%6d%61%74%65%72%69%61%6c
-
Designing the Heart of Hydrogen Cars with AI... Development of Next-Generation Super Catalyst
<(From left) KAIST Ph.D. Candidate HyunWoo Chang, Professor EunAe Cho. (Top, from left) Seoul National University Professor Won Bo Lee, Dr. Jae Hyun Ryu.>
In the era of climate crisis, hydrogen vehicles are emerging as an alternative for eco-friendly mobility. However, the fuel cell, known as the ‘heart of the hydrogen car,’ still faces limitations of high cost and short lifespan. The core cause is the platinum catalyst. While it is a decisive material for generating electricity, the reaction is slow, performance degrades over time, and manufacturing costs are high. Korean researchers have presented a clue to solving this difficult problem.
KAIST announced on February 26th that the research team led by Professor EunAe Cho of the Department of Materials Science and Engineering, together with the team of Professor Won Bo Lee of the School of Chemical and Biological Engineering at Seoul National University, has developed a technology that predicts the ‘atomic arrangement’ tendency of catalysts using artificial intelligence (AI).
This technology is akin to calculating beforehand which combination is advantageous for completing a puzzle before putting it together. By having AI calculate the arrangement speed of metal atoms first, it has become possible to efficiently design catalysts with better performance. The core of this research is that ‘AI revealed the fact that zinc plays a decisive role in the platinum-cobalt atomic arrangement.’
<Schematic diagram of AI-based atomic alignment prediction>
Despite the high performance of existing platinum-cobalt (Pt-Co) alloy catalysts, very high-temperature heat treatment was required to create the ‘intermetallic (L1₀)’ structure, where atoms are regularly arranged. In this process, particles would clump together, or the structure would become unstable, posing limitations for actual fuel cell application.
To solve this problem, the research team introduced machine learning-based quantum chemistry simulations. Through AI, they precisely predicted how atoms move and arrange themselves inside the catalyst.
As a result, they discovered that zinc (Zn) acts as a mediating element that promotes atomic arrangement. The principle is that when zinc is introduced, atoms find their places more easily, forming a more sophisticated and stable structure. In other words, AI has found the ‘optimal path for atomic arrangement creation’ in advance.
< Synthesis process of Zinc-introduced Platinum-Cobalt catalyst>
The zinc-platinum-cobalt catalyst, synthesized based on AI predictions, secured both higher activity and superior long-term durability compared to commercial platinum catalysts. This is a case proving that the ‘virtual blueprint’ calculated by artificial intelligence can be implemented as a high-performance catalyst in an actual laboratory.
In particular, this technology is expected to contribute to extending catalyst lifespan and reducing manufacturing costs across core carbon-neutral industries, such as hydrogen passenger cars, hydrogen trucks requiring long-distance operation, hydrogen ships, and energy storage systems (ESS).
< Conceptual diagram of AI-based catalyst development (AI-generated image) >
Professor EunAe Cho stated, “This research is a case of utilizing machine learning to predict the atomic arrangement tendency of catalysts in advance and implementing this through actual synthesis,” and added, “AI-based material design will become a new paradigm for the development of next-generation fuel cell catalysts.”
Ph.D. Candidate HyunWoo Chang from KAIST’s Department of Materials Science and Engineering and Dr. Jae Hyun Ryu from Seoul National University’s School of Chemical and Biological Engineering participated as co-first authors in this research. The research results were published on January 15, 2026, in ‘Advanced Energy Materials,’ a world-renowned academic journal in the energy materials field. ※ Paper Title: Machine Learning-Guided Design of L1₀-PtCo Intermetallic Catalysts: Zn-Mediated Atomic Ordering, DOI: https://doi.org/10.1002/aenm.202505211
This research was conducted with the support of the National Research Foundation of Korea’s Nano & Material Technology Development Program and the Korea Institute of Energy Technology Evaluation and Planning’s Energy Innovation Research Center for Fuel Cell Technology.
2026.02.27 View 503 -
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 1077 -
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 494 -
KAIST Directly Visualizes the Hidden Spatial Order of Electrons in a Quantum Material
<(Back row, from left) Yeongkwan Kim, SungBin Lee, Heejun Yang, Yongsoo Yang_(Front row, from left) Jemin Park, Seokjo Hong, Jaewhan Oh>
· Cryogenic 4D-STEM reveals how charge density waves form, fragment, and persist across a phase transition
· First direct measurement of electronic amplitude correlations uncovers strain-driven inhomogeneity and localized order above the transition temperature
Electronic order in quantum materials often emerges not uniformly, but through subtle and complex patterns that vary from place to place. One prominent example is the charge density wave (CDW), an ordered state in which electrons arrange themselves into periodic patterns at low temperatures. Although CDWs have been studied for decades, how their strength and spatial coherence evolve across a phase transition has remained largely inaccessible experimentally.
Now, a team led by Professor Yongsoo Yang of the Department of Physics at KAIST (Korea Advanced Institute of Science and Technology), together with Professors SungBin Lee, Heejun Yang, and Yeongkwan Kim, and in collaboration with Stanford University, has for the first time directly visualized the spatial evolution of charge density wave amplitude order inside a quantum material.
