Selected Publication

[4] Diffusion Rejection Sampling (DiffRS)

• Byeonghu Na, Yeongmin Kim, Minsang Park, Donghyeok Shin, Wanmo Kang, and Il-Chul Moon

• ICML 2024  (The Forty-first International Conference on Machine Learning)

[3] Label-Noise Robust Diffusion Models (TDSM)

• Byeonghu Na, Yeongmin Kim, HeeSun Bae, Jung Hyun Lee, Se Jung Kwon, Wanmo Kang, and Il-Chul Moon

• ICLR 2024  (The Twelfth International Conference on Learning Representations)

• [paper] [code]

[2] Maximum Likelihood Training of Implicit Nonlinear Diffusion Models (INDM)

• Dongjoun Kim*, Byeonghu Na*, Se Jung Kwon, Dongsoo Lee, Wanmo Kang, and Il-Chul Moon

• NeurIPS 2022 (The Conference on Neural Information Processing Systems)

• [paper] [code]

[1] Deep Generative Positive-Unlabeled Learning under Selection Bias (VAE-PU)

• Byeonghu Na, Hyemi Kim, Kyungwoo Song, Weonyoung Joo, Yoon-Yeong Kim, and Il-Chul Moon

• CIKM 2020  (The 29th ACM International Conference on Information and Knowledge Management)

• [paper] [code]

International Conference

[14] Reward-based Input Construction for Cross-document Relation Extraction (REIC)

• Byeonghu Na*, Suhyeon Jo*, Yeongmin Kim, and Il-Chul Moon

• ACL 2024  (The 62nd Annual Meeting of the Association for Computational Linguistics)

[13] Diffusion Rejection Sampling (DiffRS)

• Byeonghu Na, Yeongmin Kim, Minsang Park, Donghyeok Shin, Wanmo Kang, and Il-Chul Moon

• ICML 2024  (The Forty-first International Conference on Machine Learning)

[12] Label-Noise Robust Diffusion Models (TDSM)

• Byeonghu Na, Yeongmin Kim, HeeSun Bae, Jung Hyun Lee, Se Jung Kwon, Wanmo Kang, and Il-Chul Moon

• ICLR 2024  (The Twelfth International Conference on Learning Representations)

• [paper] [code]

[11] Training Unbiased Diffusion Models From Biased Dataset (TIW-DSM)

• Yeongmin Kim, Byeonghu Na, JoonHo Jang, Minsang Park, Dongjun Kim, Wanmo Kang, and Il-Chul Moon

• ICLR 2024  (The Twelfth International Conference on Learning Representations)

• [paper] [code]

[10] Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learning (RENT)

• HeeSun Bae, Seungjae Shin, Byeonghu Na, and Il-Chul Moon

• ICLR 2024  (The Twelfth International Conference on Learning Representations)

• [paper] [code]

[9] Unknown Domain Inconsistency Minimization for Domain Generalization (UDIM)

• Seungjae Shin, Heesun Bae, Byeonghu Na, Yoon-Yeong Kim, and Il-Chul Moon

• ICLR 2024  (The Twelfth International Conference on Learning Representations)

• [paper]

[8] Hierarchical Multi-Label Classification with Partial Labels and Unknown Hierarchy (HMC)

• Suhyeon Jo, DongHyeok Shin, Byeonghu Na, JoonHo Jang, Il-Chul Moon

• CIKM 2023 (The 32nd ACM International Conference on Information and Knowledge Management)

• [paper]

[7] SAAL: Sharpness-Aware Active Learning (SAAL)

• Yoon-Yeong Kim*, Youngjae Cho*, JoonHo Jang, Byeonghu Na, Yeongmin Kim, Kyungwoo Song, Wanmo Kang, Il-Chul Moon

• ICML 2023 (The 40th International Conference on Machine Learning)

• [paper] [code]

[6] Maximum Likelihood Training of Implicit Nonlinear Diffusion Models (INDM)

• Dongjoun Kim*, Byeonghu Na*, Se Jung Kwon, Dongsoo Lee, Wanmo Kang, and Il-Chul Moon

• NeurIPS 2022 (The Conference on Neural Information Processing Systems)

• [paper] [code]

[5] Unknown-Aware Domain Adversarial Learning for Open-Set Domain Adaptation (UADAL)

• JoonHo Jang, Byeonghu Na, DongHyeok Shin, Mingi Ji, Kyungwoo Song, and Il-Chull Moon

• NeurIPS 2022 (The Conference on Neural Information Processing Systems)

• [paper] [code]

[4] Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features (MATRN)

• Byeonghu Na, Yoonsik Kim, and Sungrae Park

• ECCV 2022 (European Conference on Computer Vision) 

• [paper] [code]

[3] Improving Group-based Robustness and Calibration via Ordered Risk and Confidence Regularization (ORC)

• Seungjae Shin, Byeonghu Na, HeeSun Bae, JoonHo Jang, Hyemi Kim, Kyungwoo Song, Youngjae Cho, and Il-Chul Moon

• SCIS Workshop in ICML 2022 (The Workshop on Spurious Correlations, Invariance, and Stability, International Conference on Machine Learning)

• [paper]

[2] From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model (NPC)

• HeeSun Bae*, Seungjae Shin*, Byeonghu Na, JoonHo Jang, Kyungwoo Song, and Il-Chul Moon

• ICML 2022 (The 39th International Conference on Machine Learning)

• [paper] [code]

[1] Deep Generative Positive-Unlabeled Learning under Selection Bias (VAE-PU)

• Byeonghu Na, Hyemi Kim, Kyungwoo Song, Weonyoung Joo, Yoon-Yeong Kim, and Il-Chul Moon

• CIKM 2020  (The 29th ACM International Conference on Information and Knowledge Management)

• [paper] [code]

Domestic Conference

[1] Simultaneous execution model development based on Artificial neural network (Topic modeling and article classification on news data)

• Seungjae Shin, Byeonghu Na, Donghyeok Shin, Yeongyeon Na

• KSC 2017 (The Korea Software Congress 2017)

• [paper]