%45%6e%67%69%6e%65%65%72%69%6e%67
-
KAIST Automates the Search for “Dream Semiconductor” 2D Semiconductors
The era of researchers manually searching for two-dimensional semiconductors, which are drawing attention as next-generation AI semiconductors, is coming to an end. KAIST researchers have automated semiconductor screening and device fabrication, analyzed thousands of devices, and revealed the relationship between thickness and performance that had long been difficult to identify. This achievement is expected to shift next-generation semiconductor research toward a data-driven approach and accelerate the commercialization of AI semiconductors and ultra-low-power semiconductors.
KAIST (President Choongsik Bae) announced on the 9th that a research team led by Professor Jimin Kwon of the School of Electrical Engineering and the Department of AI System has developed a technology that automatically identifies two-dimensional semiconductors from optical microscope images alone and connects the process to transistor fabrication, through joint research with UNIST, Hanbat National University, Hanyang University, and Washington University in St. Louis in the United States.
Two-dimensional semiconductors are ultrathin semiconductors only a few atomic layers thick. They are called “dream semiconductors” because they can enable smaller semiconductors that consume less electricity than conventional silicon semiconductors. Today’s silicon semiconductors are approaching physical limits, as continued miniaturization of circuits leads to greater power loss and heat generation. Two-dimensional semiconductors, which are attracting attention as next-generation materials to overcome these limits, are expected to be used in a wide range of future technologies, including AI semiconductors, smartphones, data centers, wearable devices, foldable or stretchable electronics, and ultra-small medical sensors.
However, in two-dimensional semiconductors made through solution processing, the position, size, and thickness of each small semiconductor flake all differ, requiring researchers to find the desired samples one by one under a microscope. They then had to manually design electrodes according to the identified positions, requiring substantial time and effort, and making it practically difficult to analyze thousands or more devices at once.
The research team used molybdenum disulfide (MoS₂), a representative two-dimensional semiconductor material. By using the fact that the RGB red, green, and blue brightness values seen under a microscope change depending on thickness, the team enabled a computer to automatically identify the desired semiconductor and automatically design the electrodes. Verification using atomic force microscopy (AFM) confirmed that even subtle thickness differences of three to eight layers could be accurately distinguished.
Through this approach, the team successfully selected suitable samples automatically from more than 120,000 semiconductor flakes and fabricated and analyzed 1,615 transistors.
The large-scale analysis also produced meaningful results. The team statistically clarified for the first time that as the semiconductor becomes thicker, current flows more easily, but the ability to switch electricity on and off actually decreases. This characteristic had been difficult to confirm previously because only a small number of samples could be analyzed, but the team revealed it through large-scale data.
The greatest significance of this study is that it did not simply automate the fabrication process, but transformed two-dimensional semiconductor research, which had relied on human experience, into data-driven research. Going forward, the technology is expected to enable researchers to fabricate and analyze more semiconductors more quickly, identify high-performance materials, and ultimately expand into research in which AI designs new semiconductors.
This study was conducted with Professor Jimin Kwon, Dr. Haksoon Jung, and Dr. Yongwoo Lee of KAIST as co-corresponding authors, and Sanghyun Lee of UNIST as the first author. The research results were published on April 3 in Advanced Functional Materials, a leading international journal in materials science, and were also selected as an Inside Back Cover article in the field of 2D Materials & Electronics.
※ Paper title: Statistically Resolving Thickness-Dependent Electrical Characteristics in Multilayer-MoS₂ Transistors, DOI: 10.1002/adfm.202532204
※ Author information: Professor Jimin Kwon (KAIST, corresponding author), Dr. Haksoon Jung (KAIST, corresponding author), Dr. Yongwoo Lee (KAIST, corresponding author), Sanghyun Lee (UNIST, first author), and participating researchers from partner institutions: Sumin Hong (UNIST), Minho Park (UNIST), Professor Seongju Kim (Hanbat National University), Professor Sang-Hoon Baek (Hanyang University), Professor Joonki Suh (KAIST), Seonguk Yang (KAIST), Professor Sang-Hoon Bae (Washington University in St. Louis), and Dr. Chang-Soo Lee (TDS)
This research was supported by the Individual Basic Research Program of the National Research Foundation of Korea (NRF), funded by the Ministry of Science and ICT (MSIT), and by the Advanced Strategic Industry Super-Gap Technology Development Program of the Korea Planning & Evaluation Institute of Industrial Technology (KEIT), funded by the Ministry of Trade, Industry and Energy (MOTIE).
2026.07.09 View 162 -
KAIST Develops Core Display Technology That Prevents Image Distortion Even When Stretched
Beyond bendable and foldable displays, the era of stretchable displays, whose screens can expand freely like rubber, is now emerging. KAIST researchers have developed a core technology that allows text, images, and other on-screen information to retain their original shape even when the screen is stretched by up to 15%. The achievement is expected to help solve the problem of image distortion and accelerate the commercialization of next-generation high-quality stretchable displays.
KAIST (President Choongsik Bae) announced on the July 8 that a research team led by Professor Seunghyup Yoo of the School of Electrical Engineering, in collaboration with Professor Hanul Moon’s team at Dong-A University (President Hae Woo Lee), has successfully implemented an auxetic-based stretchable display platform. Auxetic structures expand in both width and length when pulled, allowing the display to stretch uniformly at the same ratio in all directions without distorting the image on the screen.
Conventional stretchable displays are generally made by forming light-emitting devices on a stretchable substrate, which serves as the base layer of the display. However, when such a substrate is stretched in one direction, it tends to shrink in the opposite direction, causing letters and images on the screen to become flattened or distorted. Auxetic structures have been used to address this problem, but most previous approaches were limited to maintaining the overall horizontal-to-vertical ratio of the screen, while the letters and images within the screen still remained vulnerable to distortion.
Instead of bonding the auxetic structure and the stretchable substrate across the entire surface, as in conventional methods, the research team proposed a new design approach that uses computational analysis to selectively connect only the necessary points that ensure isotropic expansion throughout the substrate.
