Welcome to ODAI Lab.

At ODAI@UOS, our research delves into cutting-edge on-device AI technologies, aiming to bring advanced intelligence directly to edge devices. We primarily focus on three critical areas: Lightweight AI, Secure AI, and Physical AI.

1. Lightweight AI: We develop highly efficient models for resource-constrained environments, optimizing large language models (LLM) via techniques like BitNet-like quantization and leveraging spiking neural networks (SNN) for enhanced energy efficiency.

2. Secure AI: Our work strengthens AI system resilience against various threats, investigating methods to counter adversarial attacks on AI models, including LLM security and those impacting tasks like SNN security.

3. Physical AI: We enable AI systems to intelligently interact with the real world by designing systems that ensure real-time processing and accurate decision-making for dynamic tasks like multi-object tracking and other computer vision tasks, facilitating robust operations in physical environments.

News

• [September 2025] NRF 미래도전연구지원사업 과제선정, "초저전력 뉴로모픽 AI 반도체 기반 실시간 LMM 플렛폼 연구", 2025.9-2030.8, 연2억(총10억)원, 연구책임자: 백형부

• [September 2025] A paper entitled "ARES: Adaptive Robust Object Detection Framework for Enhancing Real-time Performance in Autonomous Vehicle Systems" has been accepted to JSA.

• [August 2025] A paper entitled "CF-DETR: Coarse-to-Fine Transformer for Real-Time Object Detection" has been accepted to RTSS'25.

• [May 2025] A paper entitled "BankTweak: Adversarial Attack against Multi-Object Trackers by Manipulating Feature Banks" has been accepted to IJCAI'25.

• [January 2025] A paper entitled "Real-Time Scheduling for Multi-Object Tracking Tasks in Regions with Different Criticalities" has been accepted to JSA.

• [August 2024] Three papers have been accepted to ICPR'24.

• [July 2024] A paper entitled "Batch-MOT: Batch-Enabled Real-Time Scheduling for Multi-Object Tracking Tasks" has been accepted to ACM EMSOFT'24 and IEEE TCAD.

• [March 2024] On-Device Artificial Intelligence (ODAI) laboratory has been launched at the University of Seoul (UOS).