%61%69
-
Professor Kyung-Jin Lee of the Department of Physics Selected for the KAISTian of the Year’ Award
< Professor Kyung-Jin Lee at the ceremony >
KAIST announced on February 12th that it has selected Professor Kyung-Jin Lee from the Department of Physics as the recipient of the ‘KAISTian of the Year’ award in celebration of the university's 55th anniversary. Established in 2001, the ‘KAISTian of the Year’ award is the university’s highest honor, presented to members who have significantly enhanced KAIST's global prestige through exceptional academic and research milestones.
As the 25th recipient of this award, Professor Kyung-Jin Lee was recognized for his groundbreaking work in identifying the phenomenon of ‘Quantum Spin Pumping,’ effectively overturning 30-year-old conventional assumptions in spin transfer theory. While existing theories treated spin as a classical physical quantity, Professor Lee focused on the fact that spins within materials possess intrinsic quantum properties, much like electrons. To verify this, he researched Iron-Rhodium (FeRh), a magnetic material where spin magnitude changes abruptly under specific conditions. He became the first to observe a quantum transition in which the spin magnitude of Rhodium (Rh) atoms increased suddenly rather than gradually, theorizing that this very change serves as a new mechanism for inducing electron movement. Experimental data showed that this effect is more than 10 times greater than what previous theories had predicted. This achievement is hailed as a major breakthrough that redefines the core premises of spin transfer theory and provides a vital theoretical foundation for next-generation ultra-low-power magnetic memory and quantum information devices. The study gained worldwide acclaim following its publication in the journal ‘Nature’ last year.
The anniversary ceremony also honored 58 faculty members for their excellence in education, research, and international cooperation. Professor Wonho Choe of the Department of Nuclear and Quantum Engineering received the ‘Academic Achievement Grand Prize’ for his world-first identification of physical phenomena in low-temperature atmospheric pressure plasma and his contributions to medical and space technologies. The ‘Creative Teaching Grand Prize’ went to Professor Hyung-soo Kim of the Department of Mechanical Engineering for his innovative sports fluid mechanics curriculum. Professor Park Bum-soon of the Graduate School of Science and Technology Policy was awarded the ‘Outstanding Teaching Grand Prize’ for his interdisciplinary ‘Anthropocene Humanities’ courses that bridge science, art, and policy.
Furthermore, Professor Hyeon-Min Bae of the School of Electrical Engineering received the ‘Distinguished Service Grand Prize’ for his leadership in accelerating deep-tech prototyping and fostering a robust startup ecosystem. Professor Shin-Hyun Kim of the Department of Chemical and Biomolecular Engineering was honored with the ‘International Cooperation Grand Prize’ for establishing the T2KN consortium between Korea, Japan, China, and ASEAN, facilitating global academic exchange for over 120 students.
KAIST President Kwang-Hyung Lee stated, “The true spirit of KAIST lies in the dedication of our members who venture into uncharted territories and strive to transcend existing limits. I hope today serves as a moment for all our members to share in the joy and celebrate the remarkable achievements of our awardees.”
2026.02.12 View 72 -
KAIST Uses Sandpaper to Polish Semiconductors… Opening a New Path for AI Semiconductor Processing
<(From Left) Dr. Sukkyung Kang, Professor Sanha Kim from Department of Mechanical Engineering>
The performance and stability of smartphones and artificial intelligence (AI) services depend on how uniformly and precisely semiconductor surfaces are processed. KAIST researchers have expanded the concept of everyday “sandpaper” into the realm of nanotechnology, developing a new technique capable of processing semiconductor surfaces uniformly down to the atomic level. This technology demonstrates the potential to significantly improve surface quality and processing precision in advanced semiconductor processes such as high-bandwidth memory (HBM).
KAIST (President Kwang Hyung Lee) announced on the 11th of February that a research team led by Professor Sanha Kim of the Department of Mechanical Engineering has developed a “nano sandpaper” that utilizes carbon nanotubes—tens of thousands of times thinner than a human hair—as abrasive materials. This technology enables more precise surface processing than existing semiconductor manufacturing processes, while also reducing environmental burdens generated during fabrication, presenting a new planarization technique.
< Nano Sandpaper AI-Generated Image >
Although sandpaper is a familiar tool used to smooth surfaces by rubbing, it has been difficult to apply it to fields such as semiconductors, where extremely precise surface processing is required. This limitation arises because conventional sandpaper is manufactured by attaching abrasive particles with adhesives, making it difficult to uniformly secure extremely fine particles.