In the conventional approach, the twisting deformation that occurs as the auxetic structure stretches is directly transferred to the substrate, distorting the image inside the screen. In contrast, the platform developed by the research team was designed so that each region moves evenly outward from its original position. This allows not only the entire screen but also small areas such as letters and images to expand together while maintaining their original shapes.
The research team verified the platform’s performance by repeatedly stretching a substrate patterned with letters and images in both the horizontal and vertical directions. In the conventional method, the patterns underwent local deformation, whereas in the new platform, the shapes of the letters and images remained intact. This demonstrates that not only the whole screen but also fine images on-screen can expand uniformly without distortion.
The team also integrated an LED array, a structure in which multiple LEDs are arranged at regular intervals, onto the platform to verify its performance as an working stretchable display. Even when stretched by up to 15% in both the horizontal and vertical directions, stable electrical operation and the screen brightness were maintained. After repeated stretching to 15%, the decrease in brightness remained below 2%, confirming the platform’s potential for practical display applications.
This technology is expected to serve as a core platform for next-generation electronics with freely changeable shapes, including wearable electronic devices, electronic skin, or e-skin, which refers to electronic devices that stretch like skin while sensing and displaying information, medical biosensors, soft robots, and curved displays for automobiles and aircraft.
Professor Seunghyup Yoo of KAIST said, “For stretchable displays to be used as actual information display devices, they must not only stretch well, but also preserve on-screen information accurately during stretching,” adding, “This platform enables uniform expansion from small areas of the screen to the entire display, and will serve as a key foundational technology for accelerating the commercialization of high-quality stretchable displays.”
This study was led by KAIST Dr. Su-Bon Kim and Dr. Junho Kim as co-first authors, with Professor Hanul Moon of Dong-A University and Professor Seunghyup Yoo of KAIST as co-corresponding authors. The research was published in the international journal Nature Communications on June 10.
※ Paper title: Hybrid auxetic metamaterial platforms enabling multiscale isotropic expansion for distortion-free stretchable displays, DOI: 10.1038/s41467-026-74141-6
This research was supported by the National Research Foundation of Korea (NRF) Mid-Career Researcher Program, the Future Display Strategic Research Laboratory Program, the Korea Planning & Evaluation Institute of Industrial Technology (KEIT), and the Korea Institute for Advancement of Technology (KIAT) HRD Program.
2026.07.08 View 207 -
KAIST Enables DNA Synthesis Using Only Temperature Instead of Chemical Reagents
"Complex chemical processes are essential for making DNA." This long-held assumption in the field of biotechnology has been overturned by a Korean research team. A KAIST research team has developed the world's first foundational technology that enables the synthesis of desired DNA using only temperature. Using this technology, the team also demonstrated a "DNA temperature black box" that records temperature changes during shipping without electricity.
KAIST announced on the 7th of July that a research team led by Professor Yeongjae Choi of the Graduate School of Engineering Biology, in collaboration with ATG Lifetech Inc. (CEO Taehoon Ryu) and a research team led by Professor Hansol Choi from the Department of Life Science at Ewha Womans University, has developed this platform technology that synthesizes desired DNA sequences by controlling only temperature.
DNA is the "blueprint" that contains the genetic information of humans and all other living organisms. Scientists use custom-made DNA in various biotechnology applications, such as diagnosing diseases, developing new drugs, and creating microorganisms with new functions. Until now, however, each time one of the four bases that make up DNA—A, T, G, and C—was connected, chemical reagents had to be added and washed out repeatedly. As a result, costly automated DNA synthesis equipment and specialized research facilities were essential.
To overcome these limitations, the research team developed "hairpin DNA that reacts only at specific temperatures." This hairpin DNA is a special DNA structure that remains folded like a hairpin and unfolds only at a certain temperature. The team placed multiple types of hairpin DNA that operate at different temperatures into a single test tube and succeeded in synthesizing desired DNA step by step by changing only the temperature in the sequence.
This opens the way for synthesizing DNA with only a general temperature control device, without the need for complex reagent replacement or large-scale equipment.
As the technology advances, it is expected to greatly reduce the cost and time required to make DNA, lowering the entry barriers not only for synthetic biology and genetic research, but also for various bioindustries such as drug development and precision medicine.
To demonstrate the practical applicability of the technology, the research team also implemented a power-free "DNA temperature black box." This device is normally stored in a freeze-dried state and begins operating when a single drop of water is added just before use. It then automatically records—directly into a DNA sequence—when, how long, and in what order the temperature changes during shipping. In addition, when exposed to temperatures above a certain level, the device changes color, allowing abnormalities to be checked visually on the spot. It is expected to be used for the quality control of products for which cold-chain distribution is important, such as vaccines, biopharmaceuticals, cell therapies, and fresh foods.
KAIST researcher Jangho Choi and GIST doctoral student Jinho Kim participated in this research as co-first authors, and the research results were published in the international journal Nature Communications on July 2.
※ Paper title: Programmable one-pot polymerase-mediated DNA synthesis via temperature control
※ DOI: https://doi.org/10.1038/s41467-026-74890-4
※ Related Video: https://drive.google.com/file/d/1bUtzC83qIm1k-hNFKTb09yFPhfsD4iU-/view?usp=drive_lin
※ Authors: Jangho Choi (KAIST, co-first author), Jinho Kim (GIST, co-first author), Hansol Choi (Ewha Womans University, corresponding author), Yeongjae Choi (KAIST, corresponding author)
This research was supported by the Ministry of Science and ICT through the Future Promising Convergence Technology Pioneer Program, the Biofoundry-Based Technology Development Program, the Young Researcher Program, and the Global Basic Research Laboratory Program.
