%41%49
-
KAIST Develops Robot That Judges Its Surroundings and Walks, Runs, and Jumps Like an Animal
An era in which robots decide "how to walk" on their own has arrived. A four-legged robot has been developed that, much like a person or an animal, autonomously chooses the appropriate gait strategy for its surroundings — changing its gait on stairs, leaping over gaps, and keeping its balance on forest trails.
KAIST (President Choongsik Bae) announced on the 16th of July that a research team led by Professor Hae-Won Park from the Department of Mechanical Engineering has developed a core control technology for four-legged robots that lets a single controller select and switch in real time among walking, running, jumping, and other locomotion skills, allowing the robot to move quickly and stably, even in real outdoor environments.
Four-legged robots move on four legs, giving them an advantage over wheeled robots on rough terrain. But in real outdoor settings, obstacles such as stairs, ledges, stepping stones, gaps, and tree branches appear one after another in different forms, meaning the ability to simply walk and run fast is not enough.
Existing four-legged robots have excelled at running quickly across flat ground or clearing simple obstacles, but they have struggled to maintain both speed and stability in real-world environments where obstacles combine in complex ways. Because walking, running, jumping, and other gaits had to be controlled individually, the robots were also limited in how naturally they could switch between them as conditions changed.
To overcome these limitations, the research team developed a new learning-based control technology called APT-RL (Action Pretrained Transformer-based Reinforcement Learning).
APT-RL is a control technology designed to enable a robot to first learn a range of locomotion skills — such as walking, running, and jumping — and then freely combine and transition among them in real-world environments as the situation demands.
Rather than filming the movements of real people or animals, the team generated 15.5 hours of training data covering a variety of gaits using computer simulations alone, in just eight minutes. That data was used to teach the robot basic movement capabilities, drawing on robot dynamics (a mathematical model of how a robot moves) and trajectory optimization (a technique for calculating the efficient path of movement). The approach is far faster and more efficient than earlier methods that relied on motion capture, a technology that records human or animal movement using sensors.
The team then applied reinforcement learning — an artificial intelligence technique in which an agent learns optimal behavior through repeated trial and error — so the robot could autonomously select and switch gaits suited to complex three-dimensional terrain such as stairs, ledges, and gaps. Finally, the team combined a depth camera (which measures the distance to objects in order to obtain three-dimensional information) with LiDAR (Laser Detection and Ranging, a sensor that uses lasers to measure the distance and shape of the surrounding environment in three dimensions), enabling the robot to recognize its surroundings and target speed in real time and choose the most appropriate walking strategy.
The team tested the control technology on its own four-legged robot, 'KAIST HOUND.' The experiments were conducted not only on an indoor obstacle course but also in real outdoor environments, including KAIST’s campus and forest trails.
KAIST HOUND moved stably across urban terrain that included stairs, grass, and slopes, as well as irregular natural terrain such as fallen trees, exposed roots, and paths covered in fallen leaves, switching gaits in real time to match the conditions. In rugged terrain with obstacles, the robot reached a peak instantaneous speed of six meters per second (about 22 kilometers per hour), demonstrating that it can achieve both fast movement and stability in real outdoor environments.
The experiments showed that KAIST HOUND autonomously selected and switched between a trot (alternating diagonal legs) and a bound (a leaping gait using the front and back leg pairs together) depending on the terrain and target speed, and that it could integrate walking, running, jumping, and ledge-clearing into a single controller.
Professor Hae-Won Park said "We expect this to become a foundational technology that expands the potential uses of physical-AI-based walking robots in rugged environments such as disaster sites, defense missions, and industrial facility inspections."
Jun-Gill Kang (affiliated with the Agency for Defense Development (ADD) at the time of the research) and Jaehyun Park, a Ph.D. candidate in KAIST's Department of Mechanical Engineering, are co-first authors of the study. Professor Hae-Won Park and Professor Seungwoo Hong from Korea University are co-corresponding authors. The research was selected as the cover paper for the July issue of Science Robotics, the world's leading academic journal in robotics, and was published on July 15 (U.S. Eastern time).
Paper title: Agile perceptive multi-skill locomotion for quadrupedal robots in the wild
DOI: 10.1126/scirobotics.adz7397
Authors: Jun-Gill Kang (the Agency for Defense Development at the time of the research, co-first author), Jaehyun Park (KAIST, co-first author), Hae-Won Park (KAIST, corresponding author), Seungwoo Hong (Korea University, corresponding author)
Related Video: https://drive.google.com/drive/folders/1306_hddGZGh7xwvWFc4B-9lLXwYisirN
This research was supported by funding from the Ministry of Trade, Industry and Resources (MOTIR) and the Korea Planning & Evaluation of Industrial Technology (KEIT) (RS-2024-00427719), as well as by the Agency for Defense Development's Future Challenge Defense Technology R&D program (912768601).
2026.07.16 View 86 -
KAIST Develops Key Technology to Make Personalized AI Safer
“Create an AI assistant trained only on our company’s documents.”
