Core ML & AI

Papers presented at the venues related to ML and AI such as ICLR, NeurIPS, ICML, AAAI, etc.

2021

Michael Poli, Stefano Massaroli, Luca Scimeca, Seong Joon Oh, Sanghyuk Chun, Atsushi Yamashita, Hajime Asama, Jinkyoo Park, Animesh Garg. Neural Hybrid Automata: Learning Dynamics with Multiple Modes and Stochastic Transitions. arXiv. 2021.

Junbum Cha, Sanghyuk Chun, Kyungjae Lee, Han-Cheol Cho, Seunghyun Park, Yunsung Lee, Sungrae Park. SWAD: Domain Generalization by Seeking Flat Minima. arXiv. 2021.

Wonjae Kim, Bokyung Son (Kakao Enterprise), Ildoo Kim (Kakaobrain), ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision. ICML 2021.

Jungsoo Park, Gyuwan Kim, Jaewoo Kang (Korea U.). Consistency Training with Virtual Adversarial Discrete Perturbation. arXiv. 2021

Joonhyun Jeong, Sungmin Cha, Youngjoon Yoo, Sangdoo Yun, Jongwon Choi (Chung-Ang Univ.). Bayesian Perspective on Visual Data Augmentation for Efficient Utilization of Sub-sampled Data. Synthetic Data Generation [email protected] 2021.

Kyung-Wha Park (SNU), Jung-Woo Ha, JungHoon Lee (Soongsil Univ.), Sunyoung Kwon (Pusan Univ.), Kyung-Min Kim, Byoung-Tak Zhang (SNU). M2FN: Multi-step modality fusion for advertisement image assessment. Applied Soft Computing. 2021

Byeongho Heo, Sanghyuk Chun, Seong Joon Oh, Dongyoon Han, Sangdoo Yun, Gyuwan Kim, Youngjung Uh, Jung-Woo Ha. AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights. ICLR 2021.

Seonhoon Kim, Seohyeong Jeong, Eunbyul Kim, Inho Kang, Nojun Kwak. Self-supervised Pre-training and Contrastive Representation Learning for Multiple-choice Video QA. AAAI 2021.

Geonmo Gu, Byungsoo Ko, Han-Gyu Kim. Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning. AAAI 2021.

Beomyoung Kim, Sangeun Han (KAIST), Junmo Kim (KAIST). Discriminative Region Suppression for Weakly-Supervised Semantic Segmentation. AAAI 2021.

Song Park, Sanghyuk Chun, Junbum Cha, Bado Lee, Hyunjung Shim (Yonsei Univ.). Few-shot Font Generation with Localized Style Representations and Factorization. AAAI 2021.

Mingi Ji, Byeongho Heo, Sungrae Park. Show, Attend and Distill: Knowledge Distillation via Attention-based Feature Matching. AAAI 2021.

Xiaodong Gu, Kang Min Yoo, Jung-Woo Ha. DialogBERT: Discourse-Aware Response Generation via Learning to Recover and Rank Utterances. AAAI 2021.

2020

Dasol Hwang (Korea Univ), Jinyoung Park (Korea Univ), Sunyoung Kwon, Kyung-Min Kim, Jung-Woo Ha, Hyunwoo J. Kim (Korea Univ). Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs. NeurIPS 2020. 2020

Kyuyong Shin, Wonyoung Shin, Jung-Woo Ha, Sunyoung Kwon. Graphs, Entities, and Step Mixture. GRL+ [email protected] 2020. 2020

Wonyoung Shin, Jung-Woo Ha, Shengzhe Li, Yongwoo Cho, Hoyean Song, Sunyoung Kwon. Which Strategies Matter for Noisy Label Classification? Insight into Loss and Uncertainty. ArXiv. 2020

Taehoon Kim, Youngjoon Yoo, Jihoon Yang. StatAssist & GradBoost: A Study on Optimal INT8 Quantization-aware Training from Scratch. ArXiv. 2020

Muhammad Ferjad Naeem, Seong Joon Oh, Youngjung Uh, Yunjey Choi, Jaejun Yoo. Reliable Fidelity and Diversity Metrics for Generative Models. ICML 2020. 2020

Hyojin Bahng, Sanghyuk Chun, Sangdoo Yun, Jaegul Choo (Korea Univ.), Seong Joon Oh. Learning De-biased Representations with Biased Representations. ICML 2020. 2020

Junho Kim, Minjae Kim, Hyeonwoo Kang, Kwang Hee Lee. U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation. ICLR 2020. 2020

Geonmo Gu, Byung Soo Ko. Symmetrical synthesis for deep metric learning. AAAI 2020. 2020

Pilhyeon Lee (Yonsei Univ.), Youngjung Uh, Heyran Byun (Yonsei Univ.). Background Suppression Networks for Weakly-supervised Temporal Action Localization. AAAI 2020. 2020

2019

Seunghyun Park, Seung Shin, Bado Lee, Junyeop Lee, Jaeheung Surh, Minjoon Seo, Hwalsuk Lee. CORD: A Consolidated Receipt Dataset for Post-OCR Parsing. Document Intelligence [email protected] 2019. 2019

YoungJoon Yoo, Dongyoon Han, Sangdoo Yun. EXTD: Extremely Tiny Face Detector via Iterative Filter Reuse. arXiv. 2019