2026.07.07 View 178 -
KAIST Identifies the “Hidden Energy Cost” of AI Agents for the First Time
As the era of AI agents—systems that can reason and act autonomously—begins, the power consumption of data centers is emerging as a critical challenge. A KAIST research team has, for the first time, analyzed the computational cost and energy consumption of AI agents, finding that they can consume up to 136.5 times energy per query than conventional generative AI. The study shows that competitiveness in the AI era is expanding beyond model performance to include the efficiency of data centers and power infrastructure.
KAIST announced that a research team led by Professor Minsoo Rhu of the School of Electrical Engineering has systematically analyzed, for the first time, how much computational resources and power AI agents require in real-world service environments.
Large language model (LLMs) powered applications such as ChatGPT have rapidly evolved beyond simply answering questions. They are now developing into AI agents: next-generation AI systems that can plan, use external tools such as web search, calculators, and code execution environments, and solve complex tasks by coordinating multiple steps on their own.
Although AI agents are increasingly being adopted in areas such as software development, research, and workplace automation, little has been known about the amount of electricity and operational cost required to run them in practice.
The research team defined AI agents not merely as software programs, but as a new type of workload that must be continuously processed by data-center servers and graphics processing units, or GPUs—high-performance chips used for large-scale AI computation. The team then analyzed the computational load and energy consumption incurred during actual AI agent execution.
The analysis found that AI agents perform, far higher volumes of LLM invocations than conventional chain-of-thought reasoning. Chain-of-thought, or CoT, refers to a method in which an AI model breaks down its reasoning process step by step to reach an answer, while an LLM invocation refers to each computational request made to a language model to generate a new judgment or response.
Because AI agents repeatedly call language models during execution, their response latency also increases significantly. The team found that response time can increase by up to 153.7 times, while GPUs remain idle for as much as 54.5 percent of the total execution time as external tools perform their tasks. In other words, as AI systems take on more complex tasks, a new form of inefficiency emerges in which expensive GPUs cannot be fully utilized.
The research team also analyzed the power consumption of AI agents at data-center scale. An AI agent using a 70-billion-parameter LLM—a scale comparable to current commercial AI services—consumed an average of 348.41 watt-hours per query. This is 136.5 times higher than the energy consumed by a conventional generative AI system performing simple question answering.
In addition, the team projected a future scenario in which 13.7 billion AI agent requests are generated per day — a volume equivalent to current Google search traffic. Under this scenario, data-center power demand would reach approximately 198.9 gigawatts, a level far exceeding the scale of AI data centers currently under development (which are in the range of a few gigawatts) and equivalent to roughly half of the average power consumption of the United States.
This study demonstrates that the focus of competition in the AI era is shifting from “smarter AI” to “optimally efficient AI.” Going forward, it will be essential not only to advance AI models, but also to jointly optimize AI semiconductors, data centers, and power infrastructure through co-design. Such an approach is expected to become a key strategy for reducing the operating cost of AI services and building sustainable AI infrastructure.
“This study is the first to quantitatively show not only how AI is becoming more intelligent, but also how much electricity and cost are required to implement and sustain that intelligence,” said Professor Rhu. “As AI agents become widespread, it will become increasingly important to take an integrated co-design approach that optimizes not only AI data-center infrastructure, but also AI agent models and power infrastructure.” He added, “Research and investment in this direction will be essential to dramatically reduce the cost for end users to access AI services while building sustainable AI infrastructure.”
The study was conducted with Jiin Kim, a Ph.D. student in the KAIST School of Electrical Engineering, as the first author. The paper was presented in February at the 32nd IEEE International Symposium on High-Performance Computer Architecture, or HPCA, one of the most prestigious international conferences in computer system design. The research team has also released the AI agent implementations and benchmarks used in the paper as open source to support follow-up studies by researchers worldwide.
Paper title: “The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Scaling from an AI Infrastructure Perspective”
Open-source repository: 10.1109/HPCA68181.2026.11408569
This research was supported by the Institute of Information & Communications Technology Planning & Evaluation (IITP) through the SW Starlab program, the K-Cloud Technology Development Program using AI semiconductors, and the Leading Technology Development Program for Advancing AI-Semiconductor-Based Data Centers, as well as by the Samsung Electronics Future Technology Incubation Center.
2026.07.07 View 249 -
KAIST Develops AI That Reads Animal Behavior Like Language
An artificial intelligence model capable of reading and interpreting animal behavior like language has been developed by researchers at KAIST. The team created BehaVERT, an AI model that learns behavioral data in a manner similar to natural language and was able to independently identify social behavioral deficits in an autism mouse model, opening a new avenue for interpretable neuroscience.
KAIST (President Kwang-Hyung Lee) announced that a research team led by Professor Dae-Soo Kim from the Department of Brain and Cognitive Sciences has developed an AI model that interprets animal movements as a form of behavioral language.
The researchers transformed skeletal movements of mice into tokens, analogous to words in natural language, and trained a transformer-based model to learn behavioral meaning. The resulting model, named BehaVERT, successfully identified core social behavioral abnormalities in an autism mouse model without being provided any prior biological knowledge.
The study introduces a novel AI framework for analyzing animal behavior through language-based representations. Beyond simple behavior classification, the model demonstrates the ability to uncover biologically meaningful patterns and may serve as a foundation for next-generation behavioral foundation models applicable to drug discovery, psychiatric research, and behavioral genetics.
Inspired by the idea that animal behavior may possess structures similar to language, the researchers represented the positions of a mouse's nose, ears, spine, limbs, and tail as behavioral tokens and trained a BERT-based transformer architecture.
As a result, BehaVERT learned not only to classify behaviors but also to understand their contextual meaning over time, much like language models infer meaning from sequences of words.
The model achieved state-of-the-art performance across five international benchmark datasets covering social interaction, multi-animal behavior, three-dimensional motion analysis, and autism-related behavioral assessment.
Importantly, BehaVERT also provides interpretability, allowing researchers to visualize which behavioral cues influenced its decisions.
