CLOVA AI x KAIST Joint AI Workshop

On June 19, KAIST AI/ML and Clova AI held the second joint AI workshop. Leading professors and veteran researchers in artificial intelligence and machine learning gave lectures about their recent publications.

Lectures from the workshop (in Korean)

14:00-14:10Opening Remarks and AI in KAISTProf. Alice Oh
14:10-14:30ML for Underwater PerceptionProf. Ayoung Kim
14:30-14:50Human-AI InteractionProf. Juho Kim
14:50-15:10Lightweight Visual RecognitionYoungjoon Yoo Ph.D.
15:10-15:30Large-Scale Graph MiningProf. Kijung Shin
15:30-16:30Poster Session and Coffee BreakKAIST AI Labs
16:30-16:50Latest ML ResearchProf. Jinwoo Shin
16:50-17:10Information Theory-Based MLProf. Hye Won Chung
17:10-17:30Curiosity-Based RL and Practical AutoMLJihoon Kim Ph.D.
17:30-17:50Computational Social Science ProblemsProf. Meeyoung Cha
17:50-18:00Closing Remarks and Research Opportunity in Clova AIProf. Sung Kim

Between the lectures, 24 students from KAIST AI/ML also delivered a poster presentation on their research works.

NameResearch AdvisorPoster TitleThe Venue where the Research was Originally Presented (Conference, Journal, or under Review)
Hwanjun SongProf. Jae-Gil LeeSELFIE: Refurbishing Unclean Samples for Robust Deep LearningICML 2019
송경우Prof. Il-Chul MoonHierarchical Context enabled Recurrent Neural Network for RecommendationAAAI-19
Kyunghwan SonProf. Yung YiQTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement learningICML 2019
Dae Woo KimProf. Yung YiLearning to Schedule Communication in Multi-agent Reinforcement LearningICLR 2019
Wissam J. BaddarProf. Yong Man RoMode Variational LSTM Robust to Unseen Modes of Variation: Application to Facial Expression RecognitionAAAI
Hyungseok SongProf. Yung YiSolving Continual Combinatorial Selection via Deep Reinforcement LearningIJCAI
Raehyuk JungProf. Jean-Charles BazinDeep360Up: Deep learning-based approach for automatic upright adjustment of VR imagesPublished in IEEE VR 2019
Taewon JeongProf. Heeyoung KimLadder Capsule NetworkICML 2019
Dongkwan KimProf. Alice OhHomogeneity-Based Transmissive Process To Model True and False News in Social NetworksWSDM 2019
JinYeong BakProf. Alice OhVariational Hierarchical User-based Conversation ModelUnder Review
박성준Prof. Alice OhConversation model fine tuning for classifying client’s utterances in counseling dialogues NAACL 2019
Giwon HongProf. Sung-Hyon Myaeng )Aligning Open IE Relations and KB Relations using a Siamese Network Based on Word EmbeddingIWCS 2019
Taehyun KimProf. Se-Young YunOrthogonal Feature Regularization: A Novel Approach for training robust modelsUnder review of NeurIPS 2019
Taegyun KwonProf. Juhan NamGraph Neural Network for Music Score Dataand Modeling Expressive Piano PerformanceICML 2019
김수민Prof. Sungeui YoonSingle Image Reflection Removal with Physically-based RenderingUnder review of ICCV
Tae KihyunProf. Steven Euijong WhangData Cleaning for Accurate, Fair, and Robust Models: A Big Data – AI Integration Approach3rd Int’l Workshop on Data Management for End-to-End Machine Learning, DEEM @ ACM SIGMOD, June 2019
Hankook LeeProf. Jinwoo ShinLearning What and Where to TransferICML2019
Jongheon JeongProf. Jinwoo ShinTraining CNNs with Selective Allocation of ChannelsICML 2019
Geon HeoProf. Steven WhangInspector Gadget: Massive Image Labeling for Machine Learningunder review
Jinhan KimProf. Shin YooGuiding Deep Learning System Testing using Surprise AdequacyICSE 2019
Giseop KimProf. Ayoung Kim1-Day Learning, 1-Year Localization: Long-term LiDAR Localization using Scan Context ImageICRA 2019
Hajin ShimProf. Eunho Yang Joint Active Feature Acquisition and Classification with Variable-Size Set EncodingNeurIPS 2018
Jinwon YoonProf. Hwasoo YeoAI-based Mobility: Traffic Predictive Solutions for Large Urban AreaConference

Among 24 presenters, Jiyoung Han and Taegyun Kwon won the best post award and received the cash prize of 500,000 South Korean Won each.

(From left to right) Alice Oh, Jiyoung Han, and Sung Kim

(From left to right) Sung Kim, Taegyun Kwon, and Alice Oh