Publications

C: Conference / J: Journal / W: Workshop / P: Preprint / *: Equal contribