Automatic C to Rust Translation Technology Gains Global Attention for Accuracy Beyond AI
<(From Left) Professor Sukyoung Ryu, Researcher Jaemin Hong>
As the C language, which forms the basis of critical global software like operating systems, faces security limitations, KAIST's research team is pioneering core original technology research for the accurate automatic conversion to Rust to replace it. By proving the mathematical correctness of the conversion, a limitation of existing Artificial Intelligence (LLM) methods, and solving C language security issues through automatic conversion to Rust, they presented a new direction and vision for future software security research. This work has been selected as the cover story for CACM, the world's highest-authority academic journal, thereby demonstrating KAIST's global research leadership in the field of computer science.
KAIST announced on the 9th of November that the paper by Professor Sukyoung Ryu's research team (Programming Language Research Group) from the School of Computing was selected as the cover story for the November issue of CACM (Communications of the ACM), the highest authority academic journal published by ACM (Association for Computing Machinery), the world's largest computer society.
<Photo of the Paper Selected for the Cover of Communications of the ACM>
This paper comprehensively addresses the technology developed by Professor Sukyoung Ryu's research team for the automatic conversion of C language to Rust, and it received high acclaim from the international research community for presenting the technical vision and academic direction this research should pursue in the future.
The C language has been widely used in the industry since the 1970s, but its structural limitations have continuously caused severe bugs and security vulnerabilities. Rust, on the other hand, is a secure programming language developed since 2015, used in the development of operating systems and web browsers, and has the characteristic of being able to detect and prevent bugs before program execution.
The US White House recommended discontinuing the use of C language in a technology report released in February 2024, and the Defense Advanced Research Projects Agency (DARPA) also explicitly stated that Rust is the core alternative for resolving C language security issues by promoting a project to develop technology for the automatic conversion of C code to Rust.
Professor Sukyoung Ryu's research team proactively raised the issues of C language safety and the importance of automatic conversion even before these movements began in earnest, and they have continuously developed core related technologies.
In May 2023, the research team presented the Mutex conversion technology (necessary for program synchronization) at ICSE (International Conference on Software Eng), the top authority conference in software engineering. In June 2024, they presented the Output Parameter conversion technology (used for result delivery) at PLDI (Programming Language Design and Implementation), the top conference in programming languages, and in October of the same year, they presented the Union conversion technology (for storing diverse data together) at ASE (Automated Software Eng), the representative conference in software automation.
These three studies are all "world-first" achievements presented at top-tier international academic conferences, successfully implementing automatic conversion technology for each feature with high completeness.
Since 2023, the research team has consistently published papers in CACM every year, establishing themselves as global leading researchers who consistently solve important and challenging problems worldwide.
This paper was published in CACM (Communications of the ACM) on October 24, with Dr. Jaemin Hong (Postdoctoral Research Fellow at KAIST Information and Electronics Research Institute) as the first author. ※Paper Title: Automatically Translating C to Rust, DOI: https://doi.org/10.1145/3737696
Dr. Jaemin Hong stated, "The conversion technology we developed is an original technology based on programming language theory, and its biggest strength is that we can logically prove the 'correctness' of the conversion." He added, "While most research relies on Large Language Models (LLMs), our technology can mathematically guarantee the correctness of the conversion."
Dr. Hong is scheduled to be appointed as an Assistant Professor in the Computer Science Department at UNIST starting in March 2025.
Furthermore, Professor Ryu's research team has four papers accepted for presentation at ASE 2025, the highest-authority conference in software engineering, including C→Rust conversion technology.
These papers, in addition to automatic conversion technology, cover various cutting-edge software engineering fields and are receiving high international acclaim. They include: technology to verify whether quantum computer programs operate correctly, 'WEST' technology that automatically checks the correctness of WebAssembly programs (technology for fast and efficient program execution on the web) and creates tests for them, and technology that automatically simplifies complex WebAssembly code to quickly find errors. Among these, the WEST paper received the Distinguished Paper Award.
This research was supported by the Leading Research Center/Mid-career Researcher Support Program of the National Research Foundation of Korea, the Institute of Information & Communications Technology Planning & Evaluation (IITP), and Samsung Electronics.
3D Worlds from Just a Few Phone Photos
<(From Left) Ph.D candidate Jumin Lee, Ph.D candidate Woo Jae Kim, Ph.D candidate Youngju Na, Ph.D candidate Kyu Beom Han, Professor Sung-eui Yoon>
Existing 3D scene reconstructions require a cumbersome process of precisely measuring physical spaces with LiDAR or 3D scanners, or correcting thousands of photos along with camera pose information. The research team at KAIST has overcome these limitations and introduced a technology enabling the reconstruction of 3D —from tabletop objects to outdoor scenes—with just two to three ordinary photographs. The breakthrough suggests a new paradigm in which spaces captured by camera can be immediately transformed into virtual environments.
KAIST announced on November 6 that the research team led by Professor Sung-Eui Yoon from the School of Computing has developed a new technology called SHARE (Shape-Ray Estimation), which can reconstruct high-quality 3D scenes using only ordinary images, without precise camera pose information.
Existing 3D reconstruction technology has been limited by the requirement of precise camera position and orientation information at the time of shooting to reproduce 3D scenes from a small number of images. This has necessitated specialized equipment or complex calibration processes, making real-world applications difficult and slowing widespread adoption.
To solve these problems, the research team developed a technology that constructs accurate 3D models by simultaneously estimating the 3D scene and the camera orientation using just two to three standard photographs. The technology has been recognized for its high efficiency and versatility, enabling rapid and precise reconstruction in real-world environments without additional training or complex calibration processes.
While existing methods calculate 3D structures from known camera poses, SHARE autonomously extracts spatial information from images themselves and infers both camera pose and scene structure. This enables stable 3D reconstruction without shape distortion by aligning multiple images taken from different positions into a single unified space.