A New Way to See Electronic Order at the Nanoscale
Using a liquid-helium-cooled electron microscope setup combined with four-dimensional scanning transmission electron microscopy (4D-STEM), the researchers mapped how CDW order develops, weakens, and fragments as temperature changes. This approach allowed them to reconstruct nanoscale maps of the CDW amplitude, revealing not just whether the order exists, but how strong it is and how it is spatially connected.
This study is similar to filming the growth of ice crystals as water freezes using an ultra-high-magnification camera. In this case, however, the researchers observed electrons arranging themselves at cryogenic temperatures of around –253°C, and used an electron microscope capable of resolving features one hundred-thousandth the width of a human hair instead of a conventional camera. The results showed that the electronic patterns do not appear uniformly across the material. In some regions, clear patterns are visible, while in neighboring areas they are entirely absent, much like a lake that does not freeze all at once, with patches of ice interspersed with liquid water.
How Electronic Order Breaks Apart in Real Space
The team further demonstrated that this spatial inhomogeneity is closely linked to local strain inside the crystal. Even extremely small distortions that are far below optical resolution strongly suppress the CDW amplitude. This clear anticorrelation between strain and electronic order provides direct evidence that local lattice distortions play a decisive role in shaping CDW patterns.
Unexpectedly, the researchers also observed that localized regions of CDW order can persist even above the transition temperature, where long-range order is generally thought to disappear. These isolated pockets of electronic order suggest that the CDW transition is not a simple, uniform melting process, but instead involves gradual loss of spatial coherence.
A key advance of this work is the world’s first direct measurement of CDW amplitude correlations. By quantifying how the strength of electronic order at one location is related to that at another, the study reveals how CDW coherence collapses across the transition, while local amplitude remains finite. Such information could not be obtained with conventional diffraction or scanning probe techniques.
Toward a New Framework for Studying Electronic Order
Charge density waves are a central feature of many quantum materials and often coexist or compete with other electronic states. By directly accessing their spatial structure and correlations, this study provides a new experimental framework for understanding how collective electronic order forms and evolves in real materials.
Dr. Yongsoo Yang, who led the research, explained the significance of the results: “Until now, the spatial coherence of charge density waves was largely inferred indirectly. Our approach allows us to directly visualize how electronic order varies across space and temperature, and to identify the factors that locally stabilize or suppress it.”
[Figure 1] Schematic illustration of an experiment employing 4D-STEM to probe the spatial variations of charge density waves in the prototypical quantum material NbSe2 under a liquid-helium cryogenic environment (AI-generated image).
This research, with Seokjo Hong, Jaewhan Oh and Jemin Park of KAIST as co-first authors, was published online in Physical Review Letters on January 6th (Title: Spatial correlations of charge density wave order across the transition in 2H-NbSe2).
The study was mainly supported by the National Research Foundation of Korea (NRF) Grants (Individual Basic Research Program, Basic Research Laboratory Program, Nanomaterial Technology Development Program) funded by the Korean Government (MSIT).
2026.01.20 View 859 -
KAIST detects ‘hidden defects’ that degrade semiconductor performance with 1,000× higher sensitivity
<(From Left) Professor Byungha Shin, Ph.D candidate Chaeyoun Kim, Dr. Oki Gunawan>
Semiconductors are used in devices such as memory chips and solar cells, and within them may exist invisible defects that interfere with electrical flow. A joint research team has developed a new analysis method that can detect these “hidden defects” (electronic traps) with approximately 1,000 times higher sensitivity than existing techniques. The technology is expected to improve semiconductor performance and lifetime, while significantly reducing development time and costs by enabling precise identification of defect sources.
KAIST (President Kwang Hyung Lee) announced on January 8th that a joint research team led by Professor Byungha Shin of the Department of Materials Science and Engineering at KAIST and Dr. Oki Gunawan of the IBM T. J. Watson Research Center has developed a new measurement technique that can simultaneously analyze defects that hinder electrical transport (electronic traps) and charge carrier transport properties inside semiconductors.
Within semiconductors, electronic traps can exist that capture electrons and hinder their movement. When electrons are trapped, electrical current cannot flow smoothly, leading to leakage currents and degraded device performance. Therefore, accurately evaluating semiconductor performance requires determining how many electronic traps are present and how strongly they capture electrons.
The research team focused on Hall measurements, a technique that has long been used in semiconductor analysis. Hall measurements analyze electron motion using electric and magnetic fields. By adding controlled light illumination and temperature variation to this method, the team succeeded in extracting information that was difficult to obtain using conventional approaches.
Under weak illumination, newly generated electrons are first captured by electronic traps. As the light intensity is gradually increased, the traps become filled, and subsequently generated electrons begin to move freely. By analyzing this transition process, the researchers were able to precisely calculate the density and characteristics of electronic traps.
The greatest advantage of this method is that multiple types of information can be obtained simultaneously from a single measurement. It allows not only the evaluation of how fast electrons move, how long they survive, and how far they travel, but also the properties of traps that interfere with electron transport.
