Data-Intensive AI Computing &
Systems Laboratory

Soyang Baek, Bodon Jeong, Hongsu Byun, and Sungyong Park’s paper on “QUICKTOPIA: Iteration-Level GPU Frequency Control for Energy–Latency Co-Optimization in LLM Inference” has been accepted in International Symposium on Cluster, Cloud, and Internet Computing (CCGrid 2026).

Kihwan Kim, Hyungsun Yoo, Woojung Kim, Donghyun Min, and Youngjae Kim's paper on “VEX: Scaling HNSW-Based Vector Search with DPU Memory and Parallelism” has been accepted in International Symposium on Cluster, Cloud, and Internet Computing (CCGrid 2026).

Jaewan Park, Kyungwook Min, Sungjin Byeon, Taewan Noh, Hyungi Park, and Youngjae Kim's paper on “BucketLSM: Breaking the Compaction Scalability Barrier in LSM-Based Key-Value Stores” has been accepted in International Symposium on Cluster, Cloud, and Internet Computing (CCGrid 2026).

Jinwoo Kim, Kihyun Kim, Hyunsun Chung and Youngjae Kim's paper on “LLM-Pilot: SLO-Aware and Cost-Efficient LLM Serving on Public Cloud VM Clusters via Offloading” has been accepted in International Symposium on Cluster, Cloud, and Internet Computing (CCGrid 2026).

Junghyun Ryu, Soon Hwang, Junhyeok Park, Seonghoon Ahn, and Youngjae Kim’s paper on “Integrating Distributed SQL Query Engines with Object-Based Computational Storage” has been accepted in International Workshop on Data Analysis and Reduction for Big Scientific Data (DRBSD 2025).

Sangyun Lee, Sungjin Byeon, Soon Hwang, Jaewan Park, Awais Khan, and Youngjae Kim’s paper on “Lightweight I/O Path Design for Write Isolation in FDP-backed In-Memory Databases” has been accepted in International Parallel Data Systems Workshop (PDSW 2025).

Kyuri Park, Sungmin Yoon, Farid Talibli, Sungyong Park, Awais Khan, and Youngjae Kim’s paper on “DoCeph: DPU-Offloaded Messaging in Ceph for Reduced Host CPU Utilization” has been accepted in International Workshop on RESource DISaggregation in High-Performance Computing (RESDIS 2025).

Yeonwoo Jeong, Hyunji Cho, Kyuri Park, Youngjae Kim, and Sungyong Park’s paper on “CALL: Context-Aware Low-Latency Retrieval in Disk-Based Vector Databases” has been accepted in 32nd International Conference on High Performance Computing, Data, and Analytics (HiPC 2025).

Bodon Jeong Hongsu Byun and Sungyong Park's paper on "PACMAN: Power Usage-Aware Capping and Management for All-Flash Storage Servers" has been accepted in 33rd International Symposium on the Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS 2025).

Hyunsun Chung, Junhyeok Park, Taewan Noh, Seonghoon Ahn, Kihwan Kim and Youngjae Kim's paper on "OPENCXD: An Open Real-Device-Guided Hybrid Evaluation Framework for CXL-SSDs" has been accepted in 33rd International Symposium on the Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS 2025).

Kihyun Kim, Jinwoo Kim and Youngjae Kim's paper on "FLEXLLM: Flexible and Cost-Efficient LLM Serving with Heterogeneous GPUs" has been accepted in 33rd International Symposium on the Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS 2025).

Junhyeok Park (MS student) won the Best Paper Award at HotStorage 2025 for "ByteExpress: A High-Performance and Traffic-Efficient Inline Transfer of Small Payloads over NVMe". Congratulations! 🎉

Hongsu Byun, Honghyeon Yoo and Sungyong Park's paper on "Revisiting Multi-threaded Compaction in LSM-trees: Enabling Compaction Pipelining" has been accepted in International Conference on Parallel Processing (ICPP 2025).

Hajin Moon has joined us as a new MS student. Welcome on board!

Kihyun Kim, Jinwoo Kim, Hyunsun Chung and Youngjae Kim's paper on "Cost-Efficient VM Selection for Cloud-Based LLM Inference with KV Cache Offloading" has been accepted in IEEE International Conference on Cloud Computing (CLOUD 2025).