<Representative Image of SHARE Technology>
"The SHARE technology is a breakthrough that dramatically lowers the barrier to entry for 3D reconstruction,” said Professor Sung-Eui Yoon. “It will enable the creation of high-quality content in various industries such as construction, media, and gaming using only a smartphone camera. It also has diverse application possibilities, such as building low-cost simulation environments in the fields of robotics and autonomous driving."
<SHARE Technology, Precise Camera Information and 3D Scene Prediction Technology>
Ph.D. Candidate Youngju Na and M.S candidate Taeyeon Kim participated as co-first authors on the research. The results were presented on September 17th at the IEEE International Conference on Image Processing (ICIP 2025), where the paper received the Best Student Paper Award.
The award, given to only one paper among 643 accepted papers this year—a selection rate of 0.16 percent—once again underscores the excellent research capabilities of the KAIST research team.
Paper Title: Pose-free 3D Gaussian Splatting via Shape-Ray Estimation, DOI: https://arxiv.org/abs/2505.22978
Award Information: https://www.linkedin.com/posts/ieeeicip_congratulations-to-the-icip-2025-best-activity-7374146976449335297-6hXz
This achievement was carried out with support from the Ministry of Science and ICT's SW Star Lab Project under the task 'Development of Perception, Action, and Interaction Algorithms for Unspecified Environments for Open World Robot Services.'
KAIST's 'FluidGPT' Wins Grand Prize at the 2025 AI Champion Competition
<Commemorative Photo After Winning at the 2025 AI Champions Award Ceremony>
The era has begun where an AI assistant goes beyond simple conversation to directly view the screen, make decisions, and complete tasks such as hailing a taxi or booking an SRT ticket.
KAIST (President Kwang Hyung Lee) announced on the 6th that the AutoPhone Team (Fluidez, KAIST, Korea University, Sungkyunkwan University), led by Professor Insik Shin (CEO of Fluidez Co., Ltd.) of the School of Computing, was selected as the inaugural AI Champion (1st place) in the '2025 Artificial Intelligence Champion (AI Champion) Competition,' hosted by the Ministry of Science and ICT.
This competition is the nation's largest AI technology contest, comprehensively evaluating the innovativeness, social impact, and commercial potential of AI technology. With 630 teams participating nationwide, the AutoPhone Team claimed the top honor and will receive 3 billion Korean won in research and development funding.
The technology developed by the AutoPhone Team, 'FluidGPT,' is a fully autonomous AI agent that understands a user's voice command and enables the smartphone to independently run apps, click, input, and even complete payments.
For example, when a user says, "Book an SRT ticket from Seoul Station to Busan," or "Call a taxi," FluidGPT opens the actual app and sequentially performs the necessary steps to complete the request.
The core of this technology is its 'Non-Invasive (API-Free)' structure. Previously, calling a taxi using an app required directly connecting to the app's internal system (API communication) through the taxi app's API. In contrast, this technology does not modify the existing app's code or link an API. Instead, the AI directly recognizes and operates the screen (UI), acquiring the ability to use the smartphone just like a human.
As a result, FluidGPT presents a new paradigm—"AI that sees, judges, and moves a hand on behalf of a person"—and is evaluated as a core technology that will usher in the 'AI Phone Era.'
FluidGPT moves beyond simple voice assistance to implement the concept of 'Agentic AI' (Action-Oriented Artificial Intelligence), where the AI directly views the screen, makes decisions, and takes action. As a fully action-oriented system, the AI clicks app buttons, fills in input fields, and references data to autonomously achieve the user's objective, foreshadowing an innovation in how smartphones are used.
Professor In-sik Shin of the School of Computing shared his thoughts, stating, "AI is now evolving from conversation to action. FluidGPT is a technology that understands the user's words and autonomously executes actual apps, and it will be the starting point of the 'AI Phone Era.' The AutoPhone Team possesses world-class research capabilities, and we will contribute to the widespread adoption of AI services that everyone can easily use."
KAIST President Kwang Hyung Lee remarked, "This achievement is a representative example that demonstrates KAIST's vision for AI convergence," adding, "AI technology is entering the daily lives of citizens and leading a new wave of innovation." He further added, "KAIST will continue to lead research in future core technologies such as AI and semiconductors to bolster national competitiveness."
KAIST, Dancing Like 'Navillera'... AI Understands and Renders Garment Motions of Avatars
<(From Left)Ph.D candidate Jihyun Lee, Professor Tae-Kyun Kim, M.S candidate Changmin Lee>
The era has begun where AI moves beyond merely 'plausibly drawing' to understanding even why clothes flutter and wrinkles form. A KAIST research team has developed a new generative AI that learns movement and interaction in 3D space following physical laws. This technology, which overcomes the limitations of existing 2D-based video AI, is expected to enhance the realism of avatars in films, the metaverse, and games, and significantly reduce the need for motion capture or manual 3D graphics work.
KAIST (President Kwang Hyung Lee) announced on the 22nd that the research team of Professor Tae-Kyun (T-K) Kim from the School of Computing has developed 'MPMAvatar,' a spatial and physics-based generative AI model that overcomes the limitations of existing 2D pixel-based video generation technology.
To solve the problems of conventional 2D technology, the research team proposed a new method that reconstructs multi-view images into 3D space using Gaussian Splatting and combines it with the Material Point Method (MPM), a physics simulation technique.
In other words, the AI was trained to learn physical laws on its own by stereoscopically reconstructing videos taken from multiple viewpoints and allowing objects within that space to move and interact as if they were in real physical world.
This enables the AI to compute the movement based on objects' material, shape, and external forces, and then learn the physical laws by comparing the results with actual videos.
The research team represented the 3D space using point-units, and by applying both Gaussian and MPM to each point, they simultaneously achieved physically natural movement and realistic video rendering.
That is, they divided the 3D space into numerous small points, making each point move and deform like a real object, thereby realizing natural video that is nearly indistinguishable from reality.
In particular, to precisely express the interaction of thin and complex objects like clothing, they calculated both the object's surface (mesh) and its particle-unit structure (point), and utilized the Material Point Method (MPM), which calculates the object's movement and deformation in 3D space according to physical laws.