To overcome such limitations, the semiconductor industry has adopted a planarization process known as chemical mechanical polishing (CMP), which uses a chemical slurry in which abrasive particles are dispersed in liquid. However, this method requires additional cleaning steps and generates large amounts of waste, making the process complex and environmentally burdensome.
To address these issues, the research team extended the concept of sandpaper to the nanoscale. By vertically aligning carbon nanotubes, fixing them inside polyurethane, and partially exposing them on the surface, they implemented a “nano sandpaper.” This structure structurally suppresses abrasive detachment, eliminating concerns about surface damage and maintaining stable performance even after repeated use.
The nano sandpaper developed in this study achieves an abrasive density approximately 500,000 times higher than that of the finest commercially available sandpaper. The precision of sandpaper is expressed in terms of “abrasive density (grit number),” which indicates how densely abrasive particles are arranged on the surface. While everyday sandpaper typically ranges from 40 to 3000 grit, the nano sandpaper exceeds 1,000,000,000 grit. Through this extremely dense structure, surfaces could be processed with precision down to several nanometers—equivalent to the thickness of only a few atoms.
The effectiveness of the nano sandpaper was confirmed through experiments. Rough copper surfaces were polished to a smoothness at the nanometer level, and in semiconductor pattern planarization experiments, the technique reduced dishing defects by up to 67% compared with conventional CMP processes. Dishing defects refer to the phenomenon in which the center of interconnect lines becomes recessed, a major defect affecting the performance and reliability of advanced semiconductors such as HBM.
In particular, because the abrasive materials are fixed on the sandpaper surface, the technology does not require continuous supply of slurry solutions as in conventional processes. This reduces cleaning steps and eliminates waste slurry, presenting the possibility of transitioning semiconductor manufacturing toward more environmentally friendly processes.
< Nano Sandpaper Schematic Diagram >
< Detailed Image of Nano Sandpaper >
The research team expects that this technology can be applied to advanced semiconductor planarization processes such as HBM used in AI servers, as well as to hybrid bonding processes, which are gaining attention as next-generation semiconductor interconnection technologies. The study is also significant in that it expands the everyday concept of sandpaper into nano-precision processing technology, suggesting the possibility of securing core technologies required for semiconductor manufacturing.
Professor Sanha Kim stated, “This is an original study demonstrating that the everyday concept of sandpaper can be extended to the nanoscale and applied to ultra-fine semiconductor manufacturing,” adding, “We hope this technology will lead not only to improved semiconductor performance but also to environmentally friendly manufacturing processes.”
In this study, Dr. Sukkyung Kang of the Department of Mechanical Engineering participated as the first author. The research was recognized for its excellence by receiving the Gold Prize (1st place) in the Mechanical Engineering Division at the 31st Samsung Human Tech Paper Award, hosted by Samsung Electronics. The findings were published online on January 8, 2026, in the international journal Advanced Composites and Hybrid Materials (IF 21.8).
※ Paper title: “Carbon nanotube sandpaper for atomic-precision surface finishing”
DOI: https://doi.org/10.1007/s42114-025-01608-3
This research was supported by the National Research Foundation of Korea (Mid-Career Researcher Program; Ministry of Science and ICT, NRF, RS-2025-00560856), the Glocal Lab Program (Ministry of Education, NRF, RS-2025-25406725), the InnoCORE Program (Ministry of Science and ICT, NRF, N10250154), and the KAIST Up Program.
2026.02.11 View 192 -
AI that Understands Chemical Principles... Accelerating the Development of New Drugs and Materials
<(From top left) Professor Woo Youn Kim (KAIST), Dr. Jeheon Woo (KISTI), Dr. Seonghwan Kim (KAIST), and Jun Hyeong Kim (PhD candidate)>
Whether a smartphone battery lasts longer or a new drug can be developed to treat incurable diseases depends on how stably the atoms constituting the material are bonded. The core of 'molecular design' lies in finding how to arrange these countless atoms to form the most stable molecule. Until now, this process has been as difficult as finding the lowest valley in a massive mountain range, requiring immense time and costs. Researchers at KAIST have developed a new technology that uses artificial intelligence to solve this process quickly and accurately.
KAIST announced on February 10th that Professor Woo Youn Kim's research team in the Department of Chemistry has developed 'Riemannian DenoisingModel (R-DM),' an artificial intelligence model that understands the physical laws governing molecular stability to predict structures.
The most significant feature of this model is that it directly considers the 'energy' of the molecule. While existing AI models simply mimicked the shape of molecules, R-DM refines the structure by considering the forces acting within the molecule. The research team represented the molecular structure as a map where higher energy is depicted as hills and lower energy as valleys, designing the AI to move toward and find the valleys with the lowest energy.
