Kaist

KAIST Succeeds in Real-Time Carbon Dioxide Monitor..

  < (From left) Master's Student Gyurim Jang, Professor Kyeongha Kwon >   KAIST (President Kwang Hyung Lee) announced on June 9th that a research team led by Professor Kyeongha Kwon from the School of Electrical Engineering, in a joint study with Professor Hanjun Ryu's team at Chung-Ang University, has developed a self-powered wireless carbon dioxide (CO2) monitoring system. This innovative system harvests fine vibrational energy from its surroundings to periodically measure CO2 concentrations.   This breakthrough addresses a critical need in environmental monitoring: accurately understanding "how much" CO2 is being emitted to combat climate change and global warming. While CO2 monitoring technology is key to this, existing systems largely rely on batteries or wired power system, imposing limitations on installation and maintenance. The KAIST team tackled this by creating a self-powered wireless system that operates without external power.   The core of this new system is an "Inertia-driven Triboelectric Nanogenerator (TENG)" that converts vibrations (with amplitudes ranging from 20-4000 ㎛ and frequencies from 0-300 Hz) generated by industrial equipment or pipelines into electricity. This enables periodic CO2 concentration measurements and wireless transmission without the need for batteries.       < Figure 1. Concept and configuration of self-powered wireless CO2 monitoring system using fine vibration harvesting (a) System block diagram (b) Photo of fabricated system prototype >   The research team successfully amplified fine vibrations and induced resonance by combining spring-attached 4-stack TENGs. They achieved stable power production of 0.5 mW under conditions of 13 Hz and 0.56 g acceleration. The generated power was then used to operate a CO2 sensor and a Bluetooth Low Energy (BLE) system-on-a-chip (SoC).   Professor Kyeongha Kwon emphasized, "For efficient environmental monitoring, a system that can operate continuously without power limitations is essential." She explained, "In this research, we implemented a self-powered system that can periodically measure and wirelessly transmit CO2 concentrations based on the energy generated from an inertia-driven TENG." She added, "This technology can serve as a foundational technology for future self-powered environmental monitoring platforms integrating various sensors."       < Figure 2. TENG energy harvesting-based wireless CO2 sensing system operation results (c) Experimental setup (d) Measured CO2 concentration results powered by TENG and conventional DC power source >   This research was published on June 1st in the internationally renowned academic journal ＇Nano Energy (IF 16.8)＇. Gyurim Jang, a master's student at KAIST, and Daniel Manaye Tiruneh, a master's student at Chung-Ang University, are the co-first authors of the paper.   ＊Paper Title: Highly compact inertia-driven triboelectric nanogenerator for self-powered wireless CO2 monitoring via fine-vibration harvesting   ＊DOI: 10.1016/j.nanoen.2025.110872   This research was supported by the Saudi Aramco-KAIST CO2 Management Center.

KAIST Professor Jee-Hwan Ryu Receives Global IEEE ..

- Professor Jee-Hwan Ryu of Civil and Environmental Engineering receives the Best Paper Award from the Institute of Electrical and Electronics Engineers (IEEE) Robotics Journal, officially presented at ICRA, a world-renowned robotics conference.   - This is the highest level of international recognition, awarded to only the top 5 papers out of approximately 1,500 published in 2024.   - Securing a new working channel technology for soft growing robots expands the practicality and application possibilities in the field of soft robotics.       < Professor Jee-Hwan Ryu (left), Nam Gyun Kim, Ph.D. Candidate (right) from the KAIST Department of Civil and Environmental Engineering and KAIST Robotics Program >   KAIST (President Kwang-Hyung Lee) announced on the 6th that Professor Jee-Hwan Ryu from the Department of Civil and Environmental Engineering received the 2024 Best Paper Award from the Robotics and Automation Letters (RA-L), a premier journal under the IEEE, at the '2025 IEEE International Conference on Robotics and Automation (ICRA)' held in Atlanta, USA, on May 22nd.   This Best Paper Award is a prestigious honor presented to only the top 5 papers out of approximately 1,500 published in 2024, boasting high international competition and authority.   The award-winning paper by Professor Ryu proposes a novel working channel securing mechanism that significantly expands the practicality and application possibilities of 'Soft Growing Robots,' which are based on soft materials that move or perform tasks through a growing motion similar to plant roots.       < IEEE Robotics Journal Award Ceremony >   Existing soft growing robots move by inflating or contracting their bodies through increasing or decreasing internal pressure, which can lead to blockages in their internal passages. In contrast, the newly developed soft growing robot achieves a growing function while maintaining the internal passage pressure equal to the external atmospheric pressure, thereby successfully securing an internal passage while retaining the robot's flexible and soft characteristics.   This structure allows various materials or tools to be freely delivered through the internal passage (working channel) within the robot and offers the advantage of performing multi-purpose tasks by flexibly replacing equipment according to the working environment.   The research team fabricated a prototype to prove the effectiveness of this technology and verified its performance through various experiments. Specifically, in the slide plate experiment, they confirmed whether materials or equipment could pass through the robot's internal channel without obstruction, and in the pipe pulling experiment, they verified if a long pipe-shaped tool could be pulled through the internal channel.       < Figure 1. Overall hardware structure of the proposed soft growing robot (left) and a cross-sectional view composing the inflatable structure (right) >   Experimental results demonstrated that the internal channel remained stable even while the robot was growing, serving as a key basis for supporting the technology's practicality and scalability.   Professor Jee-Hwan Ryu stated, "This award is very meaningful as it signifies the global recognition of Korea's robotics technology and academic achievements. Especially, it holds great significance in achieving technical progress that can greatly expand the practicality and application fields of soft growing robots. This achievement was possible thanks to the dedication and collaboration of the research team, and I will continue to contribute to the development of robotics technology through innovative research."       < Figure 2. Material supplying mechanism of the Soft Growing Robot >   This research was co-authored by Dongoh Seo, Ph.D. Candidate in Civil and Environmental Engineering, and Nam Gyun Kim, Ph.D. Candidate in Robotics. It was published in IEEE Robotics and Automation Letters on September 1, 2024.   (Paper Title: Inflatable-Structure-Based Working-Channel Securing Mechanism for Soft Growing Robots, DOI: 10.1109/LRA.2024.3426322)   This project was supported simultaneously by the National Research Foundation of Korea's Future Promising Convergence Technology Pioneer Research Project and Mid-career Researcher Project.

