported my research behind the scenes. Going forward, I will continue to develop and validate technologies grounded firmly in fundamental principles so that engineering innovation can reach real clinical and industrial settings, and I will strive to become a great researcher who contributes to society through responsible research.”
<(From Left) Ph.D candidate Yehhyun Jo, Ph.D candidate Seokjoo Cho>
Seokjoo Cho was selected for developing a wireless multi-modal sensing system based on nano- and micro-fabrication processes for the management of chronic wounds and metabolic diseases. Through this related work, Seokjoo has published 25 SCI(E)-indexed papers and is leading technological innovation in next-generation healthcare sensor platforms.
He accepted the award, saying, “I am sincerely grateful to receive the great honor of the Wonik Next-Generation Engineering Award. Winning an award that I have long dreamed of as a researcher during my graduate studies brings me both deep fulfillment and a strong sense of responsibility. Taking this award as an opportunity, I will continue striving to grow as a researcher who does not lose sight of my original motivation and who can create meaningful value for society.”
The Wonik Next-Generation Engineering Award is presented to undergraduate and graduate students in engineering-related fields in Korea to recognize creative and ambitious future engineers in the materials, components, and equipment sectors and support their growth into engineers who contribute to solving social problems.
The award ceremony was held on the afternoon of March 10 at the Grand Walkerhill Seoul Hotel in Gwangjin-gu, Seoul.
2026.04.01 View 216 -
AI Blueprints Stolen with a Single Antenna... Countermeasures Also Proposed
< Professor Jun Han >
From smartphone facial recognition to autonomous vehicles, Artificial Intelligence (AI) has long been protected as a "black box." However, a joint research team from KAIST and international institutions has uncovered a new security threat capable of "peeking" at AI blueprints from behind walls. The team also presented corresponding defense technologies. This discovery is expected to be utilized in strengthening AI security across various sectors, including autonomous driving, healthcare, and finance.
On the 31st, Professor Jun Han’s research team from the KAIST School of Computing announced that they, in collaboration with the National University of Singapore (NUS) and Zhejiang University, developed "ModelSpy"—an attack system capable of hijacking AI model structures from a distance using only a small antenna.
This technology works much like a bugging device, capturing and analyzing minute signals emitted while an AI is operational to reconstruct its internal structure. The research team focused on the electromagnetic (EM) waves generated by Graphics Processing Units (GPUs), which handle AI computations.
When an AI performs complex calculations, the GPU emits subtle electromagnetic signals. By analyzing the patterns of these signals, the team successfully restored the layer configurations and detailed parameter settings of the AI model.
Experimental results showed that the structure of AI models could be identified with high accuracy from up to 6 meters away or through walls, across five types of the latest GPUs. Notably, the team estimated the core structure—the layers of the deep learning model—with an accuracy of up to 97.6%.
< AI model structures can be stolen through walls using an antenna hidden in a bag >
This technology is considered a significant security threat because, unlike traditional hacking, it does not require direct server infiltration or malware installation. An attack can be carried out using only a portable antenna small enough to fit in a bag.
Recognizing that this technology could lead to the leakage of a company's core AI assets, the research team also proposed defensive measures, such as electromagnetic interference and computational obfuscation. This is being hailed as a responsible security study that goes beyond demonstrating an attack to suggesting realistic protection methods.
"This research demonstrates that AI systems can be exposed to new types of attacks even in physical environments," said Professor Jun Han. "To protect critical AI infrastructure, such as autonomous driving and national facilities, it is essential to establish 'cyber-physical security' systems that encompass both hardware and software."
< Research Image (AI-generated) >
Professor Jun Han of the KAIST School of Computing participated as a co-corresponding author. The study was presented at the NDSS (Network and Distributed System Security Symposium) 2026, a top-tier academic conference in computer security, where it received the Distinguished Paper Award in recognition of its innovation.