The era of building “personalized AI” by training AI models on individual or corporate documents and data is beginning. However, while such customization can improve task performance, it can also weaken the model’s existing safety safeguards. KAIST researchers have developed a core AI technology that preserves customized performance while further strengthening safety.
KAIST (President Choongsik Bae) announced on the 15th of July that a research team led by Professor Changick Kim from its School of Electrical Engineering has developed “Buffer-and-Reinforce,” a training framework for safe fine-tuning that prevents safety degradation when large language models (LLMs), such as
ChatGPT, are retrained on data from individuals or companies to better suit their needs.
Until now, one of the biggest challenges in the era of personalized AI has been that fine-tuning improves a model’s ability to perform new tasks, but can also weaken its existing safety rules. The research team focused on prior findings showing that, counterintuitively, fine-tuning an AI model while it is in a temporarily jailbroken state — a state in which it may respond even to dangerous requests it would normally refuse — does not significantly compromise its safety.
The team then devised a new approach in which this jailbroken state is not used in actual services, but is applied only temporarily during the fine-tuning process through a buffering module called “BufferLoRA,” which is removed after training.
The research team was the first to clarify why this phenomenon occurs. They found that, in the temporarily jailbroken state, the AI model becomes less easily influenced by harmful information, while still effectively learning the new task abilities desired by the user. In other words, the model can continue learning useful knowledge without additionally absorbing harmful behaviors.
Based on this insight, the team developed a two-stage learning method consisting of “buffering” and “safety reinforcement.”
First, the temporary buffering module, BufferLoRA, is applied to the AI model during user fine-tuning, where it acts as a protective layer that prevents harmful data from directly affecting the base model. Once fine-tuning is complete, this module is removed.
Next, a safety reinforcement module called “ReinforceLoRA” is applied to restore and strengthen the model’s safety. In this process, the team used QR decomposition, a mathematical technique that separates different types of information and selectively reflects only the necessary components. This allowed the model to retain the new functions learned from user data while selectively reinforcing safety.
Simply put, the researchers first placed a temporary protective layer, BufferLoRA, over the AI model so that harmful data could not directly affect it, while allowing the model to learn the necessary task. They then removed the protective layer and applied ReinforceLoRA to strengthen the model’s safety safeguards. As a result, the model maintained its customized performance while achieving even stronger safety.
In experiments, the AI model maintained high safety even in an extreme setting where all user data consisted of harmful questions and answers. After fine-tuning, the rate at which the AI generated harmful responses was about 8%, lower than the roughly 18% observed in the original model that had not been fine-tuned at all. The framework also achieved strong customized performance and state-of-the-art safety without requiring additional safety data during user fine-tuning or significantly increasing computational cost, suggesting its practical applicability to real-world personalized AI services.
Professor Changick Kim stated, “This research provides a key foundational technology that allows anyone to build customized AI with their own data while using it more safely,” adding, “We expect it to contribute significantly to building a trustworthy AI service environment in the era of personalized AI and AI agents.”
This research was led by Seokil Ham, a doctoral student in KAIST’s School of Electrical Engineering, as first author. The paper was selected as a Spotlight presentation at the International Conference on Machine Learning (ICML) 2026, one of the world’s most prestigious conferences in artificial intelligence, an honor given to only about the top 2.2% of all submitted papers, drawing international attention.
※ Paper title: Jailbreak to Protect: Buffering and Reinforcing via Temporary Jailbreaking for Safe Fine-Tuning in Large Language Models
DOI: 10.48550/arXiv.2605.24550
※ Author information: Seokil Ham (KAIST, first author), Jaehyuk Jang (KAIST, second author), Wonjun Lee (KAIST, third author), Changick Kim (KAIST, corresponding author)
※ Related video: https://drive.google.com/file/d/1gfok06dE8699qtiUR7gVsRoVmBGADaWQ/view?usp=sharing
This work was supported by Institute of Information & Communication Technology Planning & Evaluation (IITP) grant funded by Ministry of Science and ICT(MSIT) (No. RS-2025-02215344, Development of AI Technology with Robust and Flexible Resilience Against Risk Factors).
2026.07.15 View 120 -
KAIST Develops AI Technology to Detect Early Warning Signs of Cerebrovascular Disease at Home
Cerebrovascular disease can lead to serious aftereffects if treatment is delayed, but it is difficult to detect before symptoms appear. KAIST researchers have developed an AI technology that analyzes real-life daily activity and environmental data from older adults to identify digital behavioral markers of cerebrovascular disease risk based on subtle changes at home.
KAIST (President Choongsik Bae) announced on the 12th of July that a research team led by Professor Lisa Lim from the Department of Civil and Environmental Engineering, in collaboration with Professor Jo Woon Chong from the School of Electronic and Electrical Engineering at Sungkyunkwan University (President Ji-Beom Yoo) and Professor Kyung-Hee Cho from the Department of Neurology at Korea University Anam Hospital (President Dongwon Kim), has developed an AI framework that uses long-term lifelog data collected in the homes of older adults to identify the prodromal phase of cerebrovascular disease and assess imminent diagnostic risk.