Furthermore, they developed a new collision handling technology to realistically reproduce scenes where clothes or objects move and collide with each other in multiple spots and complex manner.
The generative AI model MPMAvatar, to which this technology is applied, successfully reproduced the realistic movement and interaction of a person wearing loose clothing, and also succeeded in 'Zero-shot' generation, where the AI processes data it has never seen during the learning process by inferring on its own.
<Figure 1. Modeling new human poses and clothing dynamics from multi-view video input, and zero-shot generation of novel physical interactions.>
The proposed method is applicable to various physical properties, such as rigid bodies, deformable objects, and fluids, allowing it to be used not only for avatars but also for the generation of general complex scenes.
<“Figure 2. Depiction of graceful dance movements and soft clothing folds, like Navillera.>
Professor Tae-Kyun (T-K) Kim explained, "This technology goes beyond AI simply drawing a picture; it makes the AI understand 'why' the world in front of it looks the way it does. This research demonstrates the potential of 'Physical AI' that understands and predicts physical laws, marking an important turning point toward AGI (Artificial General Intelligence)." He added, "It is expected to be practically applied across the broaden immersive content industry, including virtual production, films, short-form contents, and adverts, creating significant change."
The research team is currently expanding this technology to develop a model that can generate physically consistent 3D videos simply from a user's text input.
This research involved Changmin Lee, a Master's student at the KAIST Graduate School of AI, as the first author, and Jihyun Lee, a Ph.D. student at the KAIST School of Computing, as a co-author. The research results will be presented at NeurIPS, the most prestigious international academic conference in the field of AI, on December 2nd, and the program code is to be fully released.
· Paper: C. Lee, J. Lee, T-K. Kim, MPMAvatar: Learning 3D Gaussian Avatars with Accurate and Robust Physics-Based Dynamics, Proc. of Thirty-Ninth Annual Conf. on Neural Information Processing Systems (NeurIPS), San Diego, US, 2025
· arXiv version: https://arxiv.org/abs/2510.01619
· Related Project Site: https://kaistchangmin.github.io/MPMAvatar/
· Related video links showing the 'Navillera'-like dancing drawn by AI:
o https://www.youtube.com/shorts/ZE2KoRvUF5c
o https://youtu.be/ytrKDNqACqM
This work was supported by the Institute of Information & Communications Technology Planning & Evaluation(IITP) grant funded by the Korea government(MSIT) through the Human-Oriented Next-Generation Challenging AGI Technology Project (RS-2025-25443318) and the Professional AI Talent Development Program for Multimodal AI Agents (RS-2025-25441313).
Refrigerator Use Increases with Stress, IoT Sensors Read Mental Health
<(From Left) Ph.D candidate Chanhee Lee, Professor Uichin Lee, Professor Hyunsoo Lee, Ph.D candidate Youngji Koh from School of Computing>
The number of single-person households in South Korea has exceeded 8 million, accounting for 36% of the total, marking an all-time high. A Seoul Metropolitan Government survey found that 62% of single-person households experience 'loneliness', deepening feelings of isolation and mental health issues. KAIST researchers have gone beyond the limitations of smartphones and wearables, utilizing in-home IoT data to reveal that a disruption in daily rhythm is a key indicator of worsening mental health. This research is expected to lay the foundation for developing personalized mental healthcare management systems.
KAIST (President Kwang Hyung Lee) announced on the 21st of October that a research team led by Professor Uichin Lee from the School of Computing has demonstrated the possibility of accurately tracking an individual's mental health status using in-home Internet of Things (IoT) sensor data.
Consistent self-monitoring is important for mental health management, but existing smartphone- or wearable-based tracking methods have the limitation of data loss when the user is not wearing or carrying the device inside the home.
The research team therefore focused on in-home environmental data. A 4-week pilot study was conducted on 20 young single-person households, installing appliances, sleep mats, motion sensors, and other devices to collect IoT data, which was then analyzed along with smartphone and wearable data.
The results confirmed that utilizing IoT data alongside existing methods allows for a significantly more accurate capture of changes in mental health. For instance, reduced sleep time was closely linked to increased levels of depression, anxiety, and stress, and increased indoor temperature also showed a correlation with anxiety and depression.
<Picture1. Heatmap of the Correlation Between Each User’s Mental Health Status and Sensor Data>
Participants' behavioral patterns varied, including a 'binge-eating type' with increased refrigerator use during stress and a 'lethargic type' with a sharp decrease in activity. However, a common trend clearly emerged: mental health deteriorated as daily routines became more irregular.
Variability in daily patterns was confirmed to be a more important factor than the frequency of specific behaviors, suggesting that a regular routine is essential for maintaining mental health.
When research participants viewed their life data through visualization software, they generally perceived the data as being genuinely helpful in understanding their mental health, rather than expressing concern about privacy invasion. This significantly enhanced the research acceptance and satisfaction with participation.
<Figure 2. Comparison of Average Mental Health Status Between the High Irregularity Group (Red) and the Low Irregularity Group (Blue)>
Professor Uichin Lee stated, "This research demonstrates that in-home IoT data can serve as an important clue for understanding mental health within the context of an individual's daily life," and added, "We plan to further develop this into a remote healthcare system that can predict individual lifestyle patterns and provide personalized coaching using AI."
Youngji Koh, a Ph.D candidate, participated as the first author in this research. The findings were published in the September issue of the Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, a prominent international journal in the field of human-computer interaction (HCI). ※ Harnessing Home IoT for Self-tracking Emotional Wellbeing: Behavioral Patterns, Self-Reflection, and Privacy Concerns DOI: https://dl.acm.org/doi/10.1145/3749485 ※ Youngji Koh (KAIST, 1st author), Chanhee Lee (KAIST, 2nd author), Eunki Joung (KAIST, 3rd author), Hyunsoo Lee (KAIST, corresponding author), Uichin Lee (KAIST, corresponding author)
This research was conducted with support from the LG Electronics-KAIST Digital Healthcare Research Center and the National Research Foundation of Korea, funded by the government (Ministry of Science and ICT).