Paper Title: Peering Inside the Black-Box: Long-Range and Scalable Model Architecture Snooping via GPU Electromagnetic Side-Chan
Paper Link: https://www.ndss-symposium.org/ndss-paper/peering-inside-the-black-box-long-range-and-scalable-model-architecture-snooping-via-gpu-electromagnetic-side-channel/
2026.03.31 View 411 -
KAIST, Making Pharmaceuticals with Light and Air… Solving a Long-Standing Challenge in Chemical Synthesis
<(From Left) Professor Sang Woo Han, Researcher Jin Wook Baek>
In chemical processes for producing pharmaceuticals, catalysts are the key to determine production speed and cost. However, until now, there has been a trade-off between “precise but disposable catalysts” and “reusable catalysts.” A KAIST research team has developed an eco-friendly catalytic technology that combines these two types, operating with light and air. This opens a pathway to producing pharmaceutical ingredients more cheaply and cleanly, with expected reductions in carbon emissions and environmental pollution.
KAIST (President Kwang Hyung Lee) announced on the 30th of March that a research team led by Professor Sang Woo Han of the Department of Chemistry has succeeded in combining two different types of catalysts into one system. One is a silver (Ag)-based catalyst that operates in a solid state, and the other is an organic photocatalyst, DDQ (a substance that triggers chemical reactions upon absorbing light), which operates in solution. By enabling these two catalysts to function together, the team made it possible to carry out previously difficult reactions more efficiently.
< Schematic diagram of the operation of a heterogeneous–homogeneous hybrid photocatalytic system >
Using this technology, the researchers successfully produced amines—key raw materials for pharmaceuticals—through an environmentally friendly process using light and air. This demonstrated that the desired substances can be synthesized without additional chemical reagents, proving the practicality of the technology.
Conventional organic photocatalysis required additional chemicals to reuse catalysts after reactions, or suffered from reduced efficiency due to slow reaction rates when using oxygen from air.
To address this, the research team proposed a method of reusing byproducts generated during the reaction. These byproducts restore the catalyst to a reusable state, while oxygen in the air helps sustain this cycle. In other words, instead of being used once and discarded, the catalyst regenerates itself and continues operating in a “cyclic system.”
As a result, they established a “cyclic catalytic system” that continues functioning without the need for additional chemical inputs. Notably, this system operates with light and air. Light activates the catalyst to initiate the reaction, while air restores the used catalyst to its active state. In essence, the catalyst continuously “recharges” and operates repeatedly. Since air leaves only water as a byproduct in this process, the environmental burden is significantly reduced.
In addition, to solve the issue of reduced performance when different catalysts interact, the team introduced lithium salt (LiClO₄). This substance helps regulate interactions between the two catalysts, significantly improving their stability and lifespan.
< A hybrid catalyst powered by light and air as energy sources >
Professor Sang Woo Han stated, “This research is the first to successfully integrate an inorganic photochemical loop system—where a metal-based catalyst reacts under light and returns to its original state—into the field of organic synthesis,” adding, “It represents an important advancement that combines the advantages of different catalytic systems to dramatically reduce the carbon footprint of the chemical industry.” He further noted, “It opens a new pathway for producing high-value compounds, such as pharmaceutical ingredients, in the most environmentally friendly way.”
This research was conducted with Jin Wook Baek of the KAIST Department of Chemistry as the first author, and the results were published on March 18 in the Journal of the American Chemical Society (JACS), a leading journal in chemistry.
※ Paper title: “Merger of heterogeneous and homogeneous photocatalysis for arene C–H Amination”
※ DOI: 10.1021/jacs.5c20824
This research was supported by the National Research Foundation of Korea’s Mid-career Researcher Program.
2026.03.30 View 371 -
KAIST Enables Ultra-High-Resolution AR·VR Without Battery Burden
<(From Left) Professor Young Min Song, Ph.D candidate Hyo Eun Jeong, (Upper Left) Professor Hyeon-Ho Jeong, Dr. Joo Hwan Ko>
A new display technology has emerged that significantly increases resolution while consuming almost no power. A Korean research team has developed a “monopixel” structure in which a single pixel can independently change colors while consuming minimal energy to maintain them. This breakthrough opens the possibility of creating sharper AR/VR displays without heavy battery demands.