The study was based on lifelog data from 1,224 older adults collected by LivOn Care Co., Ltd. in real residential environments. The research team analyzed a total of 13,362 two-week lifelog samples, demonstrating the possibility of detecting early warning signs through subtle changes in daily life, rather than relying only on the conventional approach of treating the disease after it has already occurred.
The research team developed AI technology that identifies cerebrovascular disease risk stages by analyzing daily activity, sleep, circadian rhythm, and indoor environmental information, together with age and chronic disease data. This shows that changes in everyday living patterns, which are difficult to capture through hospital examinations alone, can serve as important clues for detecting early risk signals of cerebrovascular disease.
The team also succeeded in assessing whether a cerebrovascular disease diagnosis was approaching by analyzing changes in lifestyle patterns over time. When lifelog data from within four weeks before diagnosis were classified as the “imminent diagnostic risk period” and data from 12 weeks before diagnosis were classified as the “non-imminent period,” the AI distinguished between the two periods with a high accuracy of 96.53%. This result suggests that even before a hospital visit, small changes in daily life may help identify whether the risk of cerebrovascular disease has increased.
Another key feature of this study is that the AI does not simply determine whether a risk exist, but also applies explainable AI to identify the lifestyle patterns and environmental factors behind its judgment.
The analysis showed that older adults in the prodromal phase of cerebrovascular disease tended to show frequent continuous activity between 10 p.m. and 2 a.m., a time when the body would normally be preparing for sleep. In other words, irregular daily rhythms, such as delayed sleep onset and a reduced distinction between day and night activity, were closely associated with prodromal signals of cerebrovascular disease.
The researchers also found that as the time of diagnosis approached, the frequency of continuous activity during the evening period from 6 p.m. to 10 p.m. noticeably decreased, while inactive time increased. Low indoor humidity, indicating a dry indoor environment, also emerged as an important factor in identifying an imminent diagnostic risk.
The research team expects this technology to be used as a digital healthcare tool that can objectively monitor the health status of older adults who may have difficulty clearly describing their own condition, while providing useful early warning indicators to medical professionals and caregivers.
However, the team explained that this study does not predict the exact onset of cerebrovascular disease or replace clinical diagnosis. Rather, it is a supportive technology intended to aid prevention and early medical consultation, and prospective validation in larger patient groups will be necessary before actual clinical application.
Professor Lisa Lim said, “The key point of this study is not that AI should replace a hospital diagnosis, but that it can first detect risk signals in small lifestyle changes at home and help connect patients to medical care at the right time,” adding, “We expect this technology to contribute to a shift from a healthcare system that treats disease after it occurs to one that supports prevention and early intervention.”
This study, with KAIST Dr. Jeongyeop Baek as the first author, was published on June 2 in npj Digital Medicine, a leading international journal in digital healthcare published by Nature Portfolio, with an impact factor of 15.1 and ranked in the top 0.3% of JCR journals.
※ Paper title: AI home monitoring for behavioral markers of cerebrovascular disease
DOI: https://doi.org/10.1038/s41746-026-02836-7
This work was also supported by the National Research Foundation (NRF) grant funded by the Korea government (Ministry of Science and ICT) (RS-2025-16068234).
2026.07.13 View 228 -
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 446 -
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 532 -
KAIST Global Entrepreneurship Summer School Marks Fifth Consecutive Year of Cultivating Future Entrepreneurs in Silicon Valley
The 2026 Global Entrepreneurship Summer School (GESS), organized by the KAIST Office of Global Initiatives, has successfully concluded its fifth annual program.
Now in its fifth year, GESS has become KAIST's flagship global entrepreneurship program, providing students with firsthand experience in Silicon Valley—the world's leading startup ecosystem—and equipping them with the entrepreneurial mindset and global competencies needed to launch ventures on the international stage.
Participants in the 2026 GESS program, including both undergraduate and graduate students, were selected through a competitive process consisting of document screening, interviews, team presentations, and peer evaluations.
Prior to traveling to Silicon Valley, the selected students completed a four-month preparatory program that included team building, customer discovery, business model development, and pitch preparation. Throughout the program, they received mentoring from entrepreneurs, venture investors, and industry experts, enabling them to refine their business ideas and evaluate their potential for entering global markets.
The Silicon Valley program, held in late June, was organized in collaboration with leading startup support organizations, including KOTRA Silicon Valley, IBK Changgong Silicon Valley, and Plug and Play. Through meetings with entrepreneurs, venture capitalists, and representatives from global technology companies, students gained firsthand insight into the Silicon Valley startup ecosystem while developing a deeper understanding of global markets.
For the fourth consecutive year, students from the KAIST College of Business Impact MBA program also participated in the Silicon Valley program, creating valuable opportunities for interdisciplinary collaboration and exchange among students with diverse academic backgrounds and professional experiences.
A highlight of this year's program was a startup storytelling workshop conducted in collaboration with educators from Stanford University. The workshop helped students strengthen their communication skills by learning how to present their ideas more persuasively—an essential competency for aspiring global entrepreneurs.