The team first validated the accuracy of the technique using silicon semiconductors and then applied it to perovskites, which are attracting attention as next-generation solar cell materials. As a result, they successfully detected extremely small quantities of electronic traps that were difficult to identify using existing methods—demonstrating a sensitivity approximately 1,000 times higher than that of conventional techniques.
< Conceptual Diagram of the Evolution of Hall Characterization (Analysis) Techniques >
Professor Byungha Shin stated, “This study presents a new method that enables simultaneous analysis of electrical transport and the factors that hinder it within semiconductors using a single measurement,” adding that “it will serve as an important tool for improving the performance and reliability of various semiconductor devices, including memory semiconductors and solar cells.”
The results of this research were published on January 1 in Science Advances, an international academic journal, with Chaeyoun Kim, a doctoral student in the Department of Materials Science and Engineering, as the first author.
※ Paper title: “Electronic trap detection with carrier-resolved photo-Hall effect,” DOI: https://doi.org/10.1126/sciadv.adz0460
This research was supported by the Ministry of Science and ICT and the National Research Foundation of Korea.
< Conceptual Diagram of Charge Transport and Trap Characterization Using Photo-Hall Measurements (AI-generated image) >
2026.01.08 View 1226 -
Breaking Performance Barriers of All Solid State Batteries
< (Bottom, from left) Professor Dong-Hwa Seo, Researcher Jae-Seung Kim, (Top, from left) Professor Kyung-Wan Nam, Professor Sung-Kyun Jung, Professor Youn-Seok Jung >
Batteries are an essential technology in modern society, powering smartphones and electric vehicles, yet they face limitations such as fire explosion risks and high costs. While all-solid-state batteries have garnered attention as a viable alternative, it has been difficult to simultaneously satisfy safety, performance, and cost. Recently, a Korean research team successfully improved the performance of all-solid-state batteries simply through structural design—without adding expensive metals.
KAIST announced on January 7th that a research team led by Professor Dong-Hwa Seo from the Department of Materials Science and Engineering, in collaboration with teams led by Professor Sung-Kyun Jung (Seoul National University), Professor Youn-Suk Jung (Yonsei University), and Professor Kyung-Wan Nam (Dongguk University), has developed a design method for core materials for all-solid-state batteries that uses low-cost raw materials while ensuring high performance and low risk of fire or explosion.
Conventional batteries rely on lithium ions moving through a liquid electrolyte. In contrast, all-solid-state batteries use a solid electrolyte. While this makes them safer, achieving rapid lithium-ion movement within a solid has typically required expensive metals or complex manufacturing processes.
To create efficient pathways for lithium-ion transport within the solid electrolyte, the research team focused on "divalent anions" such as oxygen and sulfur . Divalent anions play a crucial role in altering the crystal structure by integrating into the basic framework of the electrolyte.
The team developed a technology to precisely control the internal structure of low-cost zirconium (Zr)-based halide solid electrolytes by introducing these divalent anions. This design principle, termed the "Framework Regulation Mechanism," widens the pathways for lithium ions and lowers the energy barriers they encounter during transport. By adjusting the bonding environment and crystal structure around the lithium ions, the team enabled faster and easier movement.
To verify these structural changes, the researchers utilized various high-precision analysis techniques, including:
High-energy Synchrontron X-ray diffraction(Synchrotron XRD)
Pair Distribution Function (PDF) analysis
X-ray Absorption Spectroscopy (XAS)
Density Functional Theory (DFT) modeling for electronic structure and diffusion.
The results showed that electrolytes incorporating oxygen or sulfur improved lithium-ion mobility by 2 to 4 times compared to conventional zirconium-based electrolytes. This signifies that performance levels suitable for practical all-solid-state battery applications can be achieved using inexpensive materials.
Specifically, the ionic conductivity at room temperature was measured at approximately 1.78 mS/cm for the oxygen-doped electrolyte and 1.01 mS/cm for the sulfur-doped electrolyte. Ionic conductivity indicates how quickly and smoothly lithium ions move; a value above 1 mS/cm is generally considered sufficient for practical battery applications at room temperature.
< Structural Regulation Mechanism of Zr-based Halide Electrolytes via Divalent Anion Introduction >
< Atomic Rearrangement of Solid Electrolyte for All-Solid-State Batteries (AI-generated image) >
Professor Dong-Hwa Seo stated, "Through this research, we have presented a design principle that can simultaneously improve the cost and performance of all-solid-state batteries using cheap raw materials. Its potential for industrial application is very high." Lead author Jae-Seung Kim added that the study shifts the focus from "what materials to use" to "how to design them" in the development of battery materials.
This study, with Jae-Seung Kim (KAIST) and Da-Seul Han (Dongguk University) as co-first authors, was published in the international journal Nature Communications on November 27, 2025.
Paper Title: Divalent anion-driven framework regulation in Zr-based halide solid electrolytes for all-solid-state batteries
DOI: https://www.nature.com/articles/s41467-025-65702-2
This research was supported by the Samsung Electronics Future Technology Promotion Center, the National Research Foundation of Korea, and the National Supercomputing Center.