R-DM completes the molecule by navigating this energy landscape, avoiding unstable structures to find the most stable state. This applies the mathematical theory of 'Riemannian geometry,' resulting in the AI learning the fundamental law of chemistry: 'matter prefers the state with the lowest energy.'
Experimental results showed that R-DM achieved up to 20 times higher accuracy than existing AI models, reducing prediction errors to a level nearly indistinguishable from precise quantum mechanical calculations. This represents the world's highest level of performance among AI-based molecular structure prediction technologies.
<Comparison of energy landscapes in Euclidean space and Riemannian space>
This technology can be utilized in various fields, including new drug development, next-generation battery materials, and high-performance catalyst design. It is expected to serve as an 'AI simulator' that will dramatically speed up research and development by significantly shortening the molecular design process, which previously took a long time. Furthermore, it has great potential in environmental and safety fields, as it can quickly predict chemical reaction paths in situations where experiments are difficult, such as chemical accidents or the spread of hazardous substances.
Professor Woo Youn Kim stated, "This is the first case where artificial intelligence has understood the basic principles of chemistry and judged molecular stability on its own. It is a technology that can fundamentally change the way new materials are developed."
<Image of Riemannian Diffusion Model application (AI-generated image)>
This study was led by Dr. Jeheon Woo from the KISTI Supercomputing Center and Dr. Seonghwan Kim from the KAIST Innovative Drug Discovery Research Group as co-first authors. The research results were published on January 2nd in the world-renowned academic journal Nature Computational Science.
※ Paper Title: Riemannian Denoising Model for Molecular Structure Optimization with Chemical Accuracy, DOI: 10.1038/s43588-025-00919-1
Meanwhile, this research was conducted with the support of the Chemical Accident Prediction-Prevention Advanced Technology Development Project of the Korea Environmental Industry & Technology Institute, the Science and Technology Institute InnoCore Project of the Ministry of Science and ICT, and the Data Science Convergence Talent Cultivation Project conducted by the National Research Foundation of Korea with support from the Ministry of Science and ICT.
2026.02.10 View 220 -
KAIST NYU Host AI Governance Summit in New York
< KAIST Professor Kyung Ryul Park delivering a keynote speech >
KAIST announced on February 9th that the KAIST-NYU AI and Digital Governance Summit, co-hosted with New York University (NYU), was held at NYU in New York from February 6 to 7 (local time). Amid the rapidly expanding impact of Artificial Intelligence (AI) across society, this summit was designed to combine private consensus meetings with public discussions to seek practical AI governance solutions that harmonize technological innovation with safety and ethical responsibility.
The summit was attended by 60 global AI governance leaders representing academia, industry, and civil society, including NYU professors Matthew Liao and David Chalmers, Victoria Nash (Director of the Oxford Internet Institute), Professor Vincent Conitzer (Carnegie Mellon University), Iason Gabriel (Principal Scientist at Google DeepMind), and Philip Goldberg (former U.S. Ambassador to South Korea). In particular, the public discussion on the second day drew high interest, with approximately 450 audience members in attendance.
< Brad Carson, U.S. Representative for Responsible Innovation and former U.S. Congressman, delivering a keynote speech >
This event garnered attention as an 'experimental consensus model' aimed at deriving an actionable AI governance framework beyond a simple forum. KAIST’s Global Center for Open Development with Evidence-based Strategies (G-CODEs) and the NYU Center for Bioethics had formed three working groups—Governance Requirements, Institutional Architecture, and Implementation Pathways—since last December to conduct preliminary discussions. At the New York site, practice-oriented recommendations were derived through intensive consensus-style discussions and voting.
In the Governance Requirements session, the need for enhanced oversight and monitoring of high-risk AI systems was discussed. In the ‘Institutional Architecture’ session, principles for designing AI oversight bodies were reviewed, referencing existing high-risk technology oversight models such as the FDA, IRB, and FAA. In the Implementation Pathways session, short-term governance tools and corporate responsibility standards that could be applied even during the current gap in international regulation were addressed as key issues.
Major global Big Tech experts from Meta, Google DeepMind, IBM, Amazon, Anthropic, TikTok and Hugging Face participated in the summit. From KAIST, researchers including Prof. So Young Kim , Prof. Kyung Ryul Park, and Prof. Hyungjun Kim shared Korea’s research achievements in AI governance.his event was conducted with support from the Korea Foundation’s (KF) international collaborative research program.
Professor Kyung Ryul Park of KAIST stated, “This summit was a meaningful attempt to expand AI governance beyond technical regulation into a matter of international cooperation and institutional design. Through the cooperation between KAIST and NYU, we will build a foundation for Korea to lead global AI governance discussions.”