KAIST Develops an AI Semiconductor Brain Combining Transformer's Intelligence and Mamba's Efficiency
<(From Left) Ph.D candidate Seongryong Oh, Ph.D candidate Yoonsung Kim, Ph.D candidate Wonung Kim, Ph.D candidate Yubin Lee, M.S candidate Jiyong Jung, Professor Jongse Park, Professor Divya Mahajan, Professor Chang Hyun Park>
As recent Artificial Intelligence (AI) models’ capacity to understand and process long, complex sentences grows, the necessity for new semiconductor technologies that can simultaneously boost computation speed and memory efficiency is increasing. Amidst this, a joint research team featuring KAIST researchers and international collaborators has successfully developed a core AI semiconductor 'brain' technology based on a hybrid Transformer and Mamba structure, which was implemented for the first time in the world in a form capable of direct computation inside the memory, resulting in a four-fold increase in the inference speed of Large Language Models (LLMs) and a 2.2-fold reduction in power consumption.
KAIST (President Kwang Hyung Lee) announced on the 17th of October that the research team led by Professor Jongse Park from KAIST School of Computing, in collaboration with Georgia Institute of Technology in the United States and Uppsala University in Sweden, developed 'PIMBA,' a core technology based on 'AI Memory Semiconductor (PIM, Processing-in-Memory),' which acts as the brain for next-generation AI models.
Currently, LLMs such as ChatGPT, GPT-4, Claude, Gemini, and Llama operate based on the 'Transformer' brain structure, which sees all of the words simultaneously. Consequently, as the AI model grows and the processed sentences become longer, the computational load and memory requirements surge, leading to speed reductions and high energy consumption as major issues.
To overcome these problems with Transformer, the recently proposed sequential memory-based 'Mamba' structure introduced a method for processing information over time, increasing efficiency. However, memory bottlenecks and power consumption limits still remained.
Professor Park Jongse's research team designed 'PIMBA,' a new semiconductor structure that directly performs computations inside the memory in order to maximize the performance of the 'Transformer–Mamba Hybrid Model,' which combines the advantages of both Transformer and Mamba.
While existing GPU-based systems move data out of the memory to perform computations, PIMBA performs calculations directly within the storage device without moving the data. This minimizes data movement time and significantly reduces power consumption.
<Analysis of Post-Transformer Models and Proposal of a Problem-Solving Acceleration System>
As a result, PIMBA showed up to a 4.1-fold improvement in processing performance and an average 2.2-fold decrease in energy consumption compared to existing GPU systems.
The research outcome is scheduled to be presented on October 20th at the '58th International Symposium on Microarchitecture (MICRO 2025),' a globally renowned computer architecture conference that will be held in Seoul. It was previously recognized for its excellence by winning the Gold Prize at the '31st Samsung Humantech Paper Award.' ※Paper Title: Pimba: A Processing-in-Memory Acceleration for Post-Transformer Large Language Model Serving, DOI: 10.1145/3725843.3756121
This research was supported by the Institute for Information & Communications Technology Planning & Evaluation (IITP), the AI Semiconductor Graduate School Support Project, and the ICT R&D Program of the Ministry of Science and ICT and the IITP, with assistance from the Electronics and Telecommunications Research Institute (ETRI). The EDA tools were supported by IDEC (the IC Design Education Center).
KAIST Develops AI Crowd Prediction Technology to Prevent Disasters like the Itaewon Tragedy
<(From Left) Ph.D candidate Youngeun Nam from KAIST, Professor Jae-Gil Lee from KAIST, Ji-Hye Na from KAIST, (Top right, from left) Professor Soo-Sik Yoon from Korea University, Professor HwanJun Song from KAIST>
To prevent crowd crush incidents like the Itaewon tragedy, it's crucial to go beyond simply counting people and to instead have a technology that can detect the real-
inflow and movement patterns of crowds. A KAIST research team has successfully developed new AI crowd prediction technology that can be used not only for managing large-scale events and mitigating urban traffic congestion but also for responding to infectious disease outbreaks.
On the 17th, KAIST (President Kwang Hyung Lee) announced that a research team led by Professor Jae-Gil Lee from the School of Computing has developed a new AI technology that can more accurately predict crowd density.
The dynamics of crowd gathering cannot be explained by a simple increase or decrease in the number of people. Even with the same number of people, the level of risk changes depending on where they are coming from and which direction they are heading.
Professor Lee's team expressed this movement using the concept of a "time-varying graph." This means that accurate prediction is only possible by simultaneously analyzing two types of information: "node information" (how many people are in a specific area) and "edge information" (the flow of people between areas).
In contrast, most previous studies focused on only one of these factors, either concentrating on "how many people are gathered right now" or "which paths are people moving along." However, the research team emphasized that combining both is necessary to truly capture a dangerous situation.
For example, a sudden increase in density in a specific alleyway, such as Alley A, is difficult to predict with just "current population" data. But by also considering the flow of people continuously moving from a nearby area, Area B, towards Area A (edge information), it's possible to pre-emptively identify the signal that "Area A will soon become dangerous."
To achieve this, the team developed a "bi-modal learning" method. This technology simultaneously considers population counts (node information) and population flow (edge information), while also learning spatial relationships (which areas are connected) and temporal changes (when and how movement occurs).
Specifically, the team introduced a 3D contrastive learning technique. This allows the AI to learn not only 2D spatial (geographical) information but also temporal information, creating a 3D relationship. As a result, the AI can understand not just whether the population is "large or small right now," but "what pattern the crowd is developing into over time." This allows for a much more accurate prediction of the time and place where congestion will occur than previous methods.
<Figure 1. Workflow of the bi-modal learning-based crowd congestion risk prediction developed by the research team.