KAIST (President Kwang Hyung Lee) announced on the 29th of March that a research team led by Professor Young Min Song of the School of Electrical Engineering, in collaboration with Professor Hyeon-Ho Jeong’s team at Gwangju Institute of Science and Technology (GIST, President Ki-Cheol Lim), has developed a new low-power monopixel technology called a “reconfigurable Gires–Tournois resonator (r-GT).” This system uses electrochromic materials—substances that change color when electricity is applied—to produce colors with very low power consumption.
Displays have been making pixels increasingly smaller to achieve higher resolution. However, as pixels shrink, power consumption rises and brightness decreases. This is especially challenging for AR/VR devices, which must achieve both extremely small pixels and low power consumption due to their proximity to the human eye.
The r-GT pixel developed by the research team changes color when voltage is applied, and once changed, the color is maintained for a certain period even after the power is turned off. In other words, power is only required when changing colors, while maintaining color requires almost no energy.
The core of this technology lies in two elements. First is a conductive polymer, polyaniline (PANI), whose properties change when voltage is applied. This material responds even at voltages below 1 volt (V), altering its refractive index and thereby changing color. The refractive index refers to how much light bends when passing through a material, and changes in this value lead to changes in perceived color.
Second, the system incorporates a resonator structure that reflects light multiple times to amplify specific colors. This structure enhances even small changes, enabling vivid color expression with minimal power.
As a result, the system achieved a wide color variation exceeding 220° using ultra-low power (90 μW cm⁻²). In simple terms, it can express more than half of the full color wheel (360°) using only about 0.00009 watts per square centimeter.
Another key feature is the “monopixel” structure. Unlike conventional displays that divide a single pixel into red (R), green (G), and blue (B) subpixels, the monopixel approach allows one pixel to independently produce various colors. This enables more pixels within the same area, resulting in higher resolution and reduced light loss, leading to clearer images.
Additionally, PANI retains its color state even after the applied voltage is removed. This confirms the feasibility of a “memory-in-pixel” display, where energy is used only when changing colors, not when maintaining them.
<Reflective display AI image>
The research team demonstrated that this technology can achieve a wide color range (220.6°) and reduce pixel size to as small as 1.5 micrometers (μm), corresponding to an ultra-high resolution of up to approximately 16,900 PPI—beyond the level where individual pixels can be distinguished by the human eye.
Moreover, even with a single-pixel structure, the system can represent about 48.1% of the standard sRGB color gamut, and up to 69.9% with varied material combinations, enabling richer color expression.
The team fabricated a 5×5 monopixel array to verify performance. The energy required to change colors was extremely low (2.31 mJ), demonstrating up to 5.8 times lower power consumption compared to conventional LEDs. As a reflective display, it also becomes more visible under brighter ambient lighting, since it uses external light rather than emitting its own.
<Structure and Representative Results of an Electrically Tunable Single Reflective Resonant Device Using Conductive Polymers>
This study demonstrates that combining electrochemical materials with optical resonator structures enables full-color implementation at ultra-low power. It is expected to be applied in various fields requiring energy efficiency, including ultra-high-resolution near-eye displays for AR/VR, wearable devices, outdoor displays, and electronic paper. It also suggests the potential for sustainable and energy-efficient display technologies by minimizing power consumption during color retention.
Professor Young Min Song stated, “This technology allows a wide range of color changes using very little electricity,” adding, “When combined with future display driving methods, it could enable not only clearer and more energy-efficient ultra-high-resolution displays but also a variety of optical applications.”
This research was conducted with Hyo Eun Jeong, an integrated M.S./Ph.D. student at KAIST, as co-first author, and Professor Young Min Song as the corresponding author. The results were published online on February 28 in Light: Science & Applications, a leading international journal in optics.
※ Paper title: “Sub-1-volt, reconfigurable Gires-Tournois resonators for full-coloured monopixel array,” DOI: https://www.nature.com/articles/s41377-026-02228-2
This research was supported by multiple programs funded by the Ministry of Science and ICT, the National Research Foundation of Korea (NRF), the InnoCORE-GIST program, nanomaterials and technology development initiatives, future medical innovation programs, international collaboration hubs, and the Ministry of Trade, Industry and Energy (MOTIE).
2026.03.30 View 185