In partnership with KAIST alumni based in Silicon Valley, participants also visited leading global technology companies and unicorn startups, including Meta, NVIDIA, and Moloco. They attended networking events with local professionals and alumni, gaining firsthand exposure to the innovation culture and growth strategies of global technology companies while broadening their perspectives on international careers and entrepreneurship.
To put into practice one of the core values of entrepreneurship—creating positive social impact—GESS participants also organized "Let's Play AI+Tech," a community outreach program for elementary school students from underserved families in Sunnyvale, California. Designed and led entirely by KAIST students, the program introduced fundamental concepts in artificial intelligence through engaging, hands-on activities for children and their parents. The initiative also offered KAIST students a meaningful opportunity to give back to the local community while sharing their expertise in AI and technology.
The program concluded with the Final Pitch Competition, where each team presented the business models they had developed over several months to a panel of Silicon Valley investors and entrepreneurship experts. Through expert feedback and evaluation, participants had the opportunity to validate the global potential of their ventures.
Following a highly competitive final round, Team CUPID was named the overall winner. Team CUPID presented an AI-powered developer platform that automatically routes coding tasks to the most cost-effective AI model, significantly reducing developers' AI usage costs. The team received high praise from the judges for its clear problem definition, strong market potential, and scalability in the global market.
Gianidita Nurani Pertiwi, a member of Team CUPID and a student in the Department of Bio and Brain Engineering, said, "GESS provided an invaluable opportunity to experience Silicon Valley's entrepreneurial ecosystem firsthand. Through conversations with founders, investors, and industry experts, I learned how to refine our ideas from a global perspective. The experience has motivated me to continue pursuing innovation that can create meaningful impact beyond borders."
The 2026 GESS program has been organized for the fifth consecutive year by the Office of Global Initiative in collaboration with the Impact MBA program and the Startup KAIST. KAIST will continue strengthening partnerships with Silicon Valley and other global innovation hubs to nurture entrepreneurial talent capable of leading future industries worldwide.
2026.07.06 View 400 -
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 912 -
KAIST Identifies Hidden Age Bias in Artificial Intelligence
Do responses generated by artificial intelligence systems such as ChatGPT reflect social prejudice? A KAIST research team has quantitatively analyzed and identified age-related stereotypes embedded in the responses of generative artificial intelligence. The study sheds light on the potential impact of hidden AI biases on social perceptions and suggests directions for the development of more inclusive AI.
KAIST, led by President Kwang Hyung Lee, announced on the 28th that a research team led by Professor Moon Choi of the Graduate School of Science and Technology Policy quantitatively analyzed subtle stereotypes about older adults embedded in sentences generated by OpenAI’s generative AI model ChatGPT-4o.
Generative AI is now widely used in everyday information search and decision-making processes, but concerns have also been raised that it may reproduce social biases contained in its training data. While previous studies have primarily focused on biases related to gender or race, this study, conducted by Ph.D. student Wan Hong as the first author, is significant in that it examined ageism from the perspective of artificial intelligence at a time when the issue is becoming increasingly important amid global population aging. Ageism refers to discrimination against, or negative perceptions of, certain groups based on age.
The research team collected 900 text samples generated by GPT-4o using neutral prompts that asked the model to describe the characteristics of age groups from 10 to 90 in 10-year intervals. The team then analyzed the responses using the Stereotype Content Model, a major theory in social psychology that explains perceptions of people or groups along two dimensions: warmth and competence.
The analysis found that older adults, defined as those aged 60 and above, received high scores for “warmth,” a trait associated with kindness, trustworthiness, and consideration. However, their scores for “competence,” which refers to ability, expertise, and efficiency, tended to be relatively lower than those of younger age groups.
The generated responses also tended to portray the human life course as divided into three groups: youth, covering those in their teens and 20s; middle age, covering those in their 30s to 50s; and older adulthood, covering those in their 60s and above. In particular, descriptions of people aged 70 and older repeatedly showed relatively uniform characteristics.
The research team also focused on “assertiveness,” which refers to the tendency to actively express one’s opinions and act with confidence and initiative. The analysis showed that the frequency of expressions related to assertiveness decreased as age increased. This suggests that ChatGPT-4o tends to portray older adults as wise and caring, while representing their agency and active capacities as relatively lower.
This study is significant because it quantitatively identified subtle biases embedded in generative AI by combining social science theory with computational analysis techniques. The findings show that generative AI tends to portray older adults as a “warm but less competent” group, a pattern similar to typical stereotypes of older adults repeatedly found in mass media.
This study is significant because it quantitatively identified subtle biases embedded in generative AI by combining social science theory with computational analysis techniques. The findings show that generative AI tends to portray older adults as a “warm but less competent” group, a pattern similar to typical stereotypes of older adults repeatedly found in mass media.
“Bias in AI is not merely a technological issue, but a social one,” said Professor Moon Choi. “To build inclusive artificial intelligence, people from diverse generations must participate in the development process.”
The study was conducted with Ph.D. student Wan Hong of the Graduate School of Science and Technology Policy as the first author. The findings were published in the February 2026 special issue of The Gerontologist, a leading international journal in the field of gerontology with an impact factor of 5.7.