The research team developed a crowd congestion risk prediction model based on bi-modal learning. The vertex-based time series represents indicator changes in a specific area (e.g., increases or decreases in crowd density), while the edge-based time series captures the flow of population movement between areas over time. Although these two types of data are collected from different sources, they are mapped onto the same network structure and provided together as input to the AI model. During training, the model simultaneously leverages both vertex and edge information based on a shared network, allowing it to capture complex movement patterns that might be overlooked when relying on only a single type of data. For example, a sudden increase in crowd density in a particular area may be difficult to predict using vertex information alone, but by additionally considering the steady inflow of people from adjacent areas (edge information), the prediction becomes more accurate. In this way, the model can precisely identify future changes based on past and present information, ultimately predicting high-risk crowd congestion areas in advance.>
The research team built and publicly released six real-world datasets for their study, which were compiled from sources such as Seoul, Busan, and Daegu subway data, New York City transit data, and COVID-19 confirmed case data from South Korea and New York.
The proposed technology achieved up to a 76.1% improvement in prediction accuracy over recent state-of-the-art methods, demonstrating strong perf
Professor Jae-Gil Lee stated, "It is important to develop technologies that can have a significant social impact," adding, "I hope this technology will greatly contribute to protecting public safety in daily life, such as in crowd management for large events, easing urban traffic congestion, and curbing the spread of infectious diseases."
Youngeun Nam, a Ph.D candidate in the KAIST School of Computing, was the first author of the study, and Jihye Na, another Ph.D candidate, was a co-author. The research findings were presented at the Knowledge Discovery and Data Mining (KDD) 2025 conference, a top international conference in the field of data mining, this past August.
※ Paper Title: Bi-Modal Learning for Networked Time Series ※ DOI: https://doi.org/10.1145/3711896.3736856
This technology is the result of research projects including the "Mid-Career Researcher Project" (RS-2023-NR077002, Core Technology Research for Crowd Management Systems Based on AI and Mobility Big Data) and the "Human-Centered AI Core Technology Development Project" (RS-2022-II220157, Robust, Fair, and Scalable Data-Centric Continuous Learning).
Making Truly Smart AI Agents a Reality with the World's Best DB Integration Technology
<(From Left) Engineer Jeongho Park from GraphAI, Ph.D candidate Geonho Lee, Prof. Min-Soo Kim from KAIST>
For a long time, companies have been using relational databases (DB) to manage data. However, with the increasing use of large AI models, integration with graph databases is now required. This process, however, reveals limitations such as cost burden, data inconsistency, and the difficulty of processing complex queries.
Our research team has succeeded in developing a next-generation graph-relational DB system that can solve these problems at once, and it is expected to be applied to industrial sites immediately. When this technology is applied, AI will be able to reason about complex relationships in real time, going beyond simple searches, making it possible to implement a smarter AI service.
The research team led by Professor Min-Soo Kim announced on the 8th of September that the team has developed a new DB system named 'Chimera' that fully integrates relational DB and graph DB to efficiently execute graph-relational queries. Chimera has proven its world-class performance by processing queries at least 4 times and up to 280 times faster than existing systems in international performance standard benchmarks.
Unlike existing relational DBs, graph DBs have a structure that represents data as vertices (nodes) and edges (connections), which gives them a strong advantage in analyzing and reasoning about complexly intertwined information like people, events, places, and time. Thanks to this feature, its use is rapidly spreading in various fields such as AI agents, SNS, finance, and e-commerce.
With the growing demand for complex query processing between relational DBs and graph DBs, a new standard language, 'SQL/PGQ,' which extends relational query language (SQL) with graph query functions, has also been proposed.
SQL/PGQ is a new standard language that adds graph traversal capabilities to the existing database language (SQL) and is designed to query both table-like data and connected information such as people, events, and places at once. Using this, complex relationships such as 'which company does my friend's friend work for?' can be searched much more simply than before.
<Diagram (a): This diagram shows the typical architecture of a graph query processing system based on a traditional RDBMS. It has separate dedicated operators for graph traversal and an in-memory graph structure, while attribute joins are handled by relational operators. However, this structure makes it difficult to optimize execution plans for hybrid queries because traversal and joins are performed in different pipelines. Additionally, for large-scale graphs, the in-memory structure creates memory constraints, and the method of extracting graph data from relational data limits data freshness. Diagram (b): This diagram shows Chimera's integrated architecture. Chimera introduces new components to the existing RDBMS architecture: a traversal-join operator that combines graph traversal and joins, a disk-based graph storage, and a dedicated graph access layer. This allows it to process both graph and relational data within a single execution flow. Furthermore, a hybrid query planner integrally optimizes both graph and relational operations. Its shared transaction management and disk-based storage structure enable it to handle large-scale graph databases without memory constraints while maintaining data freshness. This architecture removes the bottlenecks of existing systems by flexibly combining traversal, joins, and mappings in a single execution plan, thereby simultaneously improving performance and scalability.>
The problem is that existing approaches have relied on either trying to mimic graph traversal with join operations or processing by pre-building a graph view in memory. In the former case, performance drops sharply as the traversal depth increases, and in the latter case, execution fails due to insufficient memory even if the data size increases slightly. Furthermore, changes to the original data are not immediately reflected in the view, resulting in poor data freshness and the inefficiency of having to combine relational and graph results separately.
KAIST research team's 'Chimera' fundamentally solves these limitations. The research team redesigned both the storage layer and the query processing layer of the database.
First, the research team introduced a 'dual-store structure' that operates a graph-specific storage and a relational data storage together. They then applied a 'traversal-join operator' that processes graph traversal and relational operations simultaneously, allowing complex operations to be executed efficiently in a single system. Thanks to this, Chimera has established itself as the world's first graph-relational DB system that integrates the entire process from data storage to query processing into one.
As a result, it recorded world-class performance on the international performance standard benchmark 'LDBC Social Network Benchmark (SNB),' being at least 4 times and up to 280 times faster than existing systems.