KAIST Introduces ‘Virtual Teaching Assistant’ That..

- Research teams led by Prof. Yoonjae Choi (Kim Jaechul Graduate School of AI) and Prof. Hwajeong Hong (Department of Industrial Design) at KAIST developed a Virtual Teaching Assistant (VTA) to support learning and class operations for a course with 477 students.   - The VTA responds 24/7 to students’ questions related to theory and practice by referencing lecture slides, coding assignments, and lecture videos.   - The system’s source code has been released to support future development of personalized learning support systems and their application in educational settings.       < Photo 1. (From left) PhD candidate Sunjun Kweon, Master's candidate Sooyohn Nam, PhD candidate Hyunseung Lim, Professor Hwajung Hong, Professor Yoonjae Choi >   “At first, I didn’t have high expectations for the Virtual Teaching Assistant (VTA), but it turned out to be extremely helpful—especially when I had sudden questions late at night, I could get immediate answers,” said Jiwon Yang, a Ph.D. student at KAIST. “I was also able to ask questions I would’ve hesitated to bring up with a human TA, which led me to ask even more and ultimately improved my understanding of the course.”   KAIST (President Kwang Hyung Lee) announced on June 5th that a joint research team led by Prof. Yoonjae Choi of the Kim Jaechul Graduate School of AI and Prof. Hwajeong Hong of the Department of Industrial Design has successfully developed and deployed a Virtual Teaching Assistant (VTA) that provides personalized feedback to individual students even in large-scale classes.   This study marks one of the first large-scale, real-world deployments in Korea, where the VTA was introduced in the “Programming for Artificial Intelligence” course at the KAIST Kim Jaechul Graduate School of AI, taken by 477 master’s and Ph.D. students during the Fall 2024 semester, to evaluate its effectiveness and practical applicability in an actual educational setting.   The AI teaching assistant developed in this study is a course-specialized agent, distinct from general-purpose tools like ChatGPT or conventional chatbots. The research team implemented a Retrieval-Augmented Generation (RAG) architecture, which automatically vectorizes a large volume of course materials—including lecture slides, coding assignments, and video lectures—and uses them as the basis for answering students’ questions.       < Photo 2. Teaching Assistant demonstrating to the student how the Virtual Teaching Assistant works>   When a student asks a question, the system searches for the most relevant course materials in real time based on the context of the query, and then generates a response. This process is not merely a simple call to a large language model (LLM), but rather a material-grounded question answering system tailored to the course content—ensuring both high reliability and accuracy in learning support.   Sunjun Kweon, the first author of the study and head teaching assistant for the course, explained, “Previously, TAs were overwhelmed with repetitive and basic questions—such as concepts already covered in class or simple definitions—which made it difficult to focus on more meaningful inquiries.” He added, “After introducing the VTA, students began to reduce repeated questions and focus on more essential ones. As a result, the burden on TAs was significantly reduced, allowing us to concentrate on providing more advanced learning support.”   In fact, compared to the previous year’s course, the number of questions that required direct responses from human TAs decreased by approximately 40％.       < Photo 3. A student working with VTA. >   The VTA, which was operated over a 14-week period, was actively used by more than half of the enrolled students, with a total of 3,869 Q&A interactions recorded. Notably, students without a background in AI or with limited prior knowledge tended to use the VTA more frequently, indicating that the system provided practical support as a learning aid, especially for those who needed it most.   The analysis also showed that students tended to ask the VTA more frequently about theoretical concepts than they did with human TAs. This suggests that the AI teaching assistant created an environment where students felt free to ask questions without fear of judgment or discomfort, thereby encouraging more active engagement in the learning process.   According to surveys conducted before, during, and after the course, students reported increased trust, response relevance, and comfort with the VTA over time. In particular, students who had previously hesitated to ask human TAs questions showed higher levels of satisfaction when interacting with the AI teaching assistant.       < Figure 1. Internal structure of the AI Teaching Assistant (VTA) applied in this course. It follows a Retrieval-Augmented Generation (RAG) structure that builds a vector database from course materials (PDFs, recorded lectures, coding practice materials, etc.), searches for relevant documents based on student questions and conversation history, and then generates responses based on them. >   Professor Yoonjae Choi, the lead instructor of the course and principal investigator of the study, stated, “The significance of this research lies in demonstrating that AI technology can provide practical support to both students and instructors. We hope to see this technology expanded to a wider range of courses in the future.”   The research team has released the system’s source code on GitHub, enabling other educational institutions and researchers to develop their own customized learning support systems and apply them in real-world classroom settings.       < Figure 2. Initial screen of the AI Teaching Assistant (VTA) introduced in the "Programming for AI" course. It asks for student ID input along with simple guidelines, a mechanism to ensure that only registered students can use it, blocking indiscriminate external access and ensuring limited use based on students. >     The related paper, titled “A Large-Scale Real-World Evaluation of an LLM-Based Virtual Teaching Assistant,” was accepted on May 9, 2025, to the Industry Track of ACL 2025, one of the most prestigious international conferences in the field of Natural Language Processing (NLP), recognizing the excellence of the research.       < Figure 3. Example conversation with the AI Teaching Assistant (VTA). When a student inputs a class-related question, the system internally searches for relevant class materials and then generates an answer based on them. In this way, VTA provides learning support by reflecting class content in context. >   This research was conducted with the support of the KAIST Center for Teaching and Learning Innovation, the National Research Foundation of Korea, and the National IT Industry Promotion Agency.

KAIST Research Team Develops Electronic Ink for Ro..