In experiments distinguishing Shank3B knockout autism-model mice from healthy controls, the AI consistently focused on oral-oral contact behavior. This finding aligns with previous biological studies showing that autism-model mice exhibit deficits in social interaction despite maintaining normal approach behavior.
In other words, the AI independently rediscovered a key biological characteristic solely from behavioral observations, without explicit biological instruction.
The researchers further found that the model's internal representation space organized behavioral features such as mobility, attention, and social engagement into structured patterns. This suggests that animal behavior, much like language, may possess an underlying semantic structure.
The study also highlights an unusual interdisciplinary achievement. The first author, Dr. Seungjae Shin, and other members of the research team were trained primarily in biology rather than artificial intelligence. By independently learning transformer architectures and deep learning techniques, they designed specialized models and training strategies tailored for behavioral analysis.
Professor Kim's laboratory has long pursued AI-driven behavioral analysis and previously developed AVATAR, a technology that reconstructs rodent behavior in virtual environments, leading to the founding of Actnova Inc.
"The project began with a simple question: Could animal movements contain a structure similar to language?" said Dr. Seungjae Shin, the first author of the study.
The team also adopted a self-supervised learning framework that enables AI to learn directly from behavioral data without manual annotations. Furthermore, a model trained on rat behavior successfully transferred to mouse behavior analysis, demonstrating the feasibility of a behavioral foundation model applicable across species.
"BehaVERT goes beyond behavior classification and enables the interpretation of behavioral meaning," said Professor Dae-Soo Kim. "We expect it to become a key research tool for discovering new insights in drug development, psychiatric disorders, behavioral genetics, and many other areas of life sciences."
The study was published on March 24, 2026, in the International Journal of Computer Vision (IJCV), one of the world's leading journals in computer vision.
Paper Information
• Title: BehaVERT: A Transformer-Based Motion Language Model for Decoding Behavioral Semantics in Mice
• Journal: International Journal of Computer Vision (IJCV)
• DOI: 10.1007/s11263-026-02834-y
Related Videos
• BehaVERT — Social Behavior Analysis Visualization (Investigation & Mount), https://youtu.be/JshCr-ZBQR0
• BehaVERT — Social Behavior Analysis Visualization (Investigation & Attack), https://youtu.be/p9RPhZM__Js
• BehaVERT — AI Discovers Core Social Behavioral Features in an Autism Mouse Model, https://youtu.be/D6zUyDu3t9I
Funding
This research was supported by the Mid-Career Researcher Program and the Brain Convergence Technology Development Program through the National Research Foundation of Korea (NRF), funded by the Ministry of Science and ICT (MSIT), Republic of Korea.
2026.07.01 View 718 -
KAIST Identifies New Therapeutic Target by Revealing How Cancer ‘Hijacks’ the Blueprint for Blood Vessel Development
Anti-angiogenic therapies targeting VEGF have been widely used in cancer treatment, yet their long-term efficacy remains limited. Tumor vascular endothelial cells (TECs) exhibit high adaptive plasticity, enabling them to resist treatment and sustain tumor growth, but the molecular mechanism underlying this plasticity has remained poorly understood.
KAIST, led by President Kwang Hyung Lee, announced that a joint research team led by Professor Inkyung Jung (Department of Biological Sciences), Professor Ji Min Lee (Graduate School of Medical Science and Engineering), and Professor Gou Young Koh (Institute for Basic Science) has now uncovered the answer. By integrating cross-cancer single-cell transcriptomic and epigenomic atlases across eight solid tumor types with multiomic profiles, including 3D chromatin contact maps, of human embryonic stem cell (hESC)-derived vascular endothelial cell differentiation, the team demonstrated that TECs reactivate a gene regulatory program normally confined to the late progenitor stage of vascular development. Much like reusing an old blueprint rather than drawing up a new one, tumors co-opt this pre-existing developmental program to fuel blood vessel growth.
The team’s integrative framework combined single-cell RNA-seq and ATAC-seq across multiple tumor types with H3K27ac ChIP-seq, Hi-C-based 3D chromatin mapping across a dense time series of hESC-to-EC differentiation. This approach resolved the EC-progenitor specific regulatory program that defines the shared pro-angiogenic program between late EC progenitors and TECs.
Within this framework, integrin receptor (ITGAV) emerged as a functional mediator specifically upregulated in both late EC progenitors and TECs. Cell-to-cell interaction analysis identified multiple key ligands from tumor micro enviroment (TME) that reactivate the progenitor-associated gene regulatory program. Pharmacologic inhibition attenuated endothelial migration, invasion, and tube formation in vitro, and significantly reduced tumor vascularization and growth in a colorectal cancer xenograft model in vivo.
Professor Inkyung Jung noted that this study reframes how we understand tumor angiogenesis: tumors do not invent new mechanisms, but exploit regulatory programs already embedded in normal vascular development. This insight offers a new conceptual basis for why anti-VEGF therapies face limitations, and points toward targeting the underlying regulatory architecture of endothelial plasticity as a complementary anti-angiogenic strategy.
The study was co-first authored by Dr. Andrew J. Lee, Dr. Sunwoo Min, Ph.D. student Su Chan Park; and Dr. Mei-Yu Qiu. Professors Inkyung Jung, Ji Min Lee, and Gou Young Koh served as corresponding authors. The findings were published on June 8 in Cancer Research [IF = 22.3].
※ Paper title: "A Co-opted Developmental Gene Regulatory Program in Endothelial Progenitors Promotes Tumor Angiogenic Phenotypes"
※ DOI: 10.1158/0008-5472.CAN-25-5094
※ Authors: Andrew J. Lee (KAIST, first author), Sunwoo Min (KAIST, co-first), Su Chan Park (KAIST, co-first), Mei-Yu Qiu (IBS, co-first), Gou Young Koh (IBS, co-corresponding), Ji Min Lee (KAIST, co-corresponding), Inkyung Jung (KAIST, corresponding)
This research was supported by the National Research Foundation of Korea and the Institute for Basic Science.
