More Realistic Than Reality!

Search
Close
Search
 
  • home
  • 교수소개
  • 전임교수

교수소개

전임교수

  • 부교수 Computer Science
  • 우홍욱
    Lab CSI Agent

관심분야

Reinforcement Learning,  Embodied Agent, System Intelligence

학력

  • Ph.D in Computer Science, University of Texas at Austin

약력/경력

  • 삼성전자 삼성리서치 상무, 랩장

학술지 논문

  • (2023)  A Maturity Model for Trustworthy AI Software Development.  APPLIED SCIENCES-BASEL.  13,  8
  • (2023)  A Configurable Model-Based Reinforcement Learning Framework for Disaggregated Storage Systems.  IEEE ACCESS.  11, 
  • (2022)  Sample-Efficient Deep Learning Techniques for Burn Severity Assessment with Limited Data Conditions.  APPLIED SCIENCES-BASEL.  12,  14
  • (2022)  Toward an Effective Bug Triage System Using Transformers to Add New Developers.  JOURNAL OF SENSORS.  2022, 
  • (2022)  A Graph Convolution Network-Based Bug Triage System to Learn Heterogeneous Graph Representation of Bug Reports.  IEEE ACCESS.  10, 
  • (2021)  A Global DAG Task Scheduler Using Deep Reinforcement Learning and Graph Convolution Network.  IEEE ACCESS.  9, 
  • (2021)  Repot: Transferable Reinforcement Learning for Quality-centric Networked Monitoring in Various Environments.  IEEE ACCESS.  9, 
  • (2021)  Efficient User-Level Multi-Path Utilization in RDMA Networks.  IEEE ACCESS.  9, 
  • (2021)  Differentiable Ranking Metric Using Relaxed Sorting for Top-K Recommendation.  IEEE ACCESS.  9, 
  • (2021)  Gemma: Reinforcement Learning-Based Graph Embedding and Mapping for Virtual Network Applications.  IEEE ACCESS.  9, 
  • (2021)  멀티코어 환경을 위한 강화학습 기반 캐시 파티셔닝.  정보과학회논문지.  48,  6
  • (2020)  rocorl: Transferable Reinforcement Learning-Based Robust Control for Cyber-Physical Systems With Limited Data Updates.  IEEE ACCESS.  8, 
  • (2020)  Applying Convolutional Neural Networks With Different Word Representation Techniques to Recommend Bug Fixers.  IEEE ACCESS.  8, 
  • (2020)  Panda: Reinforcement Learning-Based Priority Assignment for Multi-Processor Real-Time Scheduling.  IEEE ACCESS.  8, 
  • (2020)  Continual Prediction of Bug-Fix Time Using Deep Learning-Based Activity Stream Embedding.  IEEE ACCESS.  8, 
  • (2019)  SCARL: Attentive Reinforcement Learning-Based Scheduling in a Multi-Resource Heterogeneous Cluster.  IEEE ACCESS.  7,  1
  • (2019)  Resource-Efficient Sensor Data Management for Autonomous Systems Using Deep Reinforcement Learning.  SENSORS.  19,  20
  • (2019)  Event-Triggered Ephemeral Group Communication and Coordination over Sound for Smart Consumer Devices.  SENSORS.  19,  8
  • (2016)  Quality Measurement of Push Services for Smart Devices.  WIRELESS PERSONAL COMMUNICATIONS.  88,  2