※ Paper title: “An Exploratory Semantic Analysis of Age-Related Stereotypes in OpenAI’s GPT-4o Model”
※ DOI: https://doi.org/10.1093/geront/gnaf291
This research was supported by the National Research Foundation of Korea through the Mid-Career Research Program for Convergence between Science and Technology and the Humanities and Social Sciences.
※ Research team homepage: https://aging.kaist.ac.kr
2026.07.01 View 428 -
KAIST Begins Developing the World’s First Brain-to-Robot Technology, Moving Robots by Thought and Sending Sensation Back to the Brain
KAIST researchers have begun developing a next-generation brain-robot interface platform that uses human brain signals to control an exoskeleton in real time and sends the tactile and force information sensed by the robot back to the brain.
KAIST, led by President Kwang-Hyung Lee, announced on the 25th that research teams led by Professors Kyoungchul Kong and Jung Kim of its Department of Mechanical Engineering, together with Angel Robotics Co., Ltd., have launched the world’s first bidirectional “Brain-to-Robot” system as a flagship initiative of the Korea Medical Device Development Fund (KMDF). The project runs from April 2026 to December 2032.
Professor Kyoungchul Kong is a world-renowned wearable-robotics researcher who founded Angel Robotics, a developer of walking-assist exoskeletons, and led his team to back-to-back gold medals at Cybathlon, the international competition for assistive technologies for people with disabilities. Professor Jung Kim is a globally recognized researcher who received the Scientist and Engineer of the Month Award for his work on robotic skin. Together, the two teams have formed a consortium to develop a Brain-to-Robot platform that merges neural interfaces with exoskeleton robotics.
Brain interface technologies that let users move a cursor or operate a smartphone with brain signals have already reached the stage of human clinical trials, and U.S. companies such as Neuralink and Synchron are accelerating their development. Existing approaches, however, have struggled to link actual movement and sensory feedback at the same time. They have also concentrated largely on advancing signal decoding itself, without clearly defining the target of control, namely what the brain signals actually drive and what kind of sensory information is returned.
Brain-to-Robot is designed to overcome these limitations head-on. It sets the exoskeleton itself as the control target: brain signals read the user’s movement intentions to drive the robot, and at the same time the robot’s sensory readings are delivered back to the brain. These readings include ground reaction force (the force the floor exerts on the foot), joint torque (rotational force at the joints), and tactile information. The aim is a complete bidirectional interface.
According to the research team, no fully bidirectional Brain-to-Robot system that combines exoskeleton control with sensory feedback has yet been reported anywhere in the world, and the project is expected to mark a turning point in brain interface technology.
Within this system, the KAIST teams are responsible for the core technologies. Professor Kong’s team will develop wearable-robot control and AI-based interpretation of movement intention, and will design a somatosensory interface, a system for transmitting bodily sensory information, that delivers the robot’s sensory data accurately to the Brain Chip, the semiconductor that processes brain signals.
Professor Kim’s team will develop robotic skin that senses in place of impaired sensation for people with disabilities, along with AI-based interpretation of somatosensory information.
The teams will also develop AI-based encoding and decoding algorithms that turn brain signals into robot commands and send the robot’s sensory information back to the brain. A key challenge is processing hundreds of channels of cortical signals, the neural signals generated in the cerebral cortex, while stably maintaining an ultra-low-latency closed loop, a control cycle in which signals are exchanged continuously in real time.
Commercialization of the flagship project will be led by Angel Robotics (KOSDAQ: 455900), the company founded by Professor Kong. The team plans to pursue full-cycle commercialization, from regulatory approval by the Ministry of Food and Drug Safety through to real-world deployment.
“If this technology succeeds, it will open a new rehabilitation paradigm in which people with quadriplegia can move beyond the hospital to walk on their own, pick up objects, and even feel sensation at their fingertips in everyday life,” Professor Kong said.
The research team stressed that, because this is an unprecedented and highly complex convergence technology never attempted at home or abroad, long-term safety, clinical validation, and a regulatory approval framework must advance in parallel with the technology itself. To reach the global market, they added, safety and efficacy testing, the accumulation of clinical evidence, a risk-management system, protection of brain-signal data, cybersecurity, and ethical review must all be addressed in an integrated way.
Meanwhile, KAIST is conducting a wide range of fundamental research in the field of brain interfaces. A research team led by Professor Hyung-Soon Park of the Department of Mechanical Engineering is studying wearable rehabilitation robot technologies based on neural intention-recognition interfaces, which identify users’ movement intentions from brain signals, for the effective treatment of neurological disorders. A research team led by Professor Sungho Cho of the School of Computing is developing AI-based brain-signal interpretation technologies.
A research team led by Professor Jihoon Lee of the Department of Brain and Cognitive Sciences is conducting next-generation brain–machine interface research focused on ultra-low-power bio/neural interface circuits, which connect and process biological and neural signals with low power consumption; wireless neural signal measurement technologies, which measure neural signals without wires; and on-device AI-based closed-loop neuromodulation technologies, which use cyclical control structures to exchange signals in real time.