Hyungwoo Lee, Kihyun Kim, Jinwoo Kim, and Youngjae Kim's paper on "Disk-Based Shared KV Cache Management for Fast Inference in Multi-Instance LLM RAG Systems" has been accepted in IEEE International Conference on Cloud Computing (CLOUD 2025).

Junhyeok Park, Youngjae Kim's paper on "Maximizing Interconnect Bandwidth and Efficiency in NVMe-Based Key-Value SSDs with Fine-Grained Value Transfer" has been accepted for publication in an upcoming issue of IEEE Micro.

Junhyeok Park, Youngjae Kim's paper on "ByteExpress: A High-Performance and Traffic-Efficient Inline Transfer of Small Payloads over NVMe" has been accepted in ACM Workshop on Hot Topics in Storage and File Systems(HotStorage 2025).

Safdar Jamil, Awais Khan, Xubin He, Youngjae Kim's paper on "DedupKV: A Space-Efficient and High Performance Key-Value Store via Fine-Grained Deduplication" has been accepted in International Conference on Supercomputing(ICS 2025).

Two new PhDs! Dr.Chang-Gyu Lee and Dr.Safdar Jamil. Congratulations! 🎉

Seoyeong Lee, Junghwan Park, Yoochan Kim and Youngjae Kim's paper on "Leveraging Pre-Built Catalogs and Object-Level Scheduling to Eliminate I/O Bottlenecks" has been accepted in IEEE Access.

The 4 papers titled StreamRAG(Yeonwoo Jeong), ECO-KVS(Jeeseob Kim, Hongsu Byun), EQUILIBRIA(Sejeong Oh), MemoryBridge(Yoo-Chan Kim) have been accepted for presentation at the 25th IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing (CCGrid).

Hyunsun Chung, Seonghoon Ahn, Sangyun Lee, Hyungsun Yoo, Kyungwook Min, Seungjae Lee, Hyunji Cho, Sungmin Yoon, Jihoon Woo have joined us as new MS students. Welcome on board!

Hyungsun Yoo, Kihwan Kim, Junghyun Ryu, Hongsu Byun, Youngjae Kim's paper titled "Designing a Multi-CSD-based Document Database to Improve Query Throughput" has been selected as the best paper presentation award at Korea Software Congress (KSC'24).

Kihwan Kim, Hyunsun Chung, Seonghoon Ahn, Junhyeok Park, Safdar Jamil, Hongsu Byun, and Youngjae Kim's paper on "KVAccel: A Novel Write Accelerator for LSM-Tree-Based KV Stores with Host-SSD Collaboration" has been accepted in International Parallel and Distributed Processing Symposium (IPDPS).

Kyuli Park, Dongjae Lee, Yeonwoo Jeong, Sungyong Park's paper titled "Towards an Asynchronous Commit in Micro-batch Streaming Systems with Log-Structured Merge-tree based Key-Value Store" has been accepted in Cluster Computing Journal (SCIE).

Research in the field of AI Systems: Kihyun Kim, and Youngjae Kim's paper on "DRAM 기반 스토리지를 활용한 RAG 기반 LLM 추론 가속화 연구" has been accepted in KCS 2025.

Research in the field of AI Systems: Hyungwoo Lee, Kihyun Kim, and Youngjae Kim's paper on "High-Performance LLM RAG System Utilizing Disk-Based KV Cache in Vector Database" has been accepted in KSC 2024.

Research in the field of AI Systems: Jinwoo Kim, Kihyun Kim, Yoochan Kim and Youngjae Kim's paper on "Resolving I/O Bottlenecks through Partition Prediction and Preloading in Large-Scale Disk-based GNN Training" has been accepted in KSC 2024.

Safdar Jamil, Joseph Ro and Youngjae Kim's paper on "Efficient Data Placement in Deduplication enabled ZenFS via CRC-Based Prediction" has been accepted in IEEE Access.

GyeongHwan Jung, Yeonwoo Jeong, Kyuri Park, Dongjae Lee, Hongsu Byun, Suyeon Lee, Sungyong Park's paper on "dStream: An Online-based Dynamic Operator-level Query Mapping Scheme on Discrete CPU-GPU Architectures" has been accepted in IEEE Access.