KAIST President Kwang Hyung Lee remarked, “The importance of governance discussions for responsible AI innovation is growing. KAIST will continue to lead interdisciplinary research and policy discussions in the field of AI governance through international partnerships.”
< Sebastien Krier, AI Policy Lead at Google DeepMind, speaking >
2026.02.09 View 188 -
Capturing the Instant of Electrical Switching, Paving the Way for Next-Gen Memory Material Innovation
< (From left) Ph.D candidate Changhwan Kim, Ph.D candidate Seunghwan Kim , Ph.D candidate Namwook Hur, Professor Joonki Suh, Ph. D candidate Youngseok Cho>
As artificial intelligence advances, computers demand faster and more efficient memory. The key to ultra-high-speed, low-power semiconductors lies in the "switching" principle—the mechanism by which memory materials turn electricity on and off. A South Korean research team has successfully captured the elusive moment of switching and its internal operational principles by momentarily melting and freezing materials within a microscopic electronic device. This study provides a foundational blueprint for designing next-generation memory materials that are faster and consume less power based on fundamental principles.
On February 8th, the research team led by Professor Joonki Suh from our department (Chemical and Biomolecular Engineering), in collaboration with Professor Tae-Hoon Lee’s team from Kyungpook National University, announced the development of an experimental technique capable of real-time monitoring of electrical switching processes and phase changes within nano-devices—phenomena that were previously difficult to observe.
To verify the electrical switching, the team applied a method of instantaneous melting followed by rapid cooling (quenching). Through this, they succeeded in stably implementing amorphous tellurium (a-Te)—a state where tellurium is disordered like glass—within a nano-device much smaller than a human hair. Tellurium is typically sensitive to heat and changes properties easily when current is applied; however, in its amorphous state, it is garnering significant attention as a core material for next-generation memory due to its speed and energy efficiency. *Tellurium (Te): A metalloid element possessing properties of both metals and non-metals.
< Illustration of the experiment involving instantaneous melting and freezing in a memory electronic device (AI-generated image) >
Through this study, the team specifically identified the threshold voltage and thermal conditions at which switching begins, as well as the segments where energy loss occurs. Based on these findings, they observed stable and high-speed switching even while reducing heat generation. This enables "principle-based" memory material design, allowing researchers to understand exactly why and when electricity starts to flow.
The results confirmed that microscopic defects within amorphous tellurium play a crucial role in electrical conduction. When the voltage exceeds a certain threshold, the electricity does not flow all at once; instead, it follows a two-step switching process: first, a rapid increase in current along the defects, followed by heat accumulation that causes the material to melt.
Furthermore, the team successfully implemented a "self-oscillation" phenomenon—where voltage spontaneously increases and decreases—by conducting experiments that maintained the amorphous state without excessive current flow. This demonstrates that stable electrical switching is possible using only the single element of tellurium, without the need for complex material combinations.
< Electrical characteristics of amorphous tellurium created through rapid cooling from a liquid state within an electronic device >
This research is a significant achievement as it implements amorphous tellurium—a next-generation memory material—within an actual electronic device and systematically elucidates the fundamental principles of electrical switching. These findings are expected to serve as essential guidelines for designing semiconductor materials to realize faster and more energy-efficient memory in the future.
"This is the first study to implement amorphous tellurium in a real-world device environment and clarify the switching mechanism," said Professor Joonki Suh. "It sets a new standard for research into next-generation memory and switching materials."
The study, with Namwook Hur as the first author and Seunghwan Kim as the second author, and Professor Joonki Suh (KAIST) as the corresponding author, was published online on January 13th in the international academic journal Nature Communications.
Paper Title: On-device cryogenic quenching enables robust amorphous tellurium for threshold switching
DOI: 10.1038/s41467-025-68223-0
Meanwhile, this research was supported by the National Research Foundation of Korea (NRF) through the PIM (Processor-in-Memory) AI Semiconductor Core Technology Development Project, the Excellent Young Researcher Program funded by the Ministry of Science and ICT, and Samsung Electronics.
2026.02.09 View 169 -
KAIST Extends Its Deepest Condolences on the Passing of the Late Chairman Chang Sun Jung, Founder of Jungheung Group
KAIST extends its deepest condolences on the passing of the late Chairman Chang Sun Jung, founder of Jungheung Group.
Chairman Jung made significant contributions to the development of Korea’s construction industry and regional economy, and was a visionary leader who deeply recognized and actively supported the importance of nurturing science and technology talent. In particular, through his generous contribution to the KAIST Development Fund, he left a meaningful legacy in fostering future scientific talent and advancing research environments that will shape the nation’s future.