Minz Won, Sanghyuk Chun, Xavier Serra. Visualizing and Understanding Self-Attention Based Music Tagging. Machine Learning for Music Discovery Workshop (Contributed Talk)@ICML 2019. 2019

Sanghyuk Chun, Seong Joon Oh, Sangdoo Yun, Dongyoon Han, Junsuk Choe, Youngjoon Yoo. An Empirical Evaluation on Robustness and Uncertainty of Regularization methods Robustness and Uncertainty. Uncertainty & Robustness in Deep Learning [email protected] 2019. 2019

Youngjin Kim, Wontae Nam, Hyunwoo Kim, Ji-Hoon Kim, Gunhee Kim. Curiosity-Bottleneck: Exploration By Distilling Task-Specific Novelty. ICML 2019. 2019

Xiaodong Gu, Kyunghyun Cho, Jung-Woo Ha, Sunghun Kim. DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder. ICLR 2019. 2019

Sang-Woo Lee, Tong Gao, Sohee Yang, Jaejun Yoo, Jung-Woo Ha. Large-Scale Answerer in Questioner's Mind for Visual Dialog Question Generation. ICLR 2019. 2019

Seong Joon Oh, Andrew C. Gallagher, Kevin P. Murphy, Florian Schroff, Jiyan Pan, Joseph Roth. Modeling Uncertainty with Hedged Instance Embeddings. ICLR 2019. 2019

Jisung Hwang, Younghoon Kim, Sanghyuk Chun, Jaejun Yoo, Ji-Hoon Kim, Dongyoon Han. Where To Be Adversarial Perturbations Added? Investigating and Manipulating Pixel Robustness Using Input Gradients. Debugging Machine Learning Models [email protected] 2019. 2019

Sungrae Park, Jun-Keon Park, Su-Jin Shin, Il-Chul Moon. Adversarial Dropout for Recurrent Neural Networks. AAAI 2019. 2019

Byeongho Heo, Minsik Lee, Sangdoo Yun, Jin Young Choi. Knowledge Distillation with Adversarial Samples Supporting Decision Boundary. AAAI 2019. 2019

Byeongho Heo, Minsik Lee, Sangdoo Yun, Jin Young Choi. Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons. AAAI 2019, Oral. 2019

Sunghyun Park, Seung-Won Hwang, Fuxiang Chen, Jaegul Choo, Jung-Woo Ha, Sunghun Kim. Paraphrase Diversification Using Counterfactual Debiasing. AAAI 2019. 2019

Jamin Shin, Andrea Madotto, Minjoon Seo, Pascale Fung. End-to-End Question Answering Models for Goal-Oriented Dialog Learning. Workshop on DSTC 2019 (at AAAI). 2019

Weonyoung Joo, Wonsung Lee, Sungrae Park, Il-Chul Moon. Dirichlet Variational Autoencoder. arXiv. 2019

~ 2018

Jinwoong Kim, Minkyu Kim, Heungseok Park, Ernar Kusdavletov, Adrian Kim, Ji-Hoon Kim, Jung-Woo Ha, Nako Sung. CHOPT: Automated Hyperparameter Optimization Framework for Cloud-Based Machine Learning Platforms. arXiv. 2018

Sang-Woo Lee, Yu-Jung Heo, Byoung-Tak Zhang. Answerer in Questioner's Mind: Information Theoretic Approach to Goal-Oriented Visual Dialog. NeurIPS 2018 (Spotlight).

Sihyeon Seong (KAIST), Yekang Lee (KAIST), Youngwook Kee (KAIST), Dongyoon Han, Junmo Kim (KAIST). Towards Flatter Loss Surface via Nonmonotonic Learning Rate Scheduling. UAI 2018.

Minjoon Seo, Sewon Min, Ali Farhadi, Hannaneh Hajishirzi. Neural Speed Reading via Skim-RNN. ICLR 2018.

Nako Sung, Minkyu Kim, Hyunwoo Jo, Youngil Yang, Jinwoong Kim, Leonard Lausen, Youngkwan Kim, Gayoung Lee, Donghyun Kwak, Jung-Woo Ha, Sung Kim. NSML: A Machine Learning Platform That Enables You to Focus on Your Models. NIPS WS ML Systems 2017. 2017

You Jin Kim, Yun-Geun Lee, Jeong Whun Kim, Jin Joo Park, Borim Ryu, Jung-Woo Ha. Highrisk Prediction from Electronic Medical Records via Deep Attention Networks. NIPS WS ML4H 2017. 2017

Sang-Woo Lee, Jin-Hwa Kim, Jaehyun Jun, Jung-Woo Ha, Byoung-Tak Zhang. Overcoming Catastrophic Forgetting by Incremental Moment Matching. NIPS 2017. 2017

Jungyeul Park, Loic Dugast, Jeen-Pyo Hong, Chang-Uk Shin, Jeong-Won Cha. Building a Better Bitext for Structurally Different Languages through Self-Training. Workshop on Curation and Applications of Parallel and Comparable Corpora in IJCNLP 2017. 2017

Jin-Hwa Kim, Kyoung-Woon On, Jeonghee Kim, Jung-Woo Ha, Byoung-Tak Zhang. Hadamard product for low-rank bilinear pooling. ICLR 2017. 2017