NAVER CLOVA @ ICLR 2022

Presentation of NAVER CLOVA and AI LAB @ ICLR 2022 (4/25~4/29)

12 papers by NAVER CLOVA have been accepted at the 2022 International Conference on Learning Representations (ICLR). NAVER CLOVA has emerged as the first Korean company to have double-digit paper selected by a global machine learning society.

Presentation Schedule

[Poster Session 1] Mon 25 Apr 6:30 p.m. — 8:30 p.m. (KST)

Baesung Park*(NAVER CLOVA), Sejung Kwon*(NAVER CLOVA), Daehwan Oh (Samgsung Research), Byeongwook Kim (NAVER CLOVA), Dongsoo Lee (NAVER CLOVA).Encoding Weights of Irregular Sparsity for Fixed-to-Fixed Model Compression

Hyeonmin Ha (SNU), Ji-Hoon Kim(NAVER CLOVA), Semin Park (Google), Byung-Gon Chun (SNU). SUMNAS: Supernet with Unbiased Meta-Features for Neural Architecture Search.

[Poster Session 2] Tue 26 Apr 2:30 a.m. — 4:30 a.m. (KST)

Luca Scimeca (NAVER AI Lab), Seong Joon Oh (NAVER AI Lab), Sanghyuk Chun (NAVER AI Lab), Michael Poli (NAVER AI Lab), Sangdoo Yun (NAVER AI Lab). Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective.

[Poster Session 3] Tue 26 Apr 10:30 a.m. — 12:30 p.m. (KST)

Hwanjun Song (NAVER AI Lab), Deqing Sun (Google Research), Sanghyuk Chun (NAVER AI Lab), Varun Jampani (Google Research), Dongyoon Han (NAVER AI Lab), Byeongho Heo (NAVER AI Lab), Wonjae Kim (NAVER AI Lab), Ming-Hsuan Yang (Google Research, UC Merced). ViDT: An Efficient and Effective Fully Transformer-based Object Detector.

Sihyun Yu (KAIST), Jihoon Tack (KAIST), Sangwoo Mo (KAIST), Hyunsu Kim (NAVER AI Lab), Junho Kim (NAVER AI Lab), Jung-Woo Ha (NAVER AI Lab), Jinwoo Shin (KAIST). Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks.

[Poster Session 4] Tue 26 Apr 6:30 p.m. — 8:30 p.m. (KST)

Yunji Kim (NAVER AI Lab), Jung-Woo Ha (NAVER AI Lab). Contrastive Fine-grained Class Clustering via Generative Adversarial Networks.

[Poster Session 5] Wed 27 Apr 2:30 a.m. — 4:30 a.m.(KST)

Ayush Jain*(USC), Norio Kosaka*(NAVER CLOVA), Kyung-Min Kim(NAVER CLOVA), Joseph J Lim(KAIST, USC, NAVER AI Lab). Know Your Action Set: Learning Action Relations for Reinforcement Learning.

[Poster Session 6] Wed 27 Apr 10:30 a.m. — 12:30 p.m. (KST)

Taewook Nam (KAIST), Shao-Hua Sun (USC), Karl Pertsch (USC), Sung Ju Hwang (KAIST), Joseph J Lim(KAIST, USC, NAVER AI Lab). Skill-based Meta-Reinforcement Learning.

Dongyoon Han (NAVER AI Lab), YoungJoon Yoo (NAVER CLOVA), Beomyoung Kim (NAVER CLOVA), Byeongho Heo (NAVER AI Lab). Learning Features with Parameter-Free Layers.

[Poster Session 7] Wed 27 Apr 6:30 p.m. — 8:30 p.m. (KST)

Hyunseo Koh (GIST, NAVER AI Lab), Dahyun Kim (GIST, NAVER AI Lab), Jung-Woo Ha (NAVER AI Lab), Jonghyun Choi (GIST, NAVER AI Lab). Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference.

[Poster Session 8] Thu 28 Apr 2:30 a.m. — 4:30 a.m. (KST)

Jun Yamada (U. of Oxford), Karl Pertsch (USC), Anisha Gunjal (USC), Joseph J Lim(KAIST, USC, NAVER AI Lab). Task-Induced Representation Learning.

[Poster Session 9] Thu 28 Apr 10:30 a.m. — 12:30 p.m. (KST)

Yooju Shin (KAIST), Susik Yoon (UIUC), Sundong Kim (IBS), Hwanjun Song (NAVER AI Lab), Jae-Gil Lee (KAIST), Byung Suk Lee (Univ. of Vermont). Coherence-based Label Propagation over Time Series for Accelerated Active Learning.

ICLR 2022 Social : ML in Korea

Thu 28 Apr 12:00 p.m. — 15:00 p.m. (KST)

Event Homepage (https://naver-career.gitbook.io/en/teams/clova-cic/events/iclr-2022-social-ml-in-korea)