A team of researchers from KAIST and Seoul National University has developed a groundbreaking electronic ink that enables room-temperature printing of variable-stiffness circuits capable of switching between rigid and soft modes. This advancement marks a significant leap toward next-generation wearable, implantable, and robotic devices.       < Photo 1. (From left) Professor Jae-Woong Jeong and PhD candidate Simok Lee of the School of Electrical Engineering, (in separate bubbles, from left) Professor Gun-Hee Lee of Pusan ​​National University, Professor Seongjun Park of Seoul National University, Professor Steve Park of the Department of Materials Science and Engineering>   Variable-stiffness electronics are at the forefront of adaptive technology, offering the ability for a single device to transition between rigid and soft modes depending on its use case. Gallium, a metal known for its high rigidity contrast between solid and liquid states, is a promising candidate for such applications. However, its use has been hindered by challenges including high surface tension, low viscosity, and undesirable phase transitions during manufacturing.   On June 4th, a research team led by Professor Jae-Woong Jeong from the School of Electrical Engineering at KAIST, Professor Seongjun Park from the Digital Healthcare Major at Seoul National University, and Professor Steve Park from the Department of Materials Science and Engineering at KAIST introduced a novel liquid metal electronic ink. This ink allows for micro-scale circuit printing – thinner than a human hair – at room temperature, with the ability to reversibly switch between rigid and soft modes depending on temperature.   The new ink combines printable viscosity with excellent electrical conductivity, enabling the creation of complex, high-resolution multilayer circuits comparable to commercial printed circuit boards (PCBs). These circuits can dynamically change stiffness in response to temperature, presenting new opportunities for multifunctional electronics, medical technologies, and robotics.   Conventional electronics typically have fixed form factors – either rigid for durability or soft for wearability. Rigid devices like smartphones and laptops offer robust performance but are uncomfortable when worn, while soft electronics are more comfortable but lack precise handling. As demand grows for devices that can adapt their stiffness to context, variable-stiffness electronics are becoming increasingly important.       < Figure 1. Fabrication process of stable, high-viscosity electronic ink by dispersing micro-sized gallium particles in a polymer matrix (left). High-resolution large-area circuit printing process through pH-controlled chemical sintering (right). >   To address this challenge, the researchers focused on gallium, which melts just below body temperature. Solid gallium is quite stiff, while its liquid form is fluid and soft. Despite its potential, gallium’s use in electronic printing has been limited by its high surface tension and instability when melted.   To overcome these issues, the team developed a pH-controlled liquid metal ink printing process. By dispersing micro-sized gallium particles into a hydrophilic polyurethane matrix using a neutral solvent (dimethyl sulfoxide, or DMSO), they created a stable, high-viscosity ink suitable for precision printing. During post-print heating, the DMSO decomposes to form an acidic environment, which removes the oxide layer on the gallium particles. This triggers the particles to coalesce into electrically conductive networks with tunable mechanical properties.   The resulting printed circuits exhibit fine feature sizes (~50 μm), high conductivity (2.27 × 10⁶ S/m), and a stiffness modulation ratio of up to 1,465 – allowing the material to shift from plastic-like rigidity to rubber-like softness. Furthermore, the ink is compatible with conventional printing techniques such as screen printing and dip coating, supporting large-area and 3D device fabrication.       < Figure 2. Key features of the electronic ink. (i) High-resolution printing and multilayer integration capability. (ii) Batch fabrication capability through large-area screen printing. (iii) Complex three-dimensional structure printing capability through dip coating. (iv) Excellent electrical conductivity and stiffness control capability.>   The team demonstrated this technology by developing a multi-functional device that operates as a rigid portable electronic under normal conditions but transforms into a soft wearable healthcare device when attached to the body. They also created a neural probe that remains stiff during surgical insertion for accurate positioning but softens once inside brain tissue to reduce inflammation – highlighting its potential for biomedical implants.       < Figure 3. Variable stiffness wearable electronics with high-resolution circuits and multilayer structure comparable to commercial printed circuit boards (PCBs). Functions as a rigid portable electronic device at room temperature, then transforms into a wearable healthcare device by softening at body temperature upon skin contact.>   “The core achievement of this research lies in overcoming the longstanding challenges of liquid metal printing through our innovative technology,” said Professor Jeong. “By controlling the ink’s acidity, we were able to electrically and mechanically connect printed gallium particles, enabling the room-temperature fabrication of high-resolution, large-area circuits with tunable stiffness. This opens up new possibilities for future personal electronics, medical devices, and robotics.”       < Figure 4. Body-temperature softening neural probe implemented by coating electronic ink on an optical waveguide structure. (Left) Remains rigid during surgery for precise manipulation and brain insertion, then softens after implantation to minimize mechanical stress on the brain and greatly enhance biocompatibility. (Right) >   This research was published in Science Advances under the title, “Phase-Change Metal Ink with pH-Controlled Chemical Sintering for Versatile and Scalable Fabrication of Variable Stiffness Electronics.” The work was supported by the National Research Foundation of Korea, the Boston-Korea Project, and the BK21 FOUR Program.

RAIBO Runs over Walls with Feline Agility... Ready..