Query failure due to insufficient memory does not occur no matter how large the graph data becomes, and since it does not use views, there is no delay problem in terms of data freshness.
Professor Min-Soo Kim stated, "As the connections between data become more complex, the need for integrated technology that encompasses both graph and relational DBs is increasing. Chimera is a technology that fundamentally solves this problem, and we expect it to be widely used in various industries such as AI agents, finance, and e-commerce."
The study was co-authored by Geonho Lee, a Ph.D. student in KAIST School of Computing, as the first author, and Jeongho Park, an engineer at Professor Kim's startup GraphAI Co., Ltd., as the second author, with Professor Kim as the corresponding author.
The research results were presented on September 1st at VLDB, a world-renowned international academic conference in the field of databases. In particular, the newly developed Chimera technology is expected to have an immediate industrial impact as a core technology for implementing 'high-performance AI agents based on RAG (a smart AI assistant with search capabilities),' which will be applied to 'AkasicDB,' a vector-graph-relational DB system scheduled to be released by GraphAI Co., Ltd.
*Paper title: Chimera: A System Design of Dual Storage and Traversal-Join Unified Query Processing for SQL/PGQ *DOI: https://dl.acm.org/doi/10.14778/3705829.3705845
This research was supported by the Ministry of Science and ICT's IITP SW Star Lab and the National Research Foundation of Korea's Mid-Career Researcher Program.
KAIST Develops AI that Automatically Detects Defects in Smart Factory Manufacturing Processes Even When Conditions Change
Recently, defect detection systems using artificial intelligence (AI) sensor data have been installed in smart factory manufacturing sites. However, when the manufacturing process changes due to machine replacement or variations in temperature, pressure, or speed, existing AI models fail to properly understand the new situation and their performance drops sharply. KAIST researchers have developed AI technology that can accurately detect defects even in such situations without retraining, achieving performance improvements up to 9.42%. This achievement is expected to contribute to reducing AI operating costs and expanding applicability in various fields such as smart factories, healthcare devices, and smart cities.
KAIST (President Kwang Hyung Lee) announced on the 26th of August that a research team led by Professor Jae-Gil Lee from the School of Computing has developed a new “time-series domain adaptation” technology that allows existing AI models to be utilized without additional defect labeling, even when manufacturing processes or equipment change.
Time-series domain adaptation technology enables AI models that handle time-varying data (e.g., temperature changes, machine vibrations, power usage, sensor signals) to maintain stable performance without additional training, even when the training environment (domain) and the actual application environment differ.
Professor Lee’s team paid attention to the fact that the core problem of AI models becoming confused by environmental (domain) changes lies not only in differences in data distribution but also in changes in defect occurrence patterns (label distribution) themselves. For example, in semiconductor wafer processes, the ratio of ring-shaped defects and scratch defects may change due to equipment modifications.
The research team developed a method for decomposing new process sensor data into three components—trends, non-trends, and frequencies—to analyze their characteristics individually. Just as humans detect anomalies by combining pitch, vibration patterns, and periodic changes in machine sounds, AI was enabled to analyze data from multiple perspectives.
In other words, the team developed TA4LS (Time-series domain Adaptation for mitigating Label Shifts) technology, which applies a method of automatically correcting predictions by comparing the results predicted by the existing model with the clustering information of the new process data. Through this, predictions biased toward the defect occurrence patterns of the existing process can be precisely adjusted to match the new process.
In particular, this technology is highly practical because it can be easily combined like an additional plug-in module inserted into existing AI systems without requiring separate complex development. That is, regardless of the AI technology currently being used, it can be applied immediately with only simple additional procedures.
In experiments using four benchmark datasets of time-series domain adaptation (i.e., four types of sensor data in which changes had occurred), the research team achieved up to 9.42% improvement in accuracy compared to existing methods.[TT1]
Especially when process changes caused large differences in label distribution (e.g., defect occurrence patterns), the AI demonstrated remarkable performance improvement by autonomously correcting and distinguishing such differences. These results proved that the technology can be used more effectively without defects in environments that produce small batches of various products, one of the main advantages of smart factories.
Professor Jae-Gil Lee, who supervised the research, said, “This technology solves the retraining problem, which has been the biggest obstacle to the introduction of artificial intelligence in manufacturing. Once commercialized, it will greatly contribute to the spread of smart factories by reducing maintenance costs and improving defect detection rates.”
This research was carried out with Jihye Na, a Ph.D. student at KAIST, as the first author, with Youngeun Nam, a Ph.D. student, and Junhyeok Kang, a researcher at LG AI Research, as co-authors. The research results were presented in August 2025 at KDD (the ACM SIGKDD Conference on Knowledge Discovery and Data Mining), the world’s top academic conference in artificial intelligence and data.
※Paper Title: “Mitigating Source Label Dependency in Time-Series Domain Adaptation under Label Shifts”
※DOI: https://doi.org/10.1145/3711896.3737050
This technology was developed as part of the research outcome of the SW Computing Industry Original Technology Development Program’s SW StarLab project (RS-2020-II200862, DB4DL: Development of Highly Available and High-Performance Distributed In-Memory DBMS for Deep Learning), supported by the Ministry of Science and ICT and the Institute for Information & Communications Technology Planning & Evaluation (IITP).
KAIST develops “FlexGNN,” a graph analysis AI 95 times faster with a single GPU server
<(From Left) Donghyoung Han, CTO of GraphAI Co, Ph.D candidate Jeongmin Bae from KAIST, Professor Min-soo Kim from KAIST>
Alongside text-based large language models (LLMs) including ChatGPT, in industrial fields, GNN (Graph Neural Network)-based graph AI models that analyze unstructured data such as financial transactions, stocks, social media, and patient records in graph form are being actively used. However, there is a limitation in that full graph learning—training the entire graph at once—requires massive memory and GPU servers. A KAIST research team has succeeded in developing the world’s highest-performance software technology that can train large-scale GNN models at maximum speed using only a single GPU server.