2026.01.07 View 2979 -
The World's Smallest Fully Wireless Neural Implant Achieved
< (From left) Sunwoo Lee, KAIST Joint Professor, Alyosha Molnar, Cornell University Professor >
The human brain contains about 100 billion brain cells, and the chemical and electrical signals they exchange create most mental functions. Neural implant technology for precisely reading these signals is essential for the research and treatment of neurodegenerative diseases. A research team from KAIST and international collaborators has successfully implemented a fully wireless, ultra-small implant, which was previously only a theoretical possibility, going beyond simple miniaturization and weight reduction of neural implants.
KAIST announced on the November 27th that a joint research team led by Professor Sunwoo Lee (Joint Professor in Materials Science and Engineering at KAIST and from the School of Electrical and Electronic Engineering at Nanyang Technological University, NTU) and Professor Alyosha Molnar's team from Cornell University in the US has developed 'MOTE (Micro-Scale Opto-Electronic Tetherless Electrode)', an ultra-small wireless neural implant less than 100 micrometers (µm) — smaller than a grain of salt. The team successfully implanted this device into the brains of laboratory mice and stably measured brain waves for one year.
In the brain, invisible, minute electrical signals constantly move, creating our various mental activities such as memory, judgment, and emotion. The technology to directly measure these signals outside the body without connecting wires has been highlighted as key for brain research and the treatment of neurological disorders like dementia and Parkinson's disease.
However, existing implants have limitations: their thick wired structure causes movement in the brain, leading to inflammation and signal degradation over time, and their size and heat generation restrict long-term use.
To overcome these limitations, the research team created an ultra-small circuit based on the existing semiconductor process (CMOS) and combined it with their self-developed ultra-fine Micro-LEDs (µLEDs) to drastically miniaturize the device. They also applied a special surface coating to significantly enhance durability, allowing it to withstand the biological environment for a long time.
The resulting MOTE is less than 100 µm thick and has a volume of less than 1 nanoliter, making it thinner than a human hair and smaller than a grain of salt, the world's smallest level among currently reported wireless neural implants.
Another key feature of MOTE is that it is a fully wireless system that requires no battery. The device is structured to receive external light to generate power, detect brain waves, and then transmit the information back outside embedded in the light signal using Pulse Position Modulation (PPM).
This method drastically reduces energy consumption, minimizes the risk of heat generation, and eliminates the need for battery replacement, enabling long-term use.
The research team conducted a one-year long-term experiment by implanting the ultra-small MOTE into the brains of mice. The results showed normal brain wave measurement over the extended period, with almost no inflammation observed around the implant and no degradation in device performance.
This is considered the first clear demonstration that an ultra-small wireless implant can maintain normal function for a prolonged time inside a living body.
< MOTE neural implant on a salt crystal (left), MOTE neural implants after 296 days of implantation in a laboratory mouse (right) >
Professor Sunwoo Lee stated, "The greatest significance of the newly developed neural implant lies in its actual implementation of a fully wireless, ultra-small implant that was previously only anticipated as a possibility, going beyond simple miniaturization and weight reduction." He added, "This proves the technological possibility of resolving not only the known unknowns raised during the development and use of wireless neural implants, but also the unknown unknowns that newly emerge during the actual development process."
He further added, "This technology will be broadly applicable not only to brain science research but also to nervous system disease monitoring and the development of long-term recording-based treatment technologies."
The research results were published online in the prestigious journal Nature Electronics on November 3rd. ※ Paper Title: A subnanolitre tetherless optoelectronic microsystem for chronic neural recording in awake mice, DOI: https://doi.org/10.1038/s41928-025-01484-1
This research was supported by the US National Institutes of Health (NIH), Nanyang Technological University (Singapore), the Singapore National Research Foundation, the Singapore Ministry of Education, and the ASPIRE League Partnership Seed Fund 2024. The specialized fabrication processes were conducted at the Cornell NanoScale Facility (part of the US National Nanotechnology Coordinated Infrastructure, NNCI) and NTU's Nanyang NanoFabrication Centre.
2025.11.27 View 1736 -
“AI,” the New Language of Materials Science and Engineering Spoken at KAIST
<(From Left) M.S candidate Chaeyul Kang, Professor Seumgbum Hong, Ph. D candidate Benediktus Madika, Ph.D candidate Batzorig Buyantogtokh, Ph.D candiate Aditi Saha, >
Collaborating authors include Professor Joshua Agar (Drexel University), Professors Chris Wolverton and Peter Voorhees (Northwestern University), Professor Peter Littlewood (University of St Andrews), and Professor Sergei Kalinin (University of Tennessee).
Paper Title: Artificial Intelligence for Materials Discovery, Development, and Optimization
The era has arrived in which artificial intelligence (AI) autonomously imagines and predicts the structures and properties of new materials. Today, AI functions as a researcher’s “second brain,” actively participating in every stage of research, from idea generation to experimental validation.