  < Photo 1. Research Team Photo (Professor Jemin Hwangbo, second from right in the front row) >   KAIST's quadrupedal robot, RAIBO, can now move at high speed across discontinuous and complex terrains such as stairs, gaps, walls, and debris. It has demonstrated its ability to run on vertical walls, leap over 1.3-meter-wide gaps, sprint at approximately 14.4 km/h over stepping stones, and move quickly and nimbly on terrain combining 30° slopes, stairs, and stepping stones. RAIBO is expected to be deployed soon for practical missions such as disaster site exploration and mountain searches.   Professor Jemin Hwangbo's research team in the Department of Mechanical Engineering at our university announced on June 3rd that they have developed a quadrupedal robot navigation framework capable of high-speed locomotion at 14.4 km/h (4m/s) even on discontinuous and complex terrains such as walls, stairs, and stepping stones.   The research team developed a quadrupedal navigation system that enables the robot to reach its target destination quickly and safely in complex and discontinuous terrain.   To achieve this, they approached the problem by breaking it down into two stages: first, developing a planner for planning foothold positions, and second, developing a tracker to accurately follow the planned foothold positions.   First, the planner module quickly searches for physically feasible foothold positions using a sampling-based optimization method with neural network-based heuristics and verifies the optimal path through simulation rollouts.   While existing methods considered various factors such as contact timing and robot posture in addition to foothold positions, this research significantly reduced computational complexity by setting only foothold positions as the search space. Furthermore, inspired by the walking method of cats, the introduction of a structure where the hind feet step on the same spots as the front feet further significantly reduced computational complexity.       < Figure 1. High-speed navigation across various discontinuous terrains >   Second, the tracker module is trained to accurately step on planned positions, and tracking training is conducted through a generative model that competes in environments of appropriate difficulty.   The tracker is trained through reinforcement learning to accurately step on planned plots, and during this process, a generative model called the 'map generator' provides the target distribution.   This generative model is trained simultaneously and adversarially with the tracker to allow the tracker to progressively adapt to more challenging difficulties. Subsequently, a sampling-based planner was designed to generate feasible foothold plans that can reflect the characteristics and performance of the trained tracker.   This hierarchical structure showed superior performance in both planning speed and stability compared to existing techniques, and experiments proved its high-speed locomotion capabilities across various obstacles and discontinuous terrains, as well as its general applicability to unseen terrains.   Professor Jemin Hwangbo stated, "We approached the problem of high-speed navigation in discontinuous terrain, which previously required a significantly large amount of computation, from the simple perspective of how to select the footprint positions. Inspired by the placements of cat's paw, allowing the hind feet to step where the front feet stepped drastically reduced computation. We expect this to significantly expand the range of discontinuous terrain that walking robots can overcome and enable them to traverse it at high speeds, contributing to the robot's ability to perform practical missions such as disaster site exploration and mountain searches."   This research achievement was published in the May 2025 issue of the international journal Science Robotics.   Paper Title: High-speed control and navigation for quadrupedal robots on complex and discrete terrain, (https://www.science.org/doi/10.1126/scirobotics.ads6192)   YouTube Link: https://youtu.be/EZbM594T3c4?si=kfxLF2XnVUvYVIyk  

Professor Hyun Myung＇s Team Wins First Place in a ..

  < Photo 1. (From left) Daebeom Kim (Team Leader, Ph.D. student), Seungjae Lee (Ph.D. student), Seoyeon Jang (Ph.D. student), Jei Kong (Master's student), Professor Hyun Myung >   A team of the Urban Robotics Lab, led by Professor Hyun Myung from the KAIST School of Electrical Engineering, achieved a remarkable first-place overall victory in the Nothing Stands Still Challenge (NSS Challenge) 2025, held at the 2025 IEEE International Conference on Robotics and Automation (ICRA), the world's most prestigious robotics conference, from May 19 to 23 in Atlanta, USA.   The NSS Challenge was co-hosted by HILTI, a global construction company based in Liechtenstein, and Stanford University's Gradient Spaces Group. It is an expanded version of the HILTI SLAM (Simultaneous Localization and Mapping)＊ Challenge, which has been held since 2021, and is considered one of the most prominent challenges at 2025 IEEE ICRA.   ＊SLAM: Refers to Simultaneous Localization and Mapping, a technology where robots, drones, autonomous vehicles, etc., determine their own position and simultaneously create a map of their surroundings.       < Photo 2. A scene from the oral presentation on the winning team's technology (Speakers: Seungjae Lee and Seoyeon Jang, Ph.D. candidates of KAIST School of Electrical Engineering) >   This challenge primarily evaluates how accurately and robustly LiDAR scan data, collected at various times, can be registered in situations with frequent structural changes, such as construction and industrial environments. In particular, it is regarded as a highly technical competition because it deals with multi-session localization and mapping (Multi-session SLAM) technology that responds to structural changes occurring over multiple timeframes, rather than just single-point registration accuracy.   The Urban Robotics Lab team secured first place overall, surpassing National Taiwan University (3rd place) and Northwestern Polytechnical University of China (2nd place) by a significant margin, with their unique localization and mapping technology that solves the problem of registering LiDAR data collected across multiple times and spaces. The winning team will be awarded a prize of ＄4,000.       < Figure 1. Example of Multiway-Registration for Registering Multiple Scans >   The Urban Robotics Lab team independently developed a multiway-registration framework that can robustly register multiple scans even without prior connection information. This framework consists of an algorithm for summarizing feature points within scans and finding correspondences (CubicFeat), an algorithm for performing global registration based on the found correspondences (Quatro), and an algorithm for refining results based on change detection (Chamelion). This combination of technologies ensures stable registration performance based on fixed structures, even in highly dynamic industrial environments.       < Figure 2. Example of Change Detection Using the Chamelion Algorithm>   LiDAR scan registration technology is a core component of SLAM (Simultaneous Localization And Mapping) in various autonomous systems such as autonomous vehicles, autonomous robots, autonomous walking systems, and autonomous flying vehicles.   Professor Hyun Myung of the School of Electrical Engineering stated, "This award-winning technology is evaluated as a case that simultaneously proves both academic value and industrial applicability by maximizing the performance of precisely estimating the relative positions between different scans even in complex environments. I am grateful to the students who challenged themselves and never gave up, even when many teams abandoned due to the high difficulty."       < Figure 3. Competition Result Board, Lower RMSE (Root Mean Squared Error) Indicates Higher Score (Unit: meters)>   The Urban Robotics Lab team first participated in the SLAM Challenge in 2022, winning second place among academic teams, and in 2023, they secured first place overall in the LiDAR category and first place among academic teams in the vision category.

KAIST to Develop a Korean-style ChatGPT Platform S..