KAIST honors Chairman Jung’s noble spirit of giving and dedication, and will continue to strive to ensure that his vision lives on through the advancement of science and technology in Korea.
We extend our sincere condolences to the bereaved family and to the executives and employees of Jungheung Group, and pray for the eternal rest of the deceased.
2026.02.03 View 231 -
Reading the Optical Fingerprint of Materials in Real-Time with AI
< (From Left) KAIST Dr. Jongchan Kim, Professor Sanghoo Park >
Just as every person has a unique fingerprint, every material has its own unique ‘optical fingerprint.’ Spectroscopy, which has identified materials without contact in fields ranging from semiconductor processes to environmental monitoring, disease diagnosis, and space research, has been called the ‘eyes of science.’ A KAIST research team has implemented spectroscopic analysis, which previously relied on the experience of experts, into AI-based automatic and real-time interpretation technology, greatly expanding its applicability in various industrial fields such as semiconductors, environment, and medicine.
The research team led by Professor Sanghoo Park of our university's Department of Nuclear and Quantum Engineering announced on the 3rd that they have developed ‘AI-based deep spectral interpretation technology’ that allows artificial intelligence to automatically interpret various spectral data in real-time, overcoming limitations such as noise, contamination, defects, and complex overlapping signals.
A spectrum is a graph that spreads out light emitted or absorbed by a material like a rainbow. Existing spectroscopic analysis had to manually analyze signals appearing as numbers in this spectrum by comparing them one by one with well-known reference data. Instead of this method, the research team enabled the artificial intelligence to recognize the entire spectrum as a single ‘image’ and learn its patterns.
< Deep learning-based spectrum technology >
As a result, even in situations where noise was mixed in the data or some parts were lost, the AI accurately identified material information as if it were recognizing an object in a photo. Furthermore, it equipped a function to self-check whether the prediction results are scientifically valid, significantly increasing the reliability of the analysis.
The research team verified this technology by applying it to absorption spectroscopy data widely used in atmospheric and plasma chemistry. As a result, they succeeded in predicting the concentrations of eight chemical substances, including ozone and nitrogen oxides, with very high accuracy even among complexly mixed signals. It was not only more accurate than existing manual analysis but also showed stable performance even in environments with poor data quality.
This research is expected to be a turning point in converting vast amounts of spectroscopic data, which were previously discarded due to the difficulty of analysis, into ‘immediately usable information.’ In particular, it has high potential for use in various high-tech industrial fields, such as improving yield in semiconductor plasma processes, stable control of nuclear fusion plasma, environmental monitoring in smart cities, and non-contact disease diagnosis.
< Research Image >
Professor Sanghoo Park said, “This technology is an achievement that significantly lowers the entry barrier for spectroscopic data analysis, which used to rely on the experience of experts,” and added, “It can be immediately applied to overall industries requiring spectral analysis, such as environmental monitoring, healthcare, and plasma diagnosis.”
In this study, doctoral students Jongchan Kim and Seong-Cheol Huh participated as co-first authors, and Jin Hee Bae and Su-Jin Shin also contributed to the research. The results were published online on January 12th in the prestigious international academic journal in the field of measurement and analytical chemistry, ‘Sensors and Actuators B: Chemical.’
※ Paper title: Deep spectral deconvolution for image-based broadband spectral data analysis DOI: https://doi.org/10.1016/j.snb.2025.139369
Meanwhile, this research was conducted with support from the Ministry of Science and ICT’s Global TOP Strategic Research Group Support Program, the KAIST Leap Research Project, and the Korea Institute of Materials Science (KIMS).
2026.02.03 View 173 -
KAIST Team Wins Grand Prize at Kakao AI Incubation Project
<(From Left) Professor Jongse Park, Professor youngjin Kwon, Professor Jaehyuk Huh, Professor Knunle Olukotun>
Currently, Large Language Model (LLM) services like ChatGPT rely heavily on expensive GPU servers. This structure faces significant limitations, as costs and power consumption skyrocket as service scales increase. Researchers at KAIST have developed a next-generation AI infrastructure technology to address these challenges.
KAIST announced on January 30th that the ‘AnyBridge AI’ team, led by Professor Jongse Park from the School of Computing, has developed a next-generation AI infrastructure software. This software allows for efficient LLM services by integrating various AI accelerators instead of relying solely on GPUs. The technology won the Grand Prize at the "4 ISTs (Science & Tech Institutes) × Kakao AI Incubation Project" hosted by Kakao.