KAIST (President Kwang Hyung Lee) announced on October 26 that a comprehensive review paper analyzing the impact of AI, Machine Learning (ML), and Deep Learning (DL) technologies across materials science and engineering has been published in ACS Nano (Impact Factor = 18.7). The paper was co-authored by Professor Seungbum Hong and his team from the Department of Materials Science and Engineering at KAIST, in collaboration with researchers from Drexel University, Northwestern University, the University of St Andrews, and the University of Tennessee in the United States.
The research team proposed a full-cycle utilization strategy for materials innovation through an AI-based catalyst search platform, which embodies the concept of a Self-Driving Lab—a system in which robots autonomously perform materials synthesis and optimization experiments.
Professor Hong’s team categorized materials research into three major stages—Discovery, Development, and Optimization—and detailed the distinctive role of AI in each phase:
In the Discovery Stage, AI designs new structures, predicts properties, and rapidly identifies the most promising materials among vast candidate pools.
In the Development Stage, AI analyzes experimental data and autonomously adjusts experimental processes through Self-Driving Lab systems, significantly shortening research timelines.
In the Optimization Stage, AI employs Reinforcement Learning, which identifies optimal conditions through Bayesian Optimization, which efficiently finds superior results with minimal experimentation, to fine-tune designs and process conditions for maximum performance.
In essence, AI serves as a “smart assistant” that narrows down the most promising materials, reduces experimental trial and error, and autonomously optimizes experimental conditions to achieve the best-performing outcomes.
The paper further highlights how cutting-edge technologies such as Generative AI, Graph Neural Networks (GNNs), and Transformer models are transforming AI from a computational tool into a “thinking researcher.” Nonetheless, the team cautions that AI’s predictions are not error-proof and that key challenges persist, such as imbalanced data quality, limited interpretability of AI predictions, and integration of heterogeneous datasets.
To address these limitations, the authors emphasize the importance of developing AI systems capable of autonomously understanding physical principles and ensuring transparent, verifiable decision-making processes for researchers.
The review also explores the concept of the Self-Driving Lab, where AI autonomously designs experimental plans, analyzes results, and determines the next experimental steps—without manual operation by researchers. The AI-Based Catalyst Search Platform exemplifies this concept, enabling robots to automatically design, execute, and optimize catalyst synthesis experiments.
In particular, the study presents cases in which AI-driven experimentation has dramatically accelerated catalyst development, suggesting that similar approaches could revolutionize research in battery and energy materials.
<AI Driving Innovation Across the Entire Cycle of New Material Discovery, Development, and Optimization>
“This review demonstrates that artificial intelligence is emerging as the new language of materials science and engineering, transcending its role as a mere tool,” said Professor Seungbum Hong. “The roadmap presented by the KAIST team will serve as a valuable guide for researchers in Korea’s national core industries including batteries, semiconductors, and energy materials.”
Benediktus Madika (Ph.D. candidate), Aditi Saha (Ph.D. candidate), Chaeyul Kang (M.S. candidate), and Batzorig Buyantogtokh (Ph.D. candidate) from KAIST’s Department of Materials Science and Engineering contributed as co-first authors.
Collaborating authors include Professor Joshua Agar (Drexel University), Professors Chris Wolverton and Peter Voorhees (Northwestern University), Professor Peter Littlewood (University of St Andrews), and Professor Sergei Kalinin (University of Tennessee).
Paper Title: Artificial Intelligence for Materials Discovery, Development, and Optimization
DOI: 10.1021/acsnano.5c04200
This work was supported by the National Research Foundation of Korea (NRF) with funding from the Ministry of Science and ICT (RS-2023-00247245).
2025.10.27 View 2180 -
Physics Informed AI Excels at Large Scale Discovery of New Materials!
<(From left) Ph.D candidates Songho Lee, Donggeun Park, and Hyeonbin Moon, and Professor Seunghwa Ryu from the Department of Mechanical Engineering; (top) Professor Jae Hyuk Lim from Kyung Hee University and Dr. Wabi Demeke from KAIST>
One of the key steps in developing new materials is “property identification,” which has long relied on massive amounts of experimental data and expensive equipment, limiting research efficiency. A KAIST research team has introduced a new technique that combines “physical laws,” which govern deformation and interaction of materials and energy, with artificial intelligence. This approach allows for rapid exploration of new materials even under data-scarce conditions and provides a foundation for accelerating design and verification across multiple engineering fields, including materials, mechanics, energy, and electronics.
KAIST (President Kwang Hyung Lee) announced on the 2nd of October that Professor Seunghwa Ryu’s research group in the Department of Mechanical Engineering, in collaboration with Professor Jae Hyuk Lim’s group at Kyung Hee University (President Jinsang Kim) and Dr. Byungki Ryu at the Korea Electrotechnology Research Institute (President Namkyun Kim), proposed a new method that can accurately determine material properties with only limited data. The method uses Physics-Informed Machine Learning (PIML), which directly incorporates physical laws into the AI learning process.
<Schematic Diagram of a Physics-Based Machine Learning Methodology for Understanding Material Properties>
In the first study, the researchers focused on hyperelastic materials, such as rubber. They presented a Physics-Informed Neural Network (PINN) method that can identify both the deformation behavior and the properties of materials using only a small amount of data obtained from a single experiment. Whereas previous approaches required large, complex datasets, this research demonstrated that material characteristics can be reliably reproduced even when data is scarce, limited, or noisy.