2026.07.01 View 362 -
Crude Oil Separates Without Boiling: KAIST and Georgia Tech Develop Energy-Saving Membrane Technology
An international research team led by KAIST has developed a membrane technology that could significantly reduce the energy required for crude oil refining by replacing part of the century-old distillation process.
KAIST(President Kwang Hyung Lee) announced that a team led by Professor Dong-Yeun Koh of KAIST, in collaboration with Professor Ryan Lively's group at Georgia Tech, demonstrated a simple and inexpensive membrane capable of separating crude oil at room temperature without heating. The research was published in Nature, one of the world's leading scientific journals.
Crude oil underpins modern life by providing not only transportation fuels but also essential feedstocks for plastics, packaging materials, textiles, and countless consumer products. Because the cost of refining directly influences the price of these products, technologies that reduce refining energy consumption can generate substantial economic and environmental benefits.
Traditionally, refineries separate crude oil through distillation, a process that heats crude oil above 350 °C to vaporize it and then cools the vapor to recover different fractions. Globally, crude oil distillation consumes approximately 1,100 terawatt-hours (TWh) of energy each year—equivalent to the annual output of about 130 nuclear power plants, each at gigawatt scale, operating continuously. As a result, distillation remains one of the largest sources of energy consumption and greenhouse gas emissions in the refining industry.
At the same time, increasing cost pressures in global petrochemical markets have intensified the need for more energy-efficient separation technologies.
Membrane-based crude oil fractionations have attracted increasing attention as a potential alternative. However, conventional wisdom has held that molecularly precise separation requires an ultrathin selective layer coated onto the membrane surface. While effective, such coatings increase manufacturing costs and are prone to defects when scaled to large areas, limiting industrial deployment.
To overcome this challenge, the researchers took a radically different approach. Instead of relying on a specialized coating, they passed crude oil directly through a bare porous polyacrylonitrile (PAN) membrane—a chemically stable and inexpensive polymer commonly used as a support material in industrial membranes.
As crude oil permeated through the membrane, heavy hydrocarbons selectively deposited on the pore walls, gradually narrowing the pores and creating self-assembled separation channels smaller than 2 nanometers. Rather than relying on a specially engineered coating, the crude oil itself created the nanoscale pathways needed for precise molecular separation.
Through these self-formed channels, lighter fractions such as naphtha, gasoline, and kerosene permeated rapidly, while heavier components were effectively retained. In a surprising reversal, membrane fouling—normally regarded as a performance-degrading phenomenon—became the very mechanism that enabled highly selective separation.
The bare PAN membrane delivered crude oil permeation rates approximately 23 times higher than those of previously reported state-of-the-art crude oil membranes while maintaining stable performance for 28 consecutive days.
Professor Ryan Lively (Georgia Tech) commented “one of the key challenges facing membrane systems for crude oil separation was the low productivities of the membrane units – the PAN membranes with their surprising separation mechanism – dramatically increase the productivity of the membrane unit, to the point where industry should seriously consider adopting the technology.”
Importantly, the technology can be integrated into existing refinery infrastructure as a modular filtration unit, avoiding major equipment replacement and reducing barriers to industrial adoption.
Process simulations showed that using the membrane as a pretreatment step before conventional distillation could reduce energy consumption by 31.6%, carbon dioxide emissions by 37.6%, cooling water usage by 20.7%, and operating costs by 36%.
If adopted throughout Korea's refining and petrochemical sector, the technology could reduce greenhouse-gas emissions by approximately 10 million tonnes annually—equivalent to the emissions of roughly four million internal combustion vehicles.
Beyond crude oil refining, the membrane platform could be applied to a broad range of chemical separation processes, including the purification of pyrolysis oil derived from waste plastics, the recovery of solvents used in battery manufacturing, pharmaceutical purification, and biofuel production. The researchers believe the technology could serve as a versatile platform for next-generation molecular separations across multiple industries.
Professor Dong-Yeun Koh of KAIST said, “This study reveals a new scientific principle in which a membrane interacts with a complex mixture and spontaneously forms its own separation channels. Working with real crude oil supplied by HD Hyundai Oilbank allowed us to validate the technology under conditions relevant to industrial operation.”
Professor Jae W. Lee of KAIST, a co-corresponding author of the study, added, “By advancing large-area membrane modularization and long-term operational reliability, we hope to broaden the adoption of membrane-based processes throughout the refining and petrochemical industries.”
Dr. Jihoon Choi and Dr. Hyeokjun Seo of KAIST, the study’s co-first authors, said, “Our goal is to precisely control this spontaneous pore-constriction phenomenon and develop it into a membrane platform applicable to the entire refining process. We also aim to expand the technology to plastic recycling, biofuel purification, and other sustainable chemical processes that support carbon neutrality.”
The study was co-first-authored by Dr. Jihoon Choi and Dr. Hyeokjun Seo of KAIST and was published online in Nature on June 24, 2026.
Paper Title: Crude Oil Fractionation by Means of Mesoporous Polyacrylonitrile Membranes
DOI 10.1038/s41586-026-10677-3
https://www.nature.com/articles/s41586-026-10677-3
This research was supported by the Ministry of Science and ICT of Korea through the Basic Research Program for Outstanding Early-Career Researchers and the Engineering Research Center (ERC) Program.
2026.06.25 View 1123 -
KAIST Develops Robot Learning Technology Capable of Precisely Imitating Even “Rough” Demonstrations
Robots with increasingly precise dexterity are becoming essential in everyday life and industrial settings, from assembling tiny smartphone components to assisting doctors in surgery. However, teaching robots delicate human movements has traditionally required collecting vast amounts of data at extremely fine time intervals, resulting in significant costs and time burdens. KAIST researchers have developed a robot artificial intelligence technology that can perform sophisticated tasks by autonomously adjusting precision according to the situation, even when trained only on coarsely (sparsely) sampled demonstrations.