In addition, a research team led by Professor Hyunjoo Lee of the School of Electrical Engineering is conducting research on high-resolution neural signal measurement and precision brain stimulation based on ultra-miniaturized multimodal neural electrodes, which can simultaneously measure and stimulate multiple types of neural signals. A research team led by Professor Minkyu Je of the Department of AI Semiconductor Systems is studying AI-based semiconductor integrated circuits and system technologies for next-generation neural interfaces. A research team led by Professor Jae-Woong Jeong of the School of Electrical Engineering is conducting research on high-precision brain-signal measurement, which precisely measures neural signals generated in the brain, and neuroengineering based on neural stimulation.
“This Brain-to-Robot flagship project is a world-class, highly challenging convergence research initiative led by the teams of Professors Kyoungchul Kong and Jung Kim,” said KAIST President Kwang-Hyung Lee. “KAIST has a wide range of researchers studying fundamental technologies in brain interfaces, AI, semiconductors, and robotics, and based on this foundation, we will lead innovation in next-generation Brain-to-Robot technologies.”
2026.06.25 View 1224 -
KAIST Illuminates the Eyes of Humanoid Robots with Minimal Memory
<CVPR 2026 poster session. From left to right: Minseok Seo (KAIST, first author), Mark Hamilton (MIT and Microsoft, second author), and Prof. Changick Kim (KAIST, corresponding author)>
From facial recognition on smartphones to humanoid robots, computer vision technology, which serves as the eyes of artificial intelligence (AI), is widely utilized in our daily lives. A joint research team from KAIST and international institutions has developed a technology that allows AI to see the world more clearly with minimal memory, increasing GPU (Graphics Processing Unit) memory efficiency by up to 16 times. This achievement is evaluated as a core technology that will accelerate the era of humanoid robots and on-device AI.
<Overview of Upsample Anything. Given a high-resolution image, it is first downsampled to a low-resolution image and then reconstructed through test-time optimization (TTO). During this process, pixel-wise anisotropic kernel parameters are learned. The learned kernels are subsequently applied to low-resolution foundation feature maps to generate high-resolution feature maps. These feature maps are then used to perform pixel-wise anisotropic Joint Bilateral Upsampling, enabling high-quality reconstruction at high resolution>
KAIST announced on June 17th that a research team led by Professor Changick Kim from the School of Electrical Engineering, through joint research with researchers from MIT and Microsoft in the United States, has developed 'Upsample Anything,' a universal technology that can enhance the visual performance of AI even with limited GPU memory.
Following its acceptance to 'CVPR 2026,' the world's most prestigious conference in the field of artificial intelligence and computer vision, this achievement was awarded the 'CVPR Compute Gold Star' in recognition of its efficient utilization of computational resources. It was also selected as the 'Transparency Champion,' ranking first overall in the category of research process transparency and reproducibility. This is an accomplishment that widely recognizes the core elements of responsible AI research, including research performance, computational resources used, code disclosure, and experimental reproducibility.
Recently, humanoid robots, autonomous driving systems, and AI based on world models (AI models that learn and predict the physical environment and changes of the real world) have been compressing input images into low-resolution features (core information extracted from images by AI) to increase computational speed and reduce memory usage.
However, during the compression process, a problem occurs where important visual information, such as small objects, thin structures, and minute defects, is lost. Conversely, processing all images at high resolution from the beginning requires massive GPU memory and computational resources, making real-time processing difficult. This has remained an unresolved challenge for a long time in situations where small devices like smartphones or robots, where mobility is crucial, must precisely perceive their surrounding environment.
To overcome these limitations, the research team developed a training-free (requiring no additional data training) upsampling technology that restores low-resolution feature information into high resolution by utilizing the edge and structural information of the input image.
Existing technologies required a separate retraining or complex optimization process to be applied to new environments or data. In contrast, 'Upsample Anything' developed by the research team can find the optimal restoration method using just a single input image, allowing it to be immediately applied to various environments.
In addition, by compressing and utilizing only core information instead of storing and processing all visual information at high resolution, GPU memory usage was significantly reduced. Based on a 224×224 size image (approximately 50,000 pixels) widely used in AI research, the research team restored visual information close to the original with a short calculation of about 0.4 seconds, achieving a performance that improves GPU memory efficiency by up to 16 times.
This means that artificial intelligence can perceive its surrounding environment more precisely even with limited computational resources. Therefore, this technology is expected to be widely used in various next-generation artificial intelligence fields, such as small devices like smartphones, as well as humanoid robots that need to accurately identify and manipulate small objects, autonomous driving systems, and on-device AI.
<Comparison image illustrating the performance gap with conventional methods (AI-generated). Conventional vision foundation models understand a scene by converting the input image into low-resolution features at a small patch level (left). Upsample Anything restores these low-resolution features to the original resolution level, enabling the AI to comprehend the scene's structure and boundaries with significantly higher precision (right)>
Professor Changick Kim said, “This technology is an algorithm that can significantly increase the visual precision of artificial intelligence with fewer resources, and it is expected to accelerate the commercialization of humanoid robots and on-device AI.” He added, “It is even more meaningful because it was recognized at CVPR not only for its performance but also for its computational efficiency and research transparency.”