In the second study, the team turned to thermoelectric materials—new materials that convert heat into electricity and electricity into heat. They proposed a PINN-based inverse inference technique that can estimate key indicators, such as thermal conductivity (how well heat is transferred) and the Seebeck coefficient (how efficiently electricity is generated), from just a few measurements.
Going further, the researchers introduced a Physics-Informed Neural Operator (PINO), an AI model that understands the physical laws of nature, and showed that it can generalize to previously unseen materials without requiring retraining.
In fact, after training the system on 20 materials, they tested it on 60 entirely new materials, and in all cases it predicted their properties with high accuracy. This breakthrough points to a future where large-scale, high-speed screening of countless candidate materials becomes possible.
This achievement goes beyond simply reducing the need for experiments. By intricately combining physical laws with AI, the researchers provided the first example of improving experimental efficiency while preserving reliability.
Professor Seunghwa Ryu, who led both studies, stated, “This is the first case of applying AI that understands physical laws to real material research. It enables reliable identification of material properties even when data availability is limited, and it is expected to expand into various engineering fields.”
The first paper, co-first-authored by KAIST Mechanical Engineering PhD candidates Hyeonbin Moon and Donggeun Park, was published on August 13 in Computer Methods in Applied Mechanics and Engineering.
※ Paper title: “Physics-informed neural network-based discovery of hyperelastic constitutive models from extremely scarce data”
※ DOI: https://doi.org/10.1016/j.cma.2025.118258
The second paper, co-first-authored by KAIST Mechanical Engineering PhD candidates Hyeonbin Moon and Songho Lee, and Dr. Wabi Demeke, was published on August 22 in npj Computational Materials.
※ Paper title: “Physics-informed neural operators for generalizable and label-free inference of temperature-dependent thermoelectric properties” ※ DOI: https://doi.org/10.1038/s41524-025-01769-1
Meanwhile, the first study was supported by the Korea Research Foundation and the Ministry of Science and ICT’s INNOCore Program, as well as by a research project from the Ministry of Food and Drug Safety. The second study was carried out with support from the Korea Research Foundation and the Ministry of Science and ICT’s INNOCore Program.
2025.10.10 View 1985 -
Next Generation Robots Roaming Shipyards and City Centers
< Diden Robotics Research Team Co., Ltd (Leftmost person in the front row is CEO Joon-Ha Kim)>
KAIST announced on the September 30th that domestic robot startups, founded on KAIST research achievements, are driving new innovation at shipyards and urban worksites.
An industrial walking robot that freely climbs walls and ceilings and a humanoid walking robot that walks through downtown Gangnam are attracting attention as they enter the stage of commercialization. The stars are DIDEN Robotics Co., Ltd. and Eurobotics Co., Ltd.
Diden Robotics is providing a new breakthrough in the industrial automation market, including the shipbuilding industry, by commercializing its innovative 'Seungwol (Ascend and Cross) Robot' technology, which allows it to move freely and work on steel walls and ceilings. Eurobotics is commercializing world-class humanoid walking technology, and this achievement is scheduled to be officially presented at the international humanoid robot conference, 'Humanoids 2025,' to be held on October 1st.
< Diden Robot's Outer Plate (Longi) and Welding Test >
Diden Robotics is a robotics startup jointly founded in March 2024 by four alumni from the KAIST Mechanical Engineering Hu-bo Lab DRCD research team (Professor Hae-Won Park). Its flagship product, 'DIDEN 30,' is a quadrupedal robot designed for use in high-risk work environments that are difficult for humans to access, combining autonomous driving technology, a foot-shaped leg structure, and magnetic feet.
The 'DIDEN 30' successfully completed the 'Longitudinal (longi) Overcoming Test,' in which it stepped over steel stiffeners (longitudinals) densely installed as part of the structure at a ship construction site, proving its potential for field deployment. Currently, the company is conducting research to enhance its functionality so it can stably pass through access holes, the narrow entryways inside ships. It is also pushing for performance improvements so it can be deployed for real tasks such as welding, inspection, and painting starting in the second half of 2026.
A next-generation bipedal walking robot, 'DIDEN Walker,' is also under development. Targeting the completion of a prototype in the fourth quarter of 2025, it is being designed for stable walking in cramped and complex industrial environments. Plans are also underway to equip it with an upper-body manipulator for automated welding in the shipbuilding industry.
Diden Robotics is accelerating the advancement of its proprietary 'Physical AI' technology. The core is the self-developed AI learning platform, 'DIDEN World,' which applies an offline reinforcement learning method where the AI generates optimal motion data in a virtual simulation beforehand and learns without trial and error, increasing learning efficiency and stability.
< Diden Robot (DIDEN 30) >
Furthermore, to actually implement the AI technology, the company is internalizing its hardware and advancing its 3D recognition technology, which serves as the robot's 'eyes.' It is aiming for a completely autonomous walking system that requires no worker intervention by 2026, using technology such as 3D mapping based on four cameras.