On May 23rd, KAIST (President Kwang-Hyung Lee) announced that its Digital Bio-Health AI Research Center (Director: Professor JongChul Ye of KAIST Kim Jaechul Graduate School of AI) has been selected for the Ministry of Science and ICT's 'AI Top-Tier Young Researcher Support Program (AI Star Fellowship Project).' With a total investment of ₩11.5 billion from May 2025 to December 2030, the center will embark on the full-scale development of AI technology and a platform capable of independently inferring and determining the kinds of diseases, and discovering new drugs.       < Photo. On May 20th, a kick-off meeting for the AI Star Fellowship Project was held at KAIST Kim Jaechul Graduate School of AI’s Yangjae Research Center with the KAIST research team and participating organizations of Samsung Medical Center, NAVER Cloud, and HITS. [From left to right in the front row] Professor Jaegul Joo (KAIST), Professor Yoonjae Choi (KAIST), Professor Woo Youn Kim (KAIST/HITS), Professor JongChul Ye (KAIST), Professor Sungsoo Ahn (KAIST), Dr. Haanju Yoo (NAVER Cloud), Yoonho Lee (KAIST), HyeYoon Moon (Samsung Medical Center), Dr. Su Min Kim (Samsung Medical Center) >   This project aims to foster an innovative AI research ecosystem centered on young researchers and develop an inferential AI agent that can utilize and automatically expand specialized knowledge systems in the bio and medical fields.   Professor JongChul Ye of the Kim Jaechul Graduate School of AI will serve as the lead researcher, with young researchers from KAIST including Professors Yoonjae Choi, Kimin Lee, Sungsoo Ahn, and Chanyoung Park, along with mid-career researchers like Professors Jaegul Joo and Woo Youn Kim, jointly undertaking the project. They will collaborate with various laboratories within KAIST to conduct comprehensive research covering the entire cycle from the theoretical foundations of AI inference to its practical application.     Specifically, the main goals include: - Building high-performance inference models that integrate diverse medical knowledge systems to enhance the precision and reliability of diagnosis and treatment. - Developing a convergence inference platform that efficiently combines symbol-based inference with neural network models. - Securing AI technology for new drug development and biomarker discovery based on 'cell ontology.'     Furthermore, through close collaboration with industry and medical institutions such as Samsung Medical Center, NAVER Cloud, and HITS Co., Ltd., the project aims to achieve:   - Clinical diagnostic AI utilizing medical knowledge systems. - AI-based molecular target exploration for new drug development. - Commercialization of an extendible AI inference platform.   Professor JongChul Ye, Director of KAIST's Digital Bio-Health AI Research Center, stated, "At a time when competition in AI inference model development is intensifying, it is a great honor for KAIST to lead the development of AI technology specialized in the bio and medical fields with world-class young researchers." He added, "We will do our best to ensure that the participating young researchers reach a world-leading level in terms of research achievements after the completion of this seven-year project starting in 2025."   The AI Star Fellowship is a newly established program where post-doctoral researchers and faculty members within seven years of appointment participate as project leaders (PLs) to independently lead research. Multiple laboratories within a university and demand-side companies form a consortium to operate the program.   Through this initiative, KAIST plans to nurture bio-medical convergence AI talent and simultaneously promote the commercialization of core technologies in collaboration with Samsung Medical Center, NAVER Cloud, and HITS.

“For the First Time, We Shared a Meaningful Exchan..

• KAIST team up with NAVER AI Lab and Dodakim Child Development Center Develop ‘AAcessTalk’, an AI-driven Communication Tool bridging the gap Between Children with Autism and their Parents   • The project earned the prestigious Best Paper Award at the ACM CHI 2025, the Premier International Conference in Human-Computer Interaction   • Families share heartwarming stories of breakthrough communication and newfound understanding.       < Photo 1. (From left) Professor Hwajung Hong and Doctoral candidate Dasom Choi of the Department of Industrial Design with SoHyun Park and Young-Ho Kim of Naver Cloud AI Lab >   For many families of minimally verbal autistic (MVA) children, communication often feels like an uphill battle. But now, thanks to a new AI-powered app developed by researchers at KAIST in collaboration with NAVER AI Lab and Dodakim Child Development Center, parents are finally experiencing moments of genuine connection with their children.   On the 16th, the KAIST (President Kwang Hyung Lee) research team, led by Professor Hwajung Hong of the Department of Industrial Design, announced the development of ‘AAcessTalk,’ an artificial intelligence (AI)-based communication tool that enables genuine communication between children with autism and their parents.   This research was recognized for its human-centered AI approach and received international attention, earning the Best Paper Award at the ACM CHI 2025＊, an international conference held in Yokohama, Japan.   ＊ACM CHI (ACM Conference on Human Factors in Computing Systems) 2025: One of the world's most prestigious academic conference in the field of Human-Computer Interaction (HCI).   This year, approximately 1,200 papers were selected out of about 5,000 submissions, with the Best Paper Award given to only the top 1％. The conference, which drew over 5,000 researchers, was the largest in its history, reflecting the growing interest in ‘Human-AI Interaction.’   Called AACessTalk, the app offers personalized vocabulary cards tailored to each child’s interests and context, while guiding parents through conversations with customized prompts. This creates a space where children’s voices can finally be heard—and where parents and children can connect on a deeper level.   Traditional augmentative and alternative communication (AAC) tools have relied heavily on fixed card systems that often fail to capture the subtle emotions and shifting interests of children with autism. AACessTalk breaks new ground by integrating AI technology that adapts in real time to the child’s mood and environment.       < Figure. Schematics of AACessTalk system. It provides personalized vocabulary cards for children with autism and context-based conversation guides for parents to focus on practical communication. Large ‘Turn Pass Button’ is placed at the child’s side to allow the child to lead the conversation. >     Among its standout features is a large ‘Turn Pass Button’ that gives children control over when to start or end conversations—allowing them to lead with agency. Another feature, the “What about Mom/Dad?” button, encourages children to ask about their parents’ thoughts, fostering mutual engagement in dialogue, something many children had never done before.   One parent shared, “For the first time, we shared a meaningful exchange.” Such stories were common among the 11 families who participated in a two-week pilot study, where children used the app to take more initiative in conversations and parents discovered new layers of their children’s language abilities.   Parents also reported moments of surprise and joy when their children used unexpected words or took the lead in conversations, breaking free from repetitive patterns. “I was amazed when my child used a word I hadn’t heard before. It helped me understand them in a whole new way,” recalled one caregiver.   Professor Hwajung Hong, who led the research at KAIST’s Department of Industrial Design, emphasized the importance of empowering children to express their own voices. “This study shows that AI can be more than a communication aid—it can be a bridge to genuine connection and understanding within families,” she said.   Looking ahead, the team plans to refine and expand human-centered AI technologies that honor neurodiversity, with a focus on bringing practical solutions to socially vulnerable groups and enriching user experiences.   This research is the result of KAIST Department of Industrial Design doctoral student Dasom Choi's internship at NAVER AI Lab.   ＊ Thesis Title: AACessTalk: Fostering Communication between Minimally Verbal Autistic Children and Parents with Contextual Guidance and Card Recommendation   ＊ DOI: 10.1145/3706598.3713792   ＊ Main Author Information: Dasom Choi (KAIST, NAVER AI Lab, First Author), SoHyun Park (NAVER AI Lab) , Kyungah Lee (Dodakim Child Development Center), Hwajung Hong (KAIST), and Young-Ho Kim (NAVER AI Lab, Corresponding Author)   This research was supported by the NAVER AI Lab internship program and grants from the National Research Foundation of Korea: the Doctoral Student Research Encouragement Grant (NRF-2024S1A5B5A19043580) and the Mid-Career Researcher Support Program for the Development of a Generative AI-Based Augmentative and Alternative Communication System for Autism Spectrum Disorder (RS-2024-00458557).