This project is a joint industry-academic collaboration between Kakao and the four major science and technology institutes (KAIST, GIST, DGIST, and UNIST). It selected outstanding teams by evaluating the technical prowess and business viability of preliminary startup teams based on AI technology. The Grand Prize winning team receives a total of 20 million KRW in prize money and up to 35 million KRW in Kakao Cloud credits.
AnyBridge AI is a technical startup team led by Professor Jongse Park (CEO), with Professors Youngjin Kwon and Jaehyuk Huh from KAIST's School of Computing participating. Based on research achievements in AI systems and computer architecture, the team aims to develop technology applicable to actual industrial sites. Furthermore, Professor Kunle Olukotun of Stanford University—co-founder of the Silicon Valley AI semiconductor startup SambaNova—is participating as an advisor to push for global technology and business expansion.
The AnyBridge team noted that most current LLM services are dependent on expensive GPU infrastructure, leading to structural limits where operating costs and power usage surge as services scale. The researchers analyzed that the root cause of this issue lies not in the performance of specific hardware, but in the absence of a system software layer capable of efficiently connecting and operating various AI accelerators, such as NPUs (AI-specialized chips) and PIMs (next-gen chips that process AI within memory), alongside GPUs.
<Technical diagram of AnyBridge: Enhancing LLM performance by flexibly utilizing various AI accelerators>
In response, the AnyBridge team proposed an integrated software stack that can service LLMs across the same interface and runtime environment, regardless of the accelerator type. Specifically, they received high praise for pointing out the limitations of existing GPU-centric LLM serving structures and presenting a "Multi-Accelerator LLM Serving Runtime Software" as their core technology.
This technology enables the implementation of a flexible AI infrastructure where the most suitable AI accelerator can be selected and combined based on the task's characteristics, without being tied to a specific vendor or hardware. This is evaluated as a major advantage that can reduce costs and power consumption while significantly increasing scalability for LLM services.
<Illustration of the Multi-Accelerator LLM Service Platform - AI-generated image>
Additionally, based on years of accumulated research in LLM serving system simulation, the AnyBridge team possesses a research foundation that can pre-verify various hardware/software design combinations without building a large-scale physical infrastructure. This point demonstrated both the technical maturity and the industrial feasibility of their work.
"This award is a result of recognizing the necessity of system software that integrates various AI accelerators, moving beyond the limits of GPU-centric AI infrastructure," said Professor Jongse Park. He added, "It is meaningful that we could expand our research results into industrial fields and entrepreneurship. We will continue to develop this into a core technology for next-generation LLM serving infrastructure through cooperation with industrial partners."
This award is seen as a prime example of KAIST's research moving beyond academic papers toward next-generation AI infrastructure technology and startups. AnyBridge AI plans to advance and verify its technology through future collaborations with Kakao and related industrial partners.
<Photo of the Grand Prize ceremony: Left - Kakao Investment CEO Do-young Kim; Right - KAIST Prof. Jongse Park>
2026.01.30 View 465 -
World-Renowned Masters Rodin and Chagall Meet at KAIST Museum
KAIST announced that its museum has received a donation of works by world-renowned masters Auguste Rodin and Marc Chagall from an anonymous donor, and has opened a permanent exhibition starting on the 29th. This donation is expected to not only cultivate the cultural and artistic sensibilities of the KAIST community but also contribute to the qualitative expansion of the museum's permanent collection.
The donation was made possible through the wishes of a donor who chose to remain anonymous. The donor expressed, "I hope that the members of KAIST will expand their sensibilities and imagination through art, beyond their scientific and technological research. I want the KAIST Museum to become a cultural landmark on campus and a space that provides inspiration to students."
The donated pieces consist of one bronze sculpture by Auguste Rodin, often called the "Saint of Sculpture," and one lithograph by Marc Chagall, a master of 20th-century modern art.
Rodin’s <Study for Adam Near a Column> is a preparatory piece created while conceiving "Adam," a figure featured in his immortal masterpiece, The Gates of Hell. Based on a plaster mold created around 1912 during Rodin's lifetime, this is the fourth (4/12) of twelve official casts produced posthumously by the Musée Rodin in France. It captures the essence of Rodin’s sculptural art, delicately expressing inner human agony through muscular detail and a twisted posture.
<Rodin’s Study for Adam Near a Column (45-degree side view, post-installation)]
Chagall’s <Circus with a Yellow Clown> is a lithograph produced in 1967 at the Mourlot lithography studio in France. Throughout his life, Chagall used the theme of the "circus" to express the joys and sorrows of humanity and a surreal world of dreams. This work combines the dynamism of circus performers with a fantastical atmosphere through vibrant colors and a free-form composition, capturing a unique worldview akin to a piece of poetry. It is the 104th piece of a total of 150 (104/150) and is regarded as a masterpiece that maximizes Chagall's signature lyrical imagination.