In addition to this technological development, Diden Robotics successfully performed the longitudinal overcoming, Seungwol test, and welding work on blocks under construction through a joint development with Samsung Heavy Industries in September. This is a significant achievement, meaning Diden Robotics' technology has been validated in actual industrial settings, moving beyond the laboratory level.
Meanwhile, Diden Robotics is collaborating with major domestic shipyards, including Samsung Heavy Industries, HD Hyundai Samho, Hanwha Ocean, and HD Korea Shipbuilding & Offshore Engineering, to develop site-customized robots.
Joon-Ha Kim, CEO of Diden Robotics, stated, "The successful tests at the Samsung Heavy Industries site proved the practicality and stability of our technology. We will establish ourselves as a leading company in solving labor shortages and driving automation in the shipbuilding industry."
< (Eurobotics Research Team Co., Ltd.)(Leftmost person in the top row is CEO Byung-ho Yoo) >
Eurobotics is an autonomous walking startup jointly founded by three alumni from Professor Hyun Myung's research team at KAIST. It is promoting the commercialization of autonomous walking technology for indoor and outdoor industrial sites, including rough terrain. In a recently released video, a humanoid equipped with control technology developed by Eurobotics attracted attention by walking naturally through the crowd in downtown Gangnam.
The core technology is the 'Blind Walking Controller.' It determines locomotion based only on internal information without external sensors like cameras or LiDAR, enabling stable walking regardless of day, night, or weather. The robot performs locomotion by 'imagining' the terrain without precise terrain modeling, demonstrating robust performance with the same controller across various environments such as sidewalks, downhill slopes, and stairs.
This technology originated from the quadrupedal walking competition at the 2023 International Conference on Robotics and Automation (ICRA), where Professor Myung's lab participated, and proved its world-class capability by winning, beating MIT by a large margin. At the time, Byungg-ho Yoo, CEO of Eurobotics, led the team, and Co-CTOs Min-ho Oh and Dong-kyu Lee directly participated in developing the core autonomous walking technology. Based on this, they continued further development tailored to the humanoid environment and have entered the commercialization stage.
< Eurobotics' Humanoid Walking >
Byung-ho Yoo, CEO of Eurobotics, emphasized, "This video is the first step toward complete humanoid autonomous walking. We will develop KAIST's research achievements into technologies that can be immediately utilized in industrial settings."
Hyeonmin Bae, Head of the KAIST Startup Center, said, "We will provide close support from the initial stages to help the on-campus robotics industry grow actively and assist them in settling down stably."
Kwang Hyung Lee, President of KAIST, stated, "This achievement is a representative case showing that KAIST's fundamental technologies are rapidly spreading to industrial fields through startups. KAIST will continue to actively support innovative entrepreneurship based on challenging research and help lead the global robotics industry."
※ https://2025humanoids.org https://www.seoulairobot.com/
2025.09.30 View 4348 -
KAIST Develops Semiconductor Neuron that Remembers and Responds Like the Brain
<(From left, clockwise) Professor Kyung Min Kim, Min-Gu Lee, Dae-Hee Kim, Dr. Han-Chan Song, Tae-Uk Ko, Moon-Gu Choi, and Eun-Young Kim>
The human brain does more than simply regulate synapses that exchange signals; individual neurons also process information through “intrinsic plasticity,” the adaptive ability to become more sensitive or less sensitive depending on context. Existing artificial intelligence semiconductors, however, have struggled to mimic this flexibility of the brain. A KAIST research team has now developed next-generation, ultra-low-power semiconductor technology that implements this ability as well, drawing significant attention.
KAIST (President Kwang Hyung Lee) announced on September 28 that a research team led by Professor Kyung Min Kim of the Department of Materials Science and Engineering developed a “Frequency Switching Neuristor” that mimics “intrinsic plasticity,” a property that allows neurons to remember past activity and autonomously adjust their response characteristics.
“Intrinsic plasticity” refers to the brain’s adaptive ability- for example, becoming less startled when hearing the same sound repeatedly, or responding more quickly to a specific stimulus after repeated training. The “Frequency Switching Neuristor” is an artificial neuron device that autonomously adjusts the frequency of its signals, much like how the brain becomes less startled by repeated stimuli or, conversely, increasingly sensitive through training.
The research team combined a “volatile Mott memristor,” which reacts momentarily before returning to its original state, with a “non-volatile memristor,” which remembers input signals for long periods of time. This enabled the implementation of a device that can freely control how often a neuron fires (its spiking frequency).
<Figure 1. Conceptual comparison between a neuron and a frequency-tunable neuristor. The intrinsic plasticity of brain neurons regulates excitability through ion channels. Similarly, the frequency-tunable neuristor uses a volatile Mott device to generate current spikes, while a non-volatile VCM device adjusts resistance states to realize comparable frequency modulation characteristics>
In this device, neuronal spike signals and memristor resistance changes influence each other, automatically adjusting responses. Put simply, it reproduces within a single semiconductor device how the brain becomes less startled by repeated sounds or more sensitive to repeated stimuli.