KAIST, led by President Kwang Hyung Lee, announced on the 24th that a research team led by Professor Daehyung Park of the School of Computing has developed DiSPo, a multi-granularity manipulation model that generates fine-grained robot motions tailored to a user’s desired level of precision, even from rough human demonstrations.
Existing robot learning methods, such as Behavior Transformer and Diffusion Policy, are limited by their dependence on the time intervals of the data used during training. As a result, learning precision manipulation tasks such as screw fastening or component insertion has required collecting large volumes of high-frequency data at very short time intervals. This has significantly increased data collection costs and slowed down the inference speed of robot AI models.
To overcome these limitations, the research team combined Mamba, a state-space model capable of predicting time intervals, with a diffusion model that enables rich action representation. The team also introduced a new Step-scale factor mechanism, which allows users to directly control the time intervals used by the robot.
As a result, even when trained on only low-frequency (coarse) demonstration data, the robot can generate high-precision motions during inference without additional training by autonomously subdividing actions through a discretization process.
DiSPo achieved up to an 81% higher task success rate compared to state-of-the-art models in simulation environments. In real-world experiments using a collaborative robot, DiSPo stably performed challenging tasks such as passing a clamp through a narrow gap with only a 2.5 mm radial clearance and accurately pressing a small shutter button on a smartphone. This performance was up to four times higher than that of existing AI models.
The technology is expected to make a significant contribution to automation in a wide range of everyday and industrial service fields that require high precision, including precision component assembly, cable connection, medical surgery, and precision machining.
“This study demonstrates that robots can learn precise motions from coarse demonstrations and autonomously adjust their level of precision according to the task situation,” said Professor Daehyung Park. “Moving forward, this technology is expected to dramatically reduce data collection costs while serving as a general-purpose robot learning technology for various industrial fields, including precision assembly and medical applications.”
The study was led by Nayoung Oh, a master’s student at the KAIST Graduate School of AI, as the first author, and was presented on June 1 at the 2026 IEEE International Conference on Robotics and Automation, or ICRA 2026, one of the world’s most prestigious robotics conferences, held in Vienna, Austria.
Paper Title: DiSPo: Diffusion-SSM based Policy Learning for Coarse-to-Fine Action Discretization
DOI: https://doi.org/10.48550/arXiv.2409.14719
2026.06.24 View 830 -
KAIST Team Wins IEEE RA-L Best Paper Award for Second Year in a Row
A research team led by Professor Jee-Hwan Ryu of the Department of Civil and Environmental Engineering at KAIST has received the Best Paper Award from IEEE Robotics and Automation Letters (RA-L), one of the world's most prestigious journals in robotics, for the second consecutive year.
KAIST(President Kwang Hyung Lee) announced on June 22 that Professor Ryu's team received the award during ICRA 2026, held in Vienna, Austria, with the award ceremony taking place on June 4. Following its recognition in 2025, the team has now achieved the rare distinction of winning the RA-L Best Paper Award in two consecutive years, underscoring the global competitiveness and sustained impact of KAIST's soft robotics research.
The RA-L Best Paper Award is presented annually to a select group of papers demonstrating outstanding scientific contribution, technical originality, experimental rigor, and future impact. This year, only five papers were selected from more than 1,700 papers published in IEEE Robotics and Automation Letters during 2025.
The award-winning paper, titled “Self-Wearing Adaptive Garments via Soft Robotic Unfurling,” presents a novel assistive dressing technology in which garments autonomously unfold and move along the user's body using soft robotic principles. The research was led by Dr. Namgyun Kim of KAIST in collaboration with the research group of Professor Allison M. Okamura at Stanford University.
Conventional dressing-assistance systems often rely on external robotic devices and complex control systems, which can restrict user movement and comfort. In contrast, the KAIST team incorporated the core principles of soft growing robots into garment structures, enabling the clothing itself to gently unfold and assist the wearer without requiring a separate external robotic manipulator.
The researchers integrated a pneumatic eversion mechanism into lightweight and flexible garments. When pressurized, the structure gradually unfolds along the user's body, providing reliable dressing assistance while maintaining safety and compliance. The soft robotic architecture is particularly advantageous for applications involving direct human contact, as it minimizes physical burden and reduces the need for sophisticated control systems.
The team developed and evaluated multiple garment prototypes, including sleeves, jackets, and pants. Experimental results demonstrated that the garments could reliably unfold along the user's body, reducing physical effort during dressing while maintaining safe interaction forces.
This work highlights how soft growing robotics can expand beyond traditional applications such as locomotion, exploration, and manipulation to directly support activities of daily living. The technology has strong potential for assistive applications for older adults, people with disabilities, and rehabilitation patients, while also opening new directions for wearable robotics, rehabilitation engineering, and human-robot interaction.
“This second consecutive award demonstrates the sustained global competitiveness of KAIST robotics research,” said Professor Jee-Hwan Ryu. “Our work extends the core principles of soft growing robots into assistive dressing technologies that can directly improve daily life. We will continue developing safe, flexible, and human-centered robotic technologies.”
The paper was published in IEEE Robotics and Automation Letters on November 19, 2025.
Paper Title: Self-Wearing Adaptive Garments via Soft Robotic Unfurling DOI: 10.1109/LRA.2025.3634909
2026.06.22 View 1036 -
KAIST Teams Win Both International Challenges at ICRA 2026 and CVPR 2026
Two research teams from KAIST have claimed first place in international challenge competitions held at the world’s premier robotics and computer vision conferences.
KAIST (President Kwang-Hyung Lee) announced that the ACDC-K Team and the Curaytor Team, both from the laboratory of Prof. Hyun Myung in the School of Electrical Engineering, won first place in international challenge competitions held in conjunction with the IEEE International Conference on Robotics and Automation (ICRA 2026) and the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2026), respectively.
The achievement highlights the global competitiveness of KAIST’s robotic perception and spatial intelligence technologies, with two teams from the same laboratory securing victories in leading international competitions across distinct research fields.