KAIST (President Kwang Hyung Lee) announced on the 13th that the research team led by Professor Min-Soo Kim of the School of Computing has developed “FlexGNN,” a GNN system that, unlike existing methods using multiple GPU servers, can quickly train and infer large-scale full-graph AI models on a single GPU server. FlexGNN improves training speed by up to 95 times compared to existing technologies.
Recently, in various fields such as climate, finance, medicine, pharmaceuticals, manufacturing, and distribution, there has been a growing number of cases where data is converted into graph form, consisting of nodes and edges, for analysis and prediction.
While the full graph approach, which uses the entire graph for training, achieves higher accuracy, it has the drawback of frequently running out of memory due to the generation of massive intermediate data during training, as well as prolonged training times caused by data communication between multiple servers.
To overcome these problems, FlexGNN performs optimal AI model training on a single GPU server by utilizing SSDs (solid-state drives) and main memory instead of multiple GPU servers.
<Figure (a): This illustrates the typical execution flow of a conventional full-graph GNN training system. All intermediate data generated during training are retained in GPU memory, and computations are performed sequentially without data movement or memory optimization. Consequently, if the GPU memory capacity is exceeded, training becomes infeasible. Additionally, inter-GPU data exchange relies solely on a fixed method (X_rigid), limiting performance and scalability. Figure (b): This depicts an example of the execution flow based on the optimized training execution plan generated by FlexGNN. For each intermediate data, strategies such as retention, offloading, or recomputation are selectively applied. Depending on resource constraints and data size, an appropriate inter-GPU exchange method—either GPU-to-GPU (G2G) or GPU-to-Host (G2H)—is adaptively chosen by the exchange operator (X_adapt). Furthermore, offloading and reloading operations are scheduled to overlap as much as possible with computation, maximizing compute-data movement parallelism. The adaptive exchange operator and various data offloading and reloading operators (R, O) within the figure demonstrate FlexGNN's ability to flexibly control intermediate data management and inter-GPU exchange strategies based on the training execution plan.>
Particularly, through AI query optimization training—which optimizes the quality of database systems—the team developed a new training optimization technology that calculates model parameters, training data, and intermediate data between GPU, main memory, and SSD layers at the optimal timing and method.
As a result, FlexGNN flexibly generates optimal training execution plans according to available resources such as data size, model scale, and GPU memory, thereby achieving high resource efficiency and training speed.
Consequently, it became possible to train GNN models on data far exceeding main memory capacity, and training could be up to 95 times faster even on a single GPU server. In particular, the realization of full-graph AI, capable of more precise analysis than supercomputers in applications such as climate prediction, has become a reality.
Professor Min-Soo Kim of KAIST stated, “As full-graph GNN models are actively used to solve complex problems such as weather prediction and new material discovery, the importance of related technologies is increasing.” He added that “since FlexGNN has dramatically solved the longstanding problems of training scale and speed in graph AI models, we expect it to be widely used in various industries.”
In this research, Jeongmin Bae, a doctoral student in the School of Computing at KAIST, participated as the first author, Donghyoung Han, CTO of GraphAI Co. (founded by Professor Kim) participated as the second author, and Professor Kim served as the corresponding author.
The research results were presented on August 5 at ACM KDD, a world-renowned data mining conference. The FlexGNN technology is also planned to be applied to Grapheye’s graph database solution, GraphOn.
● Paper title: FlexGNN: A High-Performance, Large-Scale Full-Graph GNN System with Best-Effort Training Plan Optimization
● DOI: https://doi.org/10.1145/3711896.3736964
This research was supported by the IITP SW Star Lab and IITP-ITRC of the Ministry of Science and ICT, as well as the mid-level project program of the National Research Foundation of Korea.
Development of Core NPU Technology to Improve ChatGPT Inference Performance by Over 60%
Latest generative AI models such as OpenAI's ChatGPT-4 and Google's Gemini 2.5 require not only high memory bandwidth but also large memory capacity. This is why generative AI cloud operating companies like Microsoft and Google purchase hundreds of thousands of NVIDIA GPUs. As a solution to address the core challenges of building such high-performance AI infrastructure, Korean researchers have succeeded in developing an NPU (Neural Processing Unit)* core technology that improves the inference performance of generative AI models by an average of over 60% while consuming approximately 44% less power compared to the latest GPUs.
*NPU (Neural Processing Unit): An AI-specific semiconductor chip designed to rapidly process artificial neural networks.
On the 4th, Professor Jongse Park's research team from KAIST School of Computing, in collaboration with HyperAccel Inc. (a startup founded by Professor Joo-Young Kim from the School of Electrical Engineering), announced that they have developed a high-performance, low-power NPU (Neural Processing Unit) core technology specialized for generative AI clouds like ChatGPT.
The technology proposed by the research team has been accepted by the '2025 International Symposium on Computer Architecture (ISCA 2025)', a top-tier international conference in the field of computer architecture.
The key objective of this research is to improve the performance of large-scale generative AI services by lightweighting the inference process, while minimizing accuracy loss and solving memory bottleneck issues. This research is highly recognized for its integrated design of AI semiconductors and AI system software, which are key components of AI infrastructure.
While existing GPU-based AI infrastructure requires multiple GPU devices to meet high bandwidth and capacity demands, this technology enables the configuration of the same level of AI infrastructure using fewer NPU devices through KV cache quantization*. KV cache accounts for most of the memory usage, thereby its quantization significantly reduces the cost of building generative AI clouds.
*KV Cache (Key-Value Cache) Quantization: Refers to reducing the data size in a type of temporary storage space used to improve performance when operating generative AI models (e.g., converting a 16-bit number to a 4-bit number reduces data size by 1/4).
The research team designed it to be integrated with memory interfaces without changing the operational logic of existing NPU architectures. This hardware architecture not only implements the proposed quantization algorithm but also adopts page-level memory management techniques* for efficient utilization of limited memory bandwidth and capacity, and introduces new encoding technique optimized for quantized KV cache.