This research was participated in by KAIST PhD student Minseok Seo as the first author, and this achievement was presented on June 7 at 'CVPR 2026,' the world's most prestigious conference in the field of artificial intelligence and computer vision.
※ Paper Title: Upsample Anything: A Simple and Hard to Beat Baseline for Feature Upsampling, DOI:10.48550/arXiv.2511.16301
※ Author Information: Minseok Seo (KAIST, First Author), Mark Hamilton (MIT, Microsoft, Second Author), Changick Kim (KAIST, Corresponding Author)
2026.06.17 View 1743 -
Seeking Innovative Financial Solutions to Help Deep Tech Startups Overcome the Valley of Death
KAIST announced on June 16 that it will co-host 'STARTUP NATION KOREA 2026' (2026 Innovation Entrepreneurship Nation Korea International Forum) with Seoul National University and The JoongAng from June 17 to 18 at the Haedong Advanced Engineering Building on Seoul National University's Gwanak Campus.
Celebrating its 5th anniversary this year, the forum serves as a platform to overcome the so-called 'R&D Paradox'—where outstanding research and development achievements fail to fully connect with entrepreneurship and industry—and to seek solutions for realizing a science and technology-based innovation entrepreneurship nation. Universities, government agencies, research institutions, investment firms, conglomerates, startups, and media will participate to discuss cooperative methods for connecting technological potential to market and industrial value.
In particular, this year's forum focuses on the role of patient capital and innovative finance, which are critical challenges for the growth of deep tech startups, under the theme “Deep Tech: Beyond the Valley of Death.”
Deep tech startups require long-term investment and large-scale funding throughout the entire process from research and development to technology verification, demonstration, and market entry. However, the domestic venture investment market is relatively focused on short-term returns, often causing these startups to face severe difficulties during the commercialization phase. Therefore, this forum will intensively discuss strategies to establish an innovative financial ecosystem where 'patient capital'—which invests based on the long-term growth potential of technology—is organically linked with investments, guarantees, and policy finance required for the entire life cycle of technology commercialization.
Kwang Hyung Lee, President of KAIST, said, “Although Korea possesses world-class R&D capabilities, major barriers still exist in the process of translating research achievements into startups and new industries. I hope this forum serves as a collective effort to seek solutions through patient capital, innovative finance, and a sustainable entrepreneurial ecosystem so that deep tech startups can overcome the valley of death and grow into the global market.”
Hyun Min Bae, Director of the KAIST Startup Institute, stated, “The success of deep tech entrepreneurship cannot be achieved through technology alone. Through this forum, we look forward to discussing the growth ladders and collaborative measures that connect laboratory technologies to markets, investments, and global expansion, thereby discovering a new direction for Korea's deep tech startup ecosystem.”
On the first day of the forum, Professor Jeong Dong Lee of the College of Engineering at Seoul National University, author of The Way of Accumulation and The First Question, will deliver a keynote speech emphasizing the role of finance in accelerating technological innovation and the importance of patient capital. This will be followed by a roundtable featuring domestic and international experts to discuss long-term investment case studies and policy directions for innovative finance.
In addition, the presentation ceremony for the '2026 Korea Innovation Entrepreneurship Awards' will be held simultaneously. This year, a total of 13 awards will be presented across three categories: the Innovation Entrepreneurship Award, the Innovation Entrepreneurship Challenge Award, and the Innovation Entrepreneurship Ecosystem Contribution Award.
The recipients of the Innovation Entrepreneurship Award include Sovagen, EndoRobotics, WIRobotics, Exo Systems, Marine Drone Tech, Daughter, MUSTBIO, IMNEWRUN, and Narnia Labs. These companies are promising deep tech enterprises recognized for their technological innovation and growth potential in national strategic sectors such as AI, robotics, bio/healthcare, drones, and mobility.
The Innovation Entrepreneurship Challenge Award will be presented to Scionic AI, RX, and TDS Innovation, while the Innovation Entrepreneurship Ecosystem Contribution Award will be awarded to the Commercialization Promotion Agency for R&D Outcomes (COMPA).
Kyeong Hwan Kim, Chair of the Evaluation Committee (Dean of the Graduate School of Global Entrepreneurship at Sungkyunkwan University), remarked, “Promising deep tech companies that will lead future industries in fields like AI, robotics, semiconductors, and bio have stood out remarkably. This contest was a meaningful opportunity to confirm the robust growth potential of Korea's innovation entrepreneurship ecosystem.”
An exhibition featuring innovative startups and various programs linked with government ministries will also run throughout the event. Participating companies will showcase their breakthrough technologies in sectors including AI, robotics, bio/healthcare, advanced materials, energy, and mobility, while exploring collaboration opportunities with investment institutions and industry leaders. Notably, WIRobotics plans to exhibit its humanoid robot 'ALLEX', which was previously unveiled at CES 2026.
The forum is co-hosted by KAIST, Seoul National University, and The JoongAng, and sponsored by major agencies including the Ministry of Science and ICT, the Ministry of Trade, Industry and Energy, and the Ministry of SMEs and Startups. The event will be broadcast live via the official YouTube channel and website of STARTUP NATION KOREA 2026.