Decoding Fear： KAIST Identifies An Affective Brain..

Even after the COVID-19 pandemic, various new infectious diseases continue to emerge, posing ongoing viral threats that demand robust and sustained immune defenses. However, excessive immune reactions can also harm body tissues, causing significant health issues. KAIST and an international research team have discovered a critical protein that acts as a 'switch' regulating immune responses to viruses. This breakthrough is expected to lay the groundwork for future infectious disease responses and autoimmune disease treatment strategies.   KAIST (President Kwang-Hyung Lee) announced on May 14 that a joint research team led by Professor Yoosik Kim from the Department of Chemical and Biomolecular Engineering at KAIST and Professor Seunghee Cha from University of Florida has discovered the mechanism by which double-stranded RNA derived from mitochondria amplifies immune responses. They identified the protein SLIRP as an 'immune switch' that regulates this process, playing a crucial role in both viral infections and autoimmune diseases.       < (From left) Master's candidate Yewon Yang, Professor Yoosik Kim and Ph.D. candidate Doyeong Ku of the Department of Chemical and Biomolecular Engineering >   Autoimmune diseases arise when the immune system fails to differentiate between external pathogens and the body's own molecules, leading to self-directed attacks. Despite extensive research, the precise causes of excessive inflammatory conditions like Sjögren’s syndrome and systemic lupus erythematosus remain unclear, and effective treatments are still limited.   To uncover the molecular mechanisms driving immune hyperactivation and to identify potential regulatory factors, the research team led by Professor Yoosik Kim focused on mitochondrial double-stranded RNA (mt-dsRNA), a genetic immunogenic material produced within cellular organelles. Since mt-dsRNA structurally resembles viral RNA, it can mistakenly trigger immune responses even in the absence of an actual viral infection.   The team discovered that SLIRP, a key regulator of mt-dsRNA, amplifies immune responses by stabilizing the RNA. They confirmed that SLIRP expression increases in experimental models simulating the tissues of autoimmune disease patients and viral infections. Conversely, suppressing SLIRP significantly reduced the immune response, underscoring its role as a critical factor in immune amplification.   This study also demonstrated the dual function of SLIRP in different contexts. In cells infected with human beta coronavirus OC43 and encephalomyocarditis virus (EMCV), SLIRP suppression led to reduced antiviral responses and increased viral replication. Meanwhile, in the blood and salivary gland cells of Sjögren’s syndrome patients, where both SLIRP and mt-dsRNA levels were elevated, suppressing SLIRP alleviated the abnormal immune response.   These findings highlight SLIRP as a key molecular switch that regulates immune responses in both infections and autoimmune diseases.       < Figure 1. Schematic diagram of antiviral signal amplification by SLIRP: SLIRP-based mt-dsRNA induction, cytoplasmic accumulation, and strong interferon response induction by positive feedback of immune response activation. Confirmation of the immune regulatory function of SLIRP in defense against autoimmune diseases Sjögren's syndrome, coronavirus, and encephalomyocarditis virus infection. >   Professor Yoosik Kim remarked, "Through this study, we have identified SLIRP as a crucial protein that drives immune amplification via mt-dsRNAs. Given its dual role in autoimmune diseases and viral infections, SLIRP presents a promising target for immune regulation therapies across various inflammatory disease contexts."   The study, with Ph.D. student Do-Young Ku (first author) and M.S. student Ye-Won Yang (second author) from the Department of Chemical and Biomolecular Engineering at KAIST as primary contributors, was published online in the journal Cell Reports on April 19, 2025.   ※ Paper title: SLIRP amplifies antiviral signaling via positive feedback regulation and contributes to autoimmune diseases   ※ Main authors: Do-Young Ku (KAIST, first author), Ye-Won Yang (KAIST, second author), Seunghee Cha (University of Florida, corresponding author), Yoosik Kim (KAIST, corresponding author)   This study was supported by the Ministry of Health and Welfare's Public Health Technology Research Program and the National Institutes of Health (NIH) through Research Project (R01) funding.

KAIST ＆ CMU Unveils Amuse, a Songwriting AI-Collab..