The ACDC-K Team won first place among more than 60 participating teams in the SLAM (Simultaneous Localization And Mapping) category of the Hilti×Trimble SLAM Challenge 2026, held during the Open Challenges in Robotics for Asset Inspection (OCRAIM) Workshop at ICRA 2026 in Vienna, Austria, from June 1 to 5.
Jointly organized by Hilti, Trimble, and the University of Oxford, the challenge evaluates robotic localization and mapping performance using sensor data collected from real construction sites. Participants were required to address practical challenges frequently encountered in construction environments, including non-overlapping front and rear fisheye camera configurations, low-texture indoor scenes, and rapid camera motion.
To tackle these challenges, the ACDC-K Team developed a robust visual-inertial SLAM system that fuses front and rear fisheye camera data with inertial measurements. By integrating feature-point and feature-line observations with adaptive constraints and correction mechanisms, the team achieved highly reliable localization and mapping performance in complex construction environments.
Meanwhile, the Curaytor Team won first place among eight participating teams in the Nothing Stands Still (NSS) Challenge 2026, held during the Computer Vision for the Built World (CV4AEC) Workshop at CVPR 2026 in Denver, Colorado, from June 3 to 7.
Jointly organized by Stanford University, ETH Zurich, and Oregon State University, the NSS Challenge evaluates 3D point cloud registration technologies for construction and industrial environments that evolve over time.
The Curaytor Team developed a novel multi-registration framework capable of aligning multiple LiDAR scans collected across different times and locations. The framework integrates feature extraction, correspondence estimation, robust global registration, registration confidence assessment, and change-aware refinement techniques. As a result, the team achieved highly accurate registration performance even in environments containing structural changes and dynamic objects.
“This achievement demonstrates the robustness of our visual-inertial SLAM and 3D LiDAR registration technologies in complex and constantly changing real-world environments,” said Prof. Hyun Myung. “It is particularly meaningful that our students secured first-place finishes in highly competitive international challenges hosted at two of the world’s most prestigious conferences in robotics and computer vision.”
Prof. Hyun Myung’s laboratory has consistently demonstrated excellence in spatial intelligence research. The laboratory previously won first place in the LiDAR track and ranked first among academic teams in the vision track of the Hilti SLAM Challenge in 2023. In addition, the Curaytor Team successfully defended its title in the NSS Challenge, securing back-to-back championships in 2025 and 2026.
2026.06.19 View 1706 -
KAIST Develops Next-Generation Database Technology That Reduces AI Hallucinations and Improves Accuracy by 78%
One of the greatest weaknesses of AI agents that read and understand vast amounts of enterprise data is “hallucination” — the generation of plausible-sounding but factually incorrect information. KAIST researchers have developed a next-generation database technology capable of understanding documents, data, and relationships among entities all at once. The technology improves AI response accuracy by up to 78% and processing speed by up to 20 times, addressing a key challenge in the commercialization of enterprise AI.
KAIST, led by President Kwang Hyung Lee, announced on the 19th that a research team led by Professor Min-Soo Kim of the School of Computing, in collaboration with faculty startup GraphAI Co., Ltd., has developed “AkasicDB,” a next-generation database technology that integrates the functions of vector databases, graph databases, and relational databases into a single database management system (DBMS). Based on this technology, the team also developed a new Retrieval-Augmented Generation (RAG) method called “Omni RAG.”
AkasicDB is designed to integrate and execute the functions of vector databases, which convert the meaning of documents or images into numerical vectors to search for similar information; graph databases, which store and analyze relationships among entities such as people, companies, and products; and relational databases, which systematically manage data in table form. Omni RAG, developed on this foundation, improves the accuracy of generative AI responses by simultaneously utilizing semantic information from documents, relationships among entities, and structured data.
AI agents have recently been spreading rapidly based on RAG technology, which searches vast collections of corporate documents and expert knowledge and generates responses based on the retrieved information. However, real-world enterprise data is distributed across various forms, including documents, tables, and relationships among entities, making it difficult for AI to comprehensively understand and use the data. As a result, AI may generate factually incorrect responses without sufficient grounding, creating hallucination issues that have been regarded as a major obstacle to the broader adoption of enterprise AI.
Conventional RAG typically works by converting user queries and documents into vectors, retrieving semantically similar documents, and providing them to a large language model (LLM), an AI model trained on massive datasets to generate human-like language. While this approach is effective for searching unstructured documents, it has limitations when handling complex queries that must also consider relationships among entities in documents or structured conditions such as specific periods, types, or ranges.
For example, a query such as, “Find clauses related to Company A among contracts signed last year, and explain how those clauses are connected to product supply issues,” requires vector search to identify document meaning, graph search to explore relationships among entities, and relational queries to filter by date and type. In existing systems, this required building multiple types of databases separately and combining the results at the application layer, leading to management complexity and response delays.
To solve this problem, the research team proposed Omni RAG, which integrates vector similarity search, graph traversal, and relational filtering within a single query and execution plan. Omni RAG identifies more accurate evidence by simultaneously utilizing semantic information from documents, relationship information from knowledge graphs, and structural conditions from tabular data, significantly reducing AI hallucinations.
AkasicDB, developed to support this method, adopts a new architecture that integrates graph databases, vector databases, and relational databases into a single engine. Users can express complex RAG queries that combine vector search, graph traversal, and relational filtering as a single SQL/GQL* query, and AkasicDB optimizes and processes the query as one unified execution plan.
SQL/GQL, or Structured Query Language/Graph Query Language, refers to command languages used to search or modify information stored in databases. SQL is the traditional language used to handle tabular data, while GQL is a language dedicated to graph data and is used to analyze connections among entities such as people, companies, and products.
Through this integrated architecture, AkasicDB minimizes unnecessary intermediate result generation and data movement, greatly reducing the number of tokens used by LLMs and shortening response latency. In experiments, complex search queries that took up to 21.3 seconds in existing systems were processed in under one second, achieving a performance improvement of more than 20 times. Omni RAG also improved response accuracy by up to 78% compared with conventional RAG. These results demonstrate its potential to substantially mitigate hallucination, one of the core challenges for enterprise AI agents.