<Chagall’s Circus with a Yellow Clown (unframed)>
KAIST President Kwang-Hyung Lee stated, "It is very meaningful to acquire masterpieces of such high value in global art history. Through these works, which contain diverse perspectives on humanity and the world, I look forward to the KAIST Museum establishing itself as a cultural space where intelligence and emotion coexist."
The donated works by Rodin and Chagall will be on permanent display at the KAIST Museum starting today. While currently open to students and the general public, the museum plans to expand its public accessibility through special exhibitions and educational programs starting in April.
2026.01.30 View 268 -
AI Enters the Experienced Hire Era... Teaching Learned Knowledge with Ease
< (From left) KAIST Professor Hyunwoo J. Kim, Postdoctoral Researcher Sanghyeok Lee, M.S candidate Taehoon Song, Korea University Ph.D candidate Jihwan Park >
How inconvenient would it be if you had to manually transfer every contact and photo from scratch every time you switched to a new smartphone? Current Artificial Intelligence (AI) models face a similar predicament. Whenever a superior new AI model—such as a new version of ChatGPT—emerges, it has to be retrained with massive amounts of data and at a high cost to acquire specialized knowledge in specific fields. A Korean research team has developed a "knowledge transplantation" technology between AI models that can resolve this inefficiency.
KAIST announced on January 27th that a research team led by Professor Hyunwoo J. Kim from the School of Computing, in collaboration with a research team from Korea University, has developed a new technology capable of effectively "transplanting" learned knowledge between different AI models.
Recently, Vision-Language Models (VLM), which understand both images and text simultaneously, have been evolving rapidly. These are easily understood as multimodal AIs, like ChatGPT, which can provide explanations when a user shows them a photo and asks a question. These models have the advantage of adapting relatively quickly to new fields using small amounts of data by pre-learning large-scale image and language data.
However, the need to repeat this "adaptation process" from scratch every time a new AI model is released has been pointed out as a major inefficiency. Existing adaptation techniques also faced limitations: they were difficult to use if the model structure changed even slightly, or they significantly increased memory and computational costs because multiple models had to be used simultaneously.
To solve these problems, the research team proposed "TransMiter," a transferable adaptation technique that allows learned knowledge to be reused regardless of the model's structure or size. The core of this technology is directly transferring the "adaptation experience" accumulated by one AI as it learns to another AI model.
< TransMiter: A transferable adaptation technique reusable regardless of model structure, size, etc. >
The researchers' technology does not overhaul the complex internal structure of the AI; instead, it adopts a method of passing on "know-how" learned by observing only the prediction results (output) to another AI. Even if the AI models have different architectures, if the know-how learned by one AI is organized based on the answers given to the same questions, another AI can utilize that knowledge immediately. Consequently, there is no need to undergo the complex and time-consuming retraining process, and there is almost no slowdown in speed.
This study is highly significant as it is the first to prove that AI adaptation knowledge—previously considered almost impossible to reuse if model structures or sizes differed—can be precisely transplanted regardless of the model type. This is expected to not only reduce repetitive learning costs but also be utilized as a so-called "knowledge patch" technology that updates Large Language Models (LLMs) in real-time according to specific needs.
Professor Hyunwoo J. Kim explained, "By extending this research, we can significantly reduce the cost of post-training that had to be performed repeatedly whenever a rapidly evolving hyper-scale language model appears. It will enable 'model patches' that easily add expertise in specific fields."
The study involved Taehoon Song (Master's student, KAIST School of Computing), Sanghyeok Lee (Postdoctoral researcher), and Jihwan Park (Doctoral student, Korea University) as co-authors, with Professor Hyunwoo J. Kim serving as the corresponding author. The research results were accepted for oral presentation (4.6% acceptance rate as of 2025) at AAAI 2026 (Association for the Advancement of Artificial Intelligence), the most prestigious international conference in the field of AI, and were presented on January 25th.
Paper Title: Transferable Model-agnostic Vision-Language Model Adaptation for Efficient Weak-to-Strong Generalization
DOI: https://doi.org/10.48550/arXiv.2508.08604
Meanwhile, Professor Hyunwoo J. Kim's laboratory presented a total of three papers at the conference, including this paper and "TabFlash," a technology developed in collaboration with Google Cloud AI to enhance the understanding of tables within documents.