*Page-level memory management technique: Virtualizes memory addresses, as the CPU does, to allow consistent access within the NPU.
Furthermore, when building an NPU-based AI cloud with superior cost and power efficiency compared to the latest GPUs, the high-performance, low-power nature of NPUs is expected to significantly reduce operating costs.
Professor Jongse Park stated, "This research, through joint work with HyperAccel Inc., found a solution in generative AI inference lightweighting algorithms and succeeded in developing a core NPU technology that can solve the 'memory problem.' Through this technology, we implemented an NPU with over 60% improved performance compared to the latest GPUs by combining quantization techniques that reduce memory requirements while maintaining inference accuracy, and hardware designs optimized for this".
He further emphasized, "This technology has demonstrated the possibility of implementing high-performance, low-power infrastructure specialized for generative AI, and is expected to play a key role not only in AI cloud data centers but also in the AI transformation (AX) environment represented by dynamic, executable AI such as 'Agentic AI'."
This research was presented by Ph.D. student Minsu Kim and Dr. Seongmin Hong from HyperAccel Inc. as co-first authors at the '2025 International Symposium on Computer Architecture (ISCA)' held in Tokyo, Japan, from June 21 to June 25. ISCA, a globally renowned academic conference, received 570 paper submissions this year, with only 127 papers accepted (an acceptance rate of 22.7%).
※Paper Title: Oaken: Fast and Efficient LLM Serving with Online-Offline Hybrid KV Cache Quantization
※DOI: https://doi.org/10.1145/3695053.3731019
Meanwhile, this research was supported by the National Research Foundation of Korea's Excellent Young Researcher Program, the Institute for Information & Communications Technology Planning & Evaluation (IITP), and the AI Semiconductor Graduate School Support Project.
KAIST Invites World-Renowned Scholars, Elevating Global Competitiveness
< Photo 1. (From left) Professor John Rogers, Professor Gregg Rothermel, Dr. Sang H. Choi >
KAIST announced on June 27th that it has appointed three world-renowned scholars, including Professor John A. Rogers of Northwestern University, USA, as Invited Distinguished Professors in key departments such as Materials Science and Engineering.
Professor John A. Rogers (Northwestern University, USA) will be working with the Department of Materials Science and Engineering from July 2025 to June 2028 with Professor Gregg Rothermel (North Carolina State University, USA) working with the School of Computing from August 2025 to July 2026, and Dr. Sang H. Choi (NASA Langley Research Center, USA) with the Department of Aerospace Engineering from May 2025 to April 2028.
Professor John A. Rogers, a person of global authority in the field of bio-integrated electronics, has been leading advanced convergence technologies such as flexible electronics, smart skin, and implantable sensors. His significant impact on academia and industry is evident through over 900 papers published in top-tier academic journals like Science, Nature, and Cell, and he comes in an H-index of 240*. His research group, the Rogers Research Group at Northwestern University, focuses on "Science that brings Solutions to Society," encompassing areas such as bio-integrated microsystems and unconventional nanofabrication techniques. He is the founding Director of the Querrey-Simpson Institute of Bioelectronics at Northwestern University.
* H-index 240: An H-index is a measurement used to assess the research productivity and impact of an individual authors. H-index 240 means that 240 or more papers have been cited at least 240 times each, indicating a significant impact and the presumable status as a world-class scholar.
The Department of Materials Science and Engineering plans to further enhance its research capabilities in next-generation bio-implantable materials and wearable devices and boost its global competitiveness through the invitation of Professor Rogers. In particular, it aims to create strong research synergies by linking with the development of bio-convergence interface materials, a core task of the Leading Research Center (ERC, total research budget of 13.5 billion KRW over 7 years) led by Professor Kun-Jae Lee.
Professor Gregg Rothermel, a world-renowned scholar in software engineering, was ranked second among the top 50 global researchers by Communications of the ACM. For over 30 years, he has conducted practical research to improve software reliability and quality. He has achieved influential research outcomes through collaborations with global companies such as Boeing, Microsoft, and Lockheed Martin. Dr. Rothermel's research at North Carolina State University focuses on software engineering and program analysis, with significant contributions through initiatives like the ESQuaReD Laboratory and the Software-Artifact Infrastructure Repository (SIR).
The School of Computing plans to strengthen its research capabilities in software engineering and conduct collaborative research on software design and testing to enhance the reliability and safety of AI-based software systems through the invitation of Professor Gregg Rothermel. In particular, he is expected to participate in the Big Data Edge-Cloud Service Research Center (ITRC, total research budget of 6.7 billion KRW over 8 years) led by Professor In-Young Ko of the School of Computing, and the Research on Improving Complex Mobility Safety (SafetyOps, Digital Columbus Project, total research budget of 3.5 billion KRW over 8 years), contributing to resolving uncertainties in machine learning-based AI software and advancing technology.
Dr. Sang H. Choi, a global expert in space exploration and energy harvesting, has worked at NASA Langley Research Center for over 40 years, authoring over 200 papers and reports, holding 45 patents, and receiving 71 awards from NASA. In 2022, he was inducted into the 'Inventors Hall of Fame' as part of NASA's Technology Transfer Program. This is a rare honor, recognizing researchers who have contributed to the private sector dissemination of space exploration technology, with only 35 individuals worldwide selected to date. Dr. Choi's extensive work at NASA includes research on advanced electronic and energetic materials, satellite sensors, and various nano-technologies.
Dr. Choi plans to collaborate with Associate Professor Hyun-Jung Kim (former NASA Research Scientist, 2009-2024), who joined the Department of Aerospace Engineering in September of 2024, to lead the development of core technologies for lunar exploration (energy sources, sensing, in-situ resource utilization ISRU).
KAIST President Kwang Hyung Lee stated, "It is very meaningful to be able to invite these world-class scholars. Through these appointments, KAIST will further strengthen its global competitiveness in research in the fields of advanced convergence technology such as bio-convergence electronics, AI software engineering, and space exploration, securing our position as the leader of global innovations."