Ubiquitous AI Lab (UAILab)
Ubiquitous AI Lab (UAILab)
Ulsan National Institute of Science and Technology (UNIST) · Computer Science and Engineering
Professor
Prof. 공태식
Professor's page · publicationsAbout
공태식 교수 연구실(유비쿼터스 인공지능 연구실, UAILab)은 UNIST 컴퓨터공학과·인공지능대학원 소속으로, 온디바이스 AI와 인간 중심 AI, 유비쿼터스 컴퓨팅을 연구한다. 다양한 엣지 기기를 위한 알고리즘·시스템 수준 혁신으로 적응적이고 효율적인 온디바이스 AI 시스템을 구축하며, 공 교수는 KAIST 박사(2023)와 Google Ph.D. Fellowship 수상 후 Bell Labs 연구원을 거쳤다.
Research keywords
Recent papers
- Can Agents Work for Everyone? Cross-User Reliability for Mobile GUI Agents in Personalized User InterfacesPreprintarXiv (Cornell University) · Oct 6
- Adapting Vision-Language-Action Models to Unknown Visual Disruptions During ExecutionPreprintarXiv (Cornell University) · Oct 6
- VLA-ZO: Fast Zeroth-Order Adaptation for Vision-Language-Action ModelsPreprintarXiv (Cornell University) · Oct 5
From OpenAlex · papers whose author affiliation matches this university
Selected publications
- From Volume to Value: Preference-Aligned Memory Construction for On-Device RAGICML · 2026
- ExPerT: Personalizing LLM Responses to Users' Domain Expertise via Query-Wise Semantic and Keystroke Behavioral CuesACL · 2026
- SNAP: Low-Latency Test-Time Adaptation with Sparse UpdatesNeurIPS · 2025
- Test-Time Adaptation with Binary FeedbackICML · 2025
- DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI AcceleratorsNeurIPS · 2024
- AETTA: Label-Free Accuracy Estimation for Test-Time AdaptationCVPR · 2024
Labs doing related research
Labs that recently published on topics this lab's recent papers share
Statistical Inference Lab
KAIST · Graduate School of AI
Pivot-SD: Efficient Self-Distillation for Masked Diffusion Language ModelsPreprintarXiv (Cornell University) · Oct 2Shared topic: Topic Modeling
Yoo Changdong Lab
KAIST · Electrical Engineering
Progress-Guided Preference Generation for Aligning Generative Control PoliciesNewPreprintarXiv (Cornell University) · Oct 19Shared topic: Domain Adaptation and Few-Shot Learning
Kim Junmo Lab
KAIST · Electrical Engineering
Do LLMs Learn from Rewards in Context? : Rethinking the role of reward in In-Context RLNewPreprintarXiv (Cornell University) · Oct 8Shared topic: Domain Adaptation and Few-Shot Learning
Other labs in this department
- Computer Systems Security Lab (CSSL)Recruiting
Hyungon Moon
개인정보보호 머신러닝, 기밀 클라우드, 시스템 보안, 컴퓨터 구조, 운영체제
- WebSec LabRecruiting
Seongil Wi
웹 보안, 소프트웨어 보안
- 이주용 교수 연구실Recruiting
Jooyong Yi
Software testing such as fuzzing, Program analysis for program repair and verification
- Next-generation Networks and Systems Laboratory (N2SL)Recruiting
Youngbin Im
네트워크 시스템, 대규모 시스템, 모바일 시스템, 신생 응용
- Ultimate Interface LabRecruiting
Seongkook Heo
인간-컴퓨터 상호작용, 인터랙티브 시스템, 에이전틱 인터랙션, 물리적 사용자 인터페이스, 접근성 기술
- Programming Languages Research Group (PLRG)Recruiting
Jaemin Hong
프로그래밍 언어, 소프트웨어 공학, 정적 분석, 프로그램 변환