To verify the effectiveness of this technology, the researchers conducted simulations with a “sparse neural network.” They found that, through the neuron’s built-in memory function, the system achieved the same performance with 27.7% less energy consumption compared to conventional neural networks.
They also demonstrated excellent resilience: even if some neurons were damaged, intrinsic plasticity allowed the network to reorganize itself and restore performance. In other words, artificial intelligence using this technology consumes less electricity while maintaining performance, and it can compensate for partial circuit failures to resume normal operation.
Professor Kyung Min Kim, who led the research, stated, “This study implemented intrinsic plasticity, a core function of the brain, in a single semiconductor device, thereby advancing the energy efficiency and stability of AI hardware to a new level. This technology, which enables devices to remember their own state and adapt or recover even from damage, can serve as a key component in systems requiring long-term stability, such as edge computing and autonomous driving.”
This research was carried out with Dr. Woojoon Park (now at Forschungszentrum Jülich, Germany) and Dr. Hanchan Song (now at ETRI) as co-first authors, and the results were published online on August 18 in Advanced Materials (IF 26.8), a leading international journal in materials science.
※ Paper title: “Frequency Switching Neuristor for Realizing Intrinsic Plasticity and Enabling Robust Neuromorphic Computing,” DOI: 10.1002/adma.202502255
This research was supported by the National Research Foundation of Korea and Samsung Electronics.
2025.09.30 View 2247 -
World's First Quantum Computing for Lego-like Design of Porous Materials
<(From Left to Right)Professor Jihan Kim, Ph.D. candidate Sinyoung Kang, Ph.D. candidate Younghoon Kim from the Department of Chemical and Biomolecular Engineering>
Multivariate Porous Materials (MTV) are like a 'collection of Lego blocks,' allowing for customized design at a molecular level to freely create desired structures. Using these materials enables a wide range of applications, including energy storage and conversion, which can significantly contribute to solving environmental problems and advancing next-generation energy technologies. Our research team has, for the first time in the world, introduced quantum computing to solve the difficult problem of designing complex MTVs, opening an innovative path for the development of next-generation catalysts, separation membranes, and energy storage materials.
On September 9, Professor Jihan Kim's research team at our university's Department of Chemical and Biomolecular Engineering announced the development of a new framework that uses a quantum computer to efficiently explore the design space of millions of multivariate porous materials (hereafter, MTV).
MTV porous materials are structures formed by the combination of two or more organic ligands (linkers) and building block materials like metal clusters. They have great potential for use in the energy and environmental fields. Their diverse compositional combinations llow for the design and synthesis of new structures. Examples include gas adsorption, mixed gas separation, sensors, and catalysts.
However, as the number of components increases, the number of possible combinations grows exponentially. It has been impossible to design and predict the properties of complex MTV structures using the conventional method of checking every single structure with a classical computer.
The research team represented the complex porous structure as a 'network (graph) drawn on a map' and then converted each connection point and block type into qubits that a quantum computer can handle. They then asked the quantum computer to solve the problem: "Which blocks should be arranged at what ratio to create the most stable structure?"
<Figure1. Overall schematics of the quantum computing algorithm to generate feasible MTV porous materials. The algorithm consists of two mapping schemes (qubit mapping and topology mapping) to allocate building blocks in a given connectivity. Different configurations go through a predetermined Hamiltonian, which is comprised of a ratio term, occupancy term, and balance term, to capture the most feasible MTV porous material>
Because quantum computers can calculate multiple possibilities simultaneously, it's like spreading out millions of Lego houses at once and quickly picking out the sturdiest one. This allows them to explore a vast number of possibilities—which a classical computer would have to calculate one by one—with far fewer resources.
The research team also conducted experiments on four different MTV structures that have been previously reported. The results from the simulation and the IBM quantum computer were identical, demonstrating that the method "actually works well."
<Figure2. VQE sampling results for experimental structures and the structures that reproduce them, using IBM Qiskit's classical simulator. The experimental structure is predicted to be the most probable outcome of the VQE algorithm's calculation, meaning it will be generated as the most stable form of the structure.>
In the future, the team plans to combine this method with machine learning to expand it into a platform that considers not only simple structural design but also synthesis feasibility, gas adsorption performance, and electrochemical properties simultaneously.
Professor Jihan Kim said, "This research is the first case to solve the bottleneck of complex multivariate porous material design using quantum computing." He added, "This achievement is expected to be widely applied as a customized material design technology in fields where precise composition is key, such as carbon capture and separation, selective catalytic reactions, and ion-conducting electrolytes, and it can be flexibly expanded to even more complex systems in the future."
Ph.D. candidates Sinyoung Kang and Younghoon Kim of the Department of Chemical and Biomolecular Engineering participated as co-first authors in this study. The research results were published in the online edition of the international journal ACS Central Science on August 22.
Paper Title: Quantum Computing Based Design of Multivariate Porous Materials
DOI: https://doi.org/10.1021/acscentsci.5c00918
Meanwhile, this research was supported by the Ministry of Science and ICT's Mid-Career Researcher Support Program and the Heterogeneous Material Support Program.
2025.09.09 View 2042