특허/프로그램

  • ELECTRONIC DEVICE AND METHOD FOR ACCESSING SERVER BY SAME.  US 11,455,363 B2.  20220927.  미국
  • METHOD FOR RECEIVING CONTENT FROM EXTERNAL DEVICE AND ELECTRONIC DEVICE THEREFOR.  US 11,330,066 B2.  20220510.  미국
  • System for providing function as a service (FaaS) and operating method of system.  16/058,597.  20210921.  미국
  • 강화학습 기반 센서 데이터 관리 방법 및 시스템.  10-2019-0175671.  20201215.  대한민국
  • DISPLAY APPARATUS AND CONTROL METHOD THEREOF.  US 10,809,896 B2.  20201020.  미국
  • SYSTEM AND METHOD OF PROVIDING SENSING DATA TO AN ELECTRONIC DEVICE USING A TEMPLATE TO IDENTIFY A DATA TYPE AND FORMAT FOR THE ELECTRONIC DEVICE.  US 10,701,532 B2.  20200630.  미국
  • USER TERMINAL DEVICE AND METHOD FOR PROVIDING WEB SERVICE THEREOF.  US 10 , 397 , 760 B2.  20190827.  미국
  • Information processing apparatus and control method thereof.  US 10,097,976 B2.  20181009.  미국
  • Electronic apparatus, server, and control method of system.  US 9,992,140 B2.  20180606.  미국
  • Terminal Apparatus and Method of Controlling Terminal Apparatus.  US 9,553,790 B2.  20170124.  미국
  • Apparatus and Method for Extending Network Area.  US 9,531,561 B2.  20161227.  미국
  • ELECTRONIC APPARATUS, NETWORK SYSTEMAND METHOD FOR ESTABLISHING PRIVATE NETWORK.  US 9,307,030 B2.  20160405.  미국
  • Method and Apparatus for Constructing a Widget Environment.  US 9,298,475 B2.  20160329.  미국
  • APPARATUS AND METHOD FOR EXTENDING UPNP NETWORKAREA.  US 9,009,255 B2.  20150414.  미국

학술회의논문

  • (2024)  Offline Policy Learning via Skill-step Abstraction for Long-horizon Goal-Conditioned Tasks.  International Joint Conference on Artificial Intelligence.  대한민국
  • (2024)  Pareto Inverse Reinforcement Learning for Diverse Expert Policy Generation.  International Joint Conference on Artificial Intelligence.  대한민국
  • (2024)  Model Adaptation for Time Constrained Embodied Control.  Conference on Computer Vision and Pattern Recognition.  미국
  • (2024)  Risk-Conditioned Reinforcement Learning: A Generalized Approach for Adapting to Varying Risk Measures.  AAAI Conference on Artificial Intelligence.  캐나다
  • (2024)  Robust Policy Learning via Offline Skill Diffusion.  AAAI Conference on Artificial Intelligence.  캐나다
  • (2024)  SemTra: A Semantic Skill Translator for Cross-Domain Zero-Shot Policy Adaptation.  AAAI Conference on Artificial Intelligence.  캐나다
  • (2023)  Efficient Policy Adaptation with Contrastive Prompt Ensemble for Embodied Agents.  Conference on Neural Information Processing Systems.  미국
  • (2023)  One-shot Imitation in a Non-Stationary Environment via Multi-Modal Skill.  International Conference on Machine Learning.  미국
  • (2022)  Skills Regularized Task Decomposition for Multi-task Offline Reinforcement Learning.  Conference on Neural Information Processing Systems.  미국
  • (2022)  Federated Offline Reinforcement Learning for Autonomous Systems.  International Conference on Computer and Communication Engineering (CCCE 2022).  이탈리아
  • (2022)  An Efficient Combinatorial Optimization Model Using Learning-to-Rank Distillation.  AAAI Conference on Artificial Intelligence.  캐나다
  • (2022)  Structure Learning-Based Task Decomposition For Reinforcement Learning In Non-Stationary Environments.  AAAI Conference on Artificial Intelligence.  캐나다
  • (2022)  Iterative Pruning-based Model Compression for Pose Estimation on Resource-constrained Devices.  International Conference on Machine Vision and Applications (ICMVA 2023).  싱가포르
  • (2022)  Mean-variance Based Risk-sensitive Reinforcement Learning with Interpretable Attention.  International Conference on Machine Vision and Applications (ICMVA 2023).  싱가포르
  • (2022)  Transfer Learning based Precise Pose Estimation with Insufficient Data.  International Conference on Machine Vision and Applications (ICMVA 2023).  싱가포르
  • (2022)  Reinforcement Learning based Load Balancing in a Distributed Heterogeneous Storage System.  International Conference on Information Networking (ICOIN).  대한민국
  • (2021)  제한된 네트워크 환경에서의 전이 강화 학습 기반 드론 운행 기법.  한국항공우주학회.  대한민국
  • (2021)  GNN 을 활용한 강화학습 기반 Virtual Link Mapping 알고리즘.  한국통신학회 학술대회논문집.  대한민국
  • (2021)  ML for RT: Priority Assignment Using Machine Learning.  IEEE Real-Time and Embedded Technology and Applications Symposium.  미국
  • (2021)  GPU-Ether: GPU-native Packet I/O for GPU Applications on Commodity Ethernet.  IEEE Conference on Computer Communications.  미국