International Conference

[22] Lookahead Sample Reward Guidance for Test-Time Scaling of Diffusion Models (LiDAR)

• Yeongmin Kim, Donghyeok Shin, Byeonghu Na, Minsang Park, Richard Lee Kim, and Il-Chul Moon

• ICML 2026 (The Forty-Third International Conference on Machine Learning)

• [paper]

[21] Semantic-aware Wasserstein Policy Regularization for Large Language Model Alignment (WPR)

• Byeonghu Na, Hyungho Na, Yeongmin Kim, Suhyeon Jo, HeeSun Bae, Mina Kang, and Il-Chul Moon

• ICLR 2026 (The Fourteenth International Conference on Learning Representations)

• [paper] [code]

[20] AMiD: Knowledge Distillation for LLMs with $\alpha$-mixture Assistant Distribution (AMiD)

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

• ICLR 2026 (The Fourteenth International Conference on Learning Representations)

• [paper]

[19] Distillation of Large Language Models via Concrete Score Matching (CSD)

• Yeongmin Kim, Donghyeok Shin, Mina Kang, Byeonghu Na, and Il-Chul Moon

• ICLR 2026 (The Fourteenth International Conference on Learning Representations)

• [paper]

[18] AC-Sampler: Accelerate and Correct Diffusion Sampling with Metropolis-Hastings Algorithm (AC-Sampler)

• Minsang Park, Gyuwon Sim, Hyungho Na, Jiseok Kwak, Sumin Lee, Richard Lee Kim, Donghyeok Shin, Byeonghu Na, Yeongmin Kim, and Il-Chul Moon

• ICLR 2026 (The Fourteenth International Conference on Learning Representations)

• [paper] [code]

[17] Training-free Safe Text Embedding Guidance for Text-to-Image Diffusion Models (STG)

• Byeonghu Na, Mina Kang, Jiseok Kwak, Minsang Park, Jiwoo Shin, SeJoon Jun, Gayoung Lee, Jin-Hwa Kim, and Il-Chul Moon

• NeurIPS 2025 (The Thirty-ninth Annual Conference on Neural Information Processing Systems)

• [paper] [code]

[16] Diffusion Adaptive Text Embedding for Text-to-Image Diffusion Models (DATE)

• Byeonghu Na, Minsang Park, Gyuwon Sim, Donghyeok Shin, HeeSun Bae, Mina Kang, Se Jung Kwon, Wanmo Kang, and Il-Chul Moon

• NeurIPS 2025 (The Thirty-ninth Annual Conference on Neural Information Processing Systems)

• [paper] [code]

[15] Preference Optimization by Estimating the Ratio of the Data Distribution (BPO)

• Yeongmin Kim, HeeSun Bae, Byeonghu Na, and Il-Chul Moon

• NeurIPS 2025 (The Thirty-ninth Annual Conference on Neural Information Processing Systems)

• [paper] [code]

[14] Diffusion Bridge AutoEncoders for Unsupervised Representation Learning (DBAE)

• Yeongmin Kim, Kwanghyeon Lee, Minsang Park, Byeonghu Na, and Il-Chul Moon

• ICLR 2025  (The Thirteenth International Conference on Learning Representations) [Spotlight presentation]

• [paper] [code]

[13] 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) [Oral presentation, Top 4%]

• [paper] [code]

[12] 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)

• [paper] [code]

[11] 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]

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

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

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

• [paper] [code]

[9] 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]

[8] 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] [code]

[7] Hierarchical Multi-Label Classification with Partial Labels and Unknown Hierarchy (HUPM)

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

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

• [paper] [code]

[6] 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]

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

• Dongjun 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]

[4] 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]

[3] 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]

[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]

International Workshop

[W3] Prompt-Based Safety Guidance Is Ineffective for Unlearned Text-to-Image Diffusion Models

• Jiwoo Shin, Byeonghu Na, Mina Kang, Wonhyeok Choi, and Il-Chul Moon

• GenProCC Workshop @ NeurIPS 2025 (Generative and Protective AI for Content Creation)

• [paper]

[W2] DPO-Finetuned Large Multi-Modal Planner with Retrieval-Augmented Generation @ EgoPlan Challenge ICML 2024

• Kwanghyeon Lee, Mina Kang, Hyungho Na, Heesun Bae, Byeonghu Na, Doyun Kwon, Seungjae Shin, Yeongmin Kim, Taewoo Kim, Seungmin Yun, and Il-Chul Moon

• The Multi-modal Foundation Model meets Embodied AI Workshop @ ICML 2024

• [paper] [code]

[W1] 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]

Domestic Conference

[D1] 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]