Wouldn't it be great if music creators had someone to brainstorm with, help them when they're stuck, and explore different musical directions together? Researchers of KAIST and Carnegie Mellon University (CMU) have developed AI technology similar to a fellow songwriter who helps create music.   KAIST (President Kwang-Hyung Lee) has developed an AI-based music creation support system, Amuse, by a research team led by Professor Sung-Ju Lee of the School of Electrical Engineering in collaboration with CMU. The research was presented at the ACM Conference on Human Factors in Computing Systems (CHI), one of the world’s top conferences in human-computer interaction, held in Yokohama, Japan from April 26 to May 1. It received the Best Paper Award, given to only the top 1％ of all submissions.       < (From left) Professor Chris Donahue of Carnegie Mellon University, Ph.D. Student Yewon Kim and Professor Sung-Ju Lee of the School of Electrical Engineering >   The system developed by Professor Sung-Ju Lee’s research team, Amuse, is an AI-based system that converts various forms of inspiration such as text, images, and audio into harmonic structures (chord progressions) to support composition.   For example, if a user inputs a phrase, image, or sound clip such as “memories of a warm summer beach”, Amuse automatically generates and suggests chord progressions that match the inspiration.   Unlike existing generative AI, Amuse is differentiated in that it respects the user's creative flow and naturally induces creative exploration through an interactive method that allows flexible integration and modification of AI suggestions.   The core technology of the Amuse system is a generation method that blends two approaches: a large language model creates music code based on the user's prompt and inspiration, while another AI model, trained on real music data, filters out awkward or unnatural results using rejection sampling.       < Figure 1. Amuse system configuration. After extracting music keywords from user input, a large language model-based code progression is generated and refined through rejection sampling (left). Code extraction from audio input is also possible (right). The bottom is an example visualizing the chord structure of the generated code. >   The research team conducted a user study targeting actual musicians and evaluated that Amuse has high potential as a creative companion, or a Co-Creative AI, a concept in which people and AI collaborate, rather than having a generative AI simply put together a song.   The paper, in which a Ph.D. student Yewon Kim and Professor Sung-Ju Lee of KAIST School of Electrical and Electronic Engineering and Carnegie Mellon University Professor Chris Donahue participated, demonstrated the potential of creative AI system design in both academia and industry.   ※ Paper title: Amuse: Human-AI Collaborative Songwriting with Multimodal Inspirations DOI: https://doi.org/10.1145/3706598.3713818   ※ Research demo video: https://youtu.be/udilkRSnftI?si=FNXccC9EjxHOCrm1   ※ Research homepage: https://nmsl.kaist.ac.kr/projects/amuse/   Professor Sung-Ju Lee said, “Recent generative AI technology has raised concerns in that it directly imitates copyrighted content, thereby violating the copyright of the creator, or generating results one-way regardless of the creator’s intention. Accordingly, the research team was aware of this trend, paid attention to what the creator actually needs, and focused on designing an AI system centered on the creator.”   He continued, “Amuse is an attempt to explore the possibility of collaboration with AI while maintaining the initiative of the creator, and is expected to be a starting point for suggesting a more creator-friendly direction in the development of music creation tools and generative AI systems in the future.”   This research was conducted with the support of the National Research Foundation of Korea with funding from the government (Ministry of Science and ICT). (RS-2024-00337007)

KAIST Identifies Master Regulator Blocking Immunot..

Immune checkpoint inhibitors, a class of immunotherapies that help immune cells attack cancer more effectively, have revolutionized cancer treatment. However, fewer than 20％ of patients respond to these treatments, highlighting the urgent need for new strategies tailored to both responders and non-responders.   KAIST researchers have discovered that 'DEAD-box helicases 54 (DDX54)', a type of RNA-binding protein, is the master regulator that hinders the effectiveness of immunotherapy—opening a new path for lung cancer treatment. This breakthrough technology has been transferred to faculty startup BioRevert Inc., where it is currently being developed as a companion therapeutic and is expected to enter clinical trials by 2028.       < Photo 1. (From left) Researcher Jungeun Lee, Professor Kwang-Hyun Cho and Postdoctoral Researcher Jeong-Ryeol Gong of the Department of Bio and Brain Engineering at KAIST >   KAIST (represented by President Kwang-Hyung Lee) announced on April 8 that a research team led by Professor Kwang-Hyun Cho from the Department of Bio and Brain Engineering had identified DDX54 as a critical factor that determines the immune evasion capacity of lung cancer cells. They demonstrated that suppressing DDX54 enhances immune cell infiltration into tumors and significantly improves the efficacy of immunotherapy.   Immunotherapy using anti-PD-1 or anti-PD-L1 antibodies is considered a powerful approach in cancer treatment. However, its low response rate limits the number of patients who actually benefit.   To identify likely responders, tumor mutational burden (TMB) has recently been approved by the FDA as a key biomarker for immunotherapy. Cancers with high mutation rates are thought to be more responsive to immune checkpoint inhibitors. However, even tumors with high TMB can display an “immune-desert” phenotype—where immune cell infiltration is severely limited—resulting in poor treatment responses.       < Figure 1. DDX54 was identified as the master regulator that induces resistance to immunotherapy by orchestrating suppression of immune cell infiltration through cancer tissues as lung cancer cells become immune-evasive >   Professor Kwang-Hyun Cho's research team compared transcriptome and genome data of lung cancer patients with immune evasion capabilities through gene regulatory network analysis (A) and discovered DDX54, a master regulator that induces resistance to immunotherapy (B-F).   This study is especially significant in that it successfully demonstrated that suppressing DDX54 in immune-desert lung tumors can overcome immunotherapy resistance and improve treatment outcomes.   The team used transcriptomic and genomic data from immune-evasive lung cancer patients and employed systems biology techniques to infer gene regulatory networks. Through this analysis, they identified DDX54 as a central regulator in the immune evasion of lung cancer cells.   In a syngeneic mouse model, the suppression of DDX54 led to significant increases in the infiltration of anti-cancer immune cells such as T cells and NK cells, and greatly improved the response to immunotherapy.   Single-cell transcriptomic and spatial transcriptomic analyses further showed that combination therapy targeting DDX54 promoted the differentiation of T cells and memory T cells that suppress tumors, while reducing the infiltration of regulatory T cells and exhausted T cells that support tumor growth.       < Figure 2. In the syngeneic mouse model made of lung cancer cells, it was confirmed that inhibiting DDX54 reversed the immune-evasion ability of cancer cells and enhanced the sensitivity to anti-PD-1 therapy >   In a syngeneic mouse model made of lung cancer cells exhibiting immunotherapy resistance, the treatment applied after DDX54 inhibition resulted in statistically significant inhibition of lung cancer growth (B-D) and a significant increase in immune cell infiltration into the tumor tissue (E, F).   The mechanism is believed to involve DDX54 suppression inactivating signaling pathways such as JAK-STAT, MYC, and NF-κB, thereby downregulating immune-evasive proteins CD38 and CD47. This also reduced the infiltration of circulating monocytes—which promote tumor development—and promoted the differentiation of M1 macrophages that play anti-tumor roles.   Professor Kwang-Hyun Cho stated, “We have, for the first time, identified a master regulatory factor that enables immune evasion in lung cancer cells. By targeting this factor, we developed a new therapeutic strategy that can induce responsiveness to immunotherapy in previously resistant cancers.”   He added, “The discovery of DDX54—hidden within the complex molecular networks of cancer cells—was made possible through the systematic integration of systems biology, combining IT and BT.”   The study, led by Professor Kwang-Hyun Cho, was published in the Proceedings of the National Academy of Sciences of the United States of America (PNAS) on April 2, 2025, with Jeong-Ryeol Gong being the first author, Jungeun Lee, a co-first author, and Younghyun Han, a co-author of the article.       < Figure 3. Single-cell transcriptome and spatial transcriptome analysis confirmed that knockdown of DDX54 increased immune cell infiltration into cancer tissues >   In a syngeneic mouse model made of lung cancer cells that underwent immunotherapy in combination with DDX54 inhibition, single-cell transcriptome (H-L) and spatial transcriptome (A-G) analysis of immune cells infiltrating inside cancer tissues were performed. As a result, it was confirmed that anticancer immune cells such as T cells, B cells, and NK cells actively infiltrated the core of lung cancer tissues when DDX54 inhibition and immunotherapy were concurrently administered.   (Paper title: “DDX54 downregulation enhances anti-PD1 therapy in immune-desert lung tumors with high tumor mutational burden,” DOI: https://doi.org/10.1073/pnas.2412310122)   This work was supported by the Ministry of Science and ICT and the National Research Foundation of Korea through the Mid-Career Research Program and Basic Research Laboratory Program.       < Figure 4. The identified master regulator DDX54 was confirmed to induce CD38 and CD47 expression through Jak-Stat3, MYC, and NF-κB activation. >   DDX54 activates the Jak-Stat3, MYC, and NF-κB pathways in lung cancer cells to increase CD38 and CD47 expression (A-G). This creates a cancer microenvironment that contributes to cancer development (H) and ultimately induces immune anticancer treatment resistance.       < Figure 5. It was confirmed that an immune-inflamed environment can be created by combining DDX54 inhibition and immune checkpoint inhibitor (ICI) therapy. >   When DDX54 inhibition and ICI therapy are simultaneously administered, the cancer cell characteristics change, the immune evasion ability is restored, and the environment is transformed into an ‘immune-activated’ environment in which immune cells easily infiltrate cancer tissues. This strengthens the anticancer immune response, thereby increasing the sensitivity of immunotherapy even in lung cancer tissues that previously had low responsiveness to immunotherapy.