2026.01.27 View 631 -
KAIST’s Reliability-Aware AI Opens Path to Faster Cathode Design and Next-Generation Batteries
< (From front left) Professor Seungbum Hong, Professor EunAe Cho (From back left) Chaeyul Kang, Benediktus Madika, Jung Hyeon Moon, Taemin Park (Top) JooSung Shim >
The power that makes electric vehicles travel further and smartphones last longer comes from battery materials. Among them, the core material that directly determines the performance and lifespan of a battery is the cathode material. What if artificial intelligence could replace the numerous experiments required for battery material development? KAIST's research team has developed an artificial intelligence (AI) framework that presents both the particle size of cathode materials and prediction reliability even in situations where experimental data is insufficient, opening the possibility of expansion to next-generation energy technologies such as all-solid-state batteries.
KAIST announced on January 26th that a research team led by Professor Seungbum Hong of the Department of Materials Science and Engineering, in joint research with Professor EunAe Cho's team, has developed a machine learning framework that accurately predicts the particle size of battery cathode materials even when experimental data is incomplete and provides the degree of reliability of the results.
The cathode material inside the battery is the core material that allows lithium-ion batteries to store and use energy. Currently, the most widely used cathode material for electric vehicle batteries is an NCM-based metal oxide mixed with nickel (Ni), cobalt (Co), and manganese (Mn), which greatly affects the battery's lifespan, charging speed, driving range, and safety.
KAIST research team focused on the fact that the size of the very small primary particles that make up these cathode materials is a key factor in determining battery performance. This is because if the particles are too large, performance deteriorates, and conversely, if they are too small, stability problems may occur. Accordingly, the research team developed an AI-based technology that can accurately predict and control particle size.
< Battery performance prediction related (AI-generated image) >
In the past, to determine the particle size, numerous experiments had to be repeated while changing the sintering temperature, time, and material composition. However, in actual research fields, it was difficult to measure all conditions without omission, and experimental data were often missing, which limited the precise analysis of the relationship between process conditions and particle size.
To solve this problem, the research team designed an AI framework that supplements missing data and presents prediction results along with reliability. This framework is characterized by combining a technology (MatImpute) that supplements missing experimental data by considering chemical characteristics and a probabilistic machine learning model (NGBoost) that calculates prediction uncertainty.
This AI model does not stop at simply predicting particle size but also provides information on the extent to which the prediction can be trusted. This serves as an important criterion for deciding under what conditions to actually synthesize materials.
As a result of learning by expanding experimental data, the AI model showed a high prediction accuracy of about 86.6%. According to the analysis, it was found that the cathode material particle size is more significantly affected by process conditions such as baking temperature and time than by material components, which aligns well with existing experimental understanding.
To verify the reliability of the AI prediction, the research team conducted an experiment by newly producing four types of cathode material samples synthesized under manufacturing conditions not included in the existing data while maintaining the same metal component ratio of NCM811 (Ni 80% / Co 10% / Mn 10%) composition. As a result, the particle size predicted by the AI almost matched the actual microscopic measurement results, and most of the errors were 0.13 micrometers (μm) or less, which is much smaller than the thickness of a human hair. In particular, the actual experimental results were included within the prediction uncertainty range presented by the AI, confirming that not only the predicted value but also its reliability was valid.
< Distribution shift condition experiment verification using 4 types of samples >
This study is significant in that it has opened a way to find conditions with a high probability of success first without performing all experiments in battery research. Through this, it is expected to speed up the development of battery materials and significantly reduce unnecessary experiments and costs.
Professor Seungbum Hong said, "The key is that the AI presents not only the predicted value but also how much the result can be trusted," and added, "It will be of practical help in designing next-generation battery materials more quickly and efficiently."
In this study, Benediktus Madika, a doctoral student in the Department of Materials Science and Engineering, participated as the first author, and it was published on October 8, 2025, in 'Advanced Science', an internationally prestigious academic journal in the field of materials science and chemical engineering.
※ Paper Title: Uncertainty-Quantified Primary Particle Size Prediction in Li-Rich NCM Materials via Machine Learning and Chemistry-Aware Imputation, DOI: https://doi.org/10.1002/advs.202515694
Meanwhile, this research was conducted by researchers Benediktus Madika, Chaeyul Kang, JooSung Shim, Taemin Park, Jung Hyeon Moon, and the research team of Professor EunAe Cho and Professor Seungbum Hong, and was conducted with support from the Ministry of Science and ICT (MSIT) National Research Foundation of Korea (NRF) Future Convergence Technology Pioneer (Strategic) (Project No. RS-2023-00247245).
< Battery performance prediction (AI-generated image) >
2026.01.26 View 619 -
KAIST Proposes a Multinational AI Cooperation Strategy Beyond U.S.–China Dominance
2026.01.19 View 725