Professor Min-Soo Kim said, “For AI agents to accurately understand and utilize the vast amounts of data held by enterprises, data infrastructure capable of processing vector, graph, and relational data in an integrated manner within a single system is essential. AkasicDB is a next-generation database technology for the era of AI agents, and we expect it to be used as core data infrastructure in fields requiring high reliability, including defense, manufacturing, finance, law, science, and technology.”
KAIST School of Computing Ph.D. student Geonho Lee participated in this research as the first author. The research results were presented as a demo paper on June 2 at ACM SIGMOD 2026, one of the world’s most prestigious international conferences in the field of databases, where they drew strong interest from global companies and researchers.
※ Paper title: AkasicDB: Demonstrating Omni RAG with a Unified Vector-Graph-Relational DBMS
DOI: https://doi.org/10.1145/3788853.3801609
※ Author information: Geonho Lee, KAIST, first author; Jeongho Park and Donghyoung Han, GraphAI Co., Ltd., co-authors; Professor Min-Soo Kim, KAIST, corresponding author
※ Demonstration video: https://www.youtube.com/watch?v=KD6MznZ61P4
2026.06.19 View 1278 -
KAIST Develops Next-Generation Self-Powered Wearable Sensor Resilient to 668% Elongation
Wearable medical devices that monitor heart rate, respiration, and joint movements for long periods without battery concerns, electronic skins that sense external stimuli like human skin, and soft robots made of flexible materials that move freely have all come one step closer to reality. KAIST researchers have developed a self-powered sensor (a sensor that generates electricity on its own without a battery) that can stretch up to 668% while producing stable electrical signals.
KAIST announced on June 18th that a research team led by Professor Miso Kim from the Department of Mechanical Engineering has overcome the durability limitations of conventional piezoelectric fiber sensors (fiber-type sensors that convert pressure or movement into electrical signals) and successfully developed a highly stretchable piezoelectric fiber sensor that operates stably even under repeated deformation.
The core material of the sensor, piezoelectric polymer, is a polymeric material that generates electricity when subjected to mechanical force. Although its lightweight and flexible nature makes it suitable for skin-attachable wearable sensors, conventional piezoelectric fiber sensors suffered from signal degradation during repeated stretching or bending, as the electrode layer collecting electrical signals and the piezoelectric layer generating electricity would become damaged. Furthermore, while coiling the fibers can increase stretchability to allow greater elongation, maintaining electrical stability remained a significant challenge.
To resolve these issues, the research team developed a "Hierarchical Resilient Design" strategy, engineering the sensor to withstand deformation across multiple levels—from its constituent materials and electrodes to its overall structure. Simply put, just as a rubber band returns to its original shape after repeated stretching, the sensor is designed to self-maintain its performance after cyclical deformation.
First, the research team embedded elastic polymer microparticles inside the piezoelectric nanofibers to create a closely interlocking structure. This creates a supportive effect similar to Velcro, helping the sensor recover its original shape even after being repeatedly stretched.
Additionally, they designed the interface so that the electricity-collecting electrode and the electricity-generating piezoelectric layer connect seamlessly. By strongly bonding different materials together, they ensured they would not easily delaminate under impact or deformation, allowing the sensor to maintain a stable electrical signal even when significantly stretched or bent.
Applying this design to a coil structure, the research team successfully stretched the sensor up to 668%—approximately 6.7 times its original length—while maintaining a stable output. The developed sensor generated consistent electrical signals under various movements, including stretching, bending, and pressing.
Furthermore, the research team fabricated the sensor not only in coil forms but also in knot configurations, confirming its stable operation under repeated forces or sudden impacts. By leveraging artificial intelligence (AI) to analyze the sensor signals, they were also able to accurately distinguish between different movements, such as pressing, bending, and stretching.
This study holds great significance as it presents a self-powered sensor platform that simultaneously achieves high stretchability and long-term stability without requiring a battery. In particular, because it enables stable signal measurement in environments undergoing repeated deformation, it is expected to be utilized in developing next-generation wearable medical devices for long-term monitoring of various biosignals, including heart rate, respiration, joint movement, and muscle activity. It is also projected to expand its range of applications to digital healthcare devices, electronic skins, and sensory sensors for soft robots by making devices lighter and more convenient to use.
"The core achievement of this research is that it simultaneously secured mechanical resilience and electrical reliability by combining fiber structure design with electrode interface engineering (a technology that controls the boundary where different materials meet)," said Professor Miso Kim. She added, "In the future, we expect it to be applied to wearable medical devices requiring long-term wear, electronic skins, and sensory sensors for soft robots, enabling more accurate and continuous biosignal monitoring."
The research findings, with researcher Yong Jun Choi as the first author, were published on March 10, 2026, in ACS Nano (Impact Factor 16.1), a world-renowned academic journal in the fields of nanotechnology and materials science.
Paper Title: Mechanically and Functionally Resilient Piezoelectric Fiber Coils and Knots for Reliable Self-Powered Sensing DOI: doi/10.1021/acsnano.5c19628 Author Information: Yong Jun Choi 1 (KAIST, First Author), JungHun Park 1 (KAIST, Co-author), Jisoo Nam 1 (KAIST, Co-author), Gi-Dong Sim 1 (KAIST, Co-author), Myung-Gil Kim 2 (Sungkyunkwan University, Co-author), Miso Kim (KAIST, Corresponding Author)
This research was conducted with support from the BRIDGE Convergence Research and Development Program (RS-2023-00254689), the Nano·Material Technology Development Program (RS-2024-00468995), and the Next-Generation Semiconductor-Compatible Micro-Substrate Technology Development Program (RS-2024-00433654) funded by the National Research Foundation of Korea under the Ministry of Science and ICT.
2026.06.18 View 2112