KAIST Develops Eco-Friendly, Nylon-Like Plastic Us..

Poly(ester amide) amide is a next-generation material that combines the advantages of PET (polyester) and nylon (polyamide), two widely used plastics. However, it could only be produced from fossil fuels, which posed environmental concerns. Using microorganisms, KAIST researchers have successfully developed a new bio-based plastic to replace conventional plastic.       < Photo 1. (From left) Professor Sang Yup Lee, Dr. Tong Un Chae, Dr. So Young Choi, and Ph.D. candidate Da-Hee Ahn of the Department of Chemical and Biomolecular Engineering >   KAIST (represented by President Kwang Hyung Lee) announced on the 20th of March that a research team led by Distinguished Professor Sang Yup Lee from the Department of Chemical and Biomolecular Engineering has developed microbial strains through systems metabolic engineering to produce various eco-friendly, bio-based poly(ester amide)s. The team collaborated with researchers from the Korea Research Institute of Chemical Technology (KRICT, President Young-Kook Lee) to analyze and confirm the properties of the resulting plastic.   Professor Sang Yup Lee’s research team designed new metabolic pathways that do not naturally exist in microorganisms, and developed a platform microbial strain capable of producing nine different types of poly(ester amide)s, including poly(3-hydroxybutyrate-ran-3-aminopropionate) and poly(3-hydroxybutyrate-ran-4-aminobutyrate).   Using glucose derived from abundant biomass sources such as waste wood and weeds, the team successfully produced poly(ester amide)s in an eco-friendly manner. The researchers also confirmed the potential for industrial-scale production by demonstrating high production efficiency (54.57 g/L) using fed-batch fermentation of the engineered strain.   In collaboration with researchers Haemin Jeong and Jihoon Shin from KRICT, the KAIST team analyzed the properties of the bio-based plastic and found that it exhibited characteristics similar to high-density polyethylene (HDPE). This means the new plastic is not only eco-friendly but also strong and durable enough to replace conventional plastics.       < Figure 1. New-to-nature metabolic pathways for the production of poly(ester amide)s (PEAs). >   The engineered strains and strategies developed in this study are expected to be useful not only for producing various poly(ester amide)s but also for constructing metabolic pathways for the biosynthesis of other types of polymers.   Professor Sang Yup Lee stated, “This study is the first to demonstrate the possibility of producing poly(ester amide)s (plastics) through a renewable bio-based chemical process rather than relying on the petroleum-based chemical industry. We plan to further enhance the production yield and efficiency through continued research.”   The study was published online on March 17 in the international journal Nature Chemical Biology.   ·Title: Biosynthesis of poly(ester amide)s in engineered Escherichia coli   ·DOI: 10.1038/s41589-025-01842-2   ·Authors: A total of seven authors including Tong Un Chae (KAIST, first author), So Young Choi (KAIST, second author), Da-Hee Ahn (KAIST, third author), Woo Dae Jang (KAIST, fourth author), Haemin Jeong (KRICT, fifth author), Jihoon Shin (KRICT, sixth author), and Sang Yup Lee (KAIST, corresponding author).   This research was supported by the Ministry of Science and ICT (MSIT) under the Eco-Friendly Chemical Technology Development Project as part of the "Next-Generation Biorefinery Technology Development to Lead the Bio-Chemical Industry" initiative (project led by Distinguished Professor Sang Yup Lee at KAIST).