2026.06.16 View 1936 -
KAIST Breaks a Major AI Bottleneck with Liquid Cooling Technology 10 Times More Efficient Than the Previous Record
<(From Left) Professor Sung Jin Kim, Professor Ikjin Lee, Dr. Yong Jin Lee, Ph.D candidate Hansol Lee, Ph.D candidate ChulHyun Hwang>
AI data centers are often described as “power-hungry giants.” Not only do artificial intelligence computations consume enormous amounts of electricity, but a significant amount of energy is also required to cool the semiconductor chips that heat up during operation. As AI chips continue to deliver higher performance, the amount of heat they generate is increasing rapidly. As a result, conventional air cooling and external copper heat spreaders are approaching their practical limits. To address this challenge, KAIST research team has developed an ultra-high-efficiency liquid-cooling technology that cools semiconductor chips from within.
KAIST (President Kwang Hyung Lee) announced on the 16th that a joint research team led by Professor Sung Jin Kim of the Department of Mechanical Engineering and Professor Ikjin Lee of the School of AI and Computing has developed a highly efficient liquid-cooling technology that directly cools high-heat-flux semiconductor chips using room-temperature water. The researchers achieved this by embedding liquid-cooling channels, thinner than a human hair, directly inside a silicon semiconductor chip. The team successfully maintained the chip temperature below 100°C even under extreme heat-generation conditions exceeding 2,000 watts per square centimeter (W/cm²).
<Manifold Microchannel Cooling Device Structure for Cooling High-Heat-Generation Semiconductor Chips>
The researchers focused on a Manifold MicroChannel (MMC hereafter) structure embedded directly inside a silicon chip. Microchannel cooling removes heat through microscopic fluid channels that are smaller than a human hair. In conventional designs, coolant must travel through numerous microchannels from one end of the chip to the other. This long flow path increases flow resistance and requires greater pumping power to circulate the coolant.
The manifold structure developed by the research team distributes coolant through multiple inlet channels and collects it through multiple outlets. An analogy can be drawn to a logistics network: instead of shipping all goods from a single origin to a distant destination, multiple distribution centers are strategically placed to shorten transportation distances. Because the coolant travels only a short distance within each channel, flow resistance is significantly reduced, and the required pumping pressure becomes much lower.
Previous MMC designs often suffered from uneven coolant distribution, with some channels receiving too much coolant while others received too little. The research team overcame this challenge by optimizing the structure so that coolant could flow evenly through all microchannels. Through extensive design analysis and advanced simulations, they identified an optimized cooling architecture that delivers high cooling performance while minimizing energy loss.
The optimized structure was then fabricated in an actual silicon semiconductor chip and experimentally validated. Under the same temperature-rise condition, the cooling system achieved a coefficient of performance (COP) of 106,000. This is approximately ten times higher than the previous world-leading result of around 10,000 reported in Nature (van Erp et al.) in 2020. In practical terms, it means that only about one-tenth of the pumping power is required to remove the same amount of heat.
Notably, this performance was achieved without relying on phase-change cooling, nanoscale surface modifications, or expensive materials such as diamond. Ordinary room-temperature water was used as the coolant. In addition, the device was fabricated using a low-temperature process below 350°C that is compatible with conventional semiconductor manufacturing. This means the technology could be implemented in existing semiconductor foundries without requiring major additional equipment investments.
<Fabricated Cooling Device, Experimental Results, and Applications>
The technology is expected to help address thermal management challenges in a wide range of high-heat-flux electronic systems, including AI accelerators, high-performance computing (HPC) systems, three-dimensional semiconductor packaging, power electronics, and defense electronics. In particular, data centers are increasingly constrained not only by computing performance but also by cooling power consumption and cooling infrastructure requirements. Technologies that reduce pumping power at the chip level could therefore play an important role in improving the energy efficiency of next-generation data centers and alleviating thermal bottlenecks.
<Research Image(AI-generated)>
Professor Sung Jin Kim said, “As the performance of AI semiconductors and advanced electronic packaging becomes increasingly limited by heat, we expect this technology to serve as a foundational cooling solution for future high-performance computing systems.”
The study was co-first-authored by Young Jin Lee, ChulHyun Hwang, and Hansol Lee from the Department of Mechanical Engineering at KAIST. The research was published on June 15 in the international journal Energy Conversion and Management.
Paper title: Highly energy-efficient manifold microchannel for cooling electronics with a coefficient of performance over 100,000
DOI: 10.1016/j.enconman.2026.121422
This research was supported by the Mid-Career Researcher Program of the National Research Foundation of Korea (NRF), funded by the Ministry of Science and ICT (Grant No. 2021R1A2C3011944), and by the Specialized Research Laboratory Program for Ultra-High-Heat-Flux Cooling Systems of the Korea Research Institute for Defense Technology Planning and Advancement (KRIT), funded by the Defense Acquisition Program Administration (Grant No. KRIT-CT-22-022).
2026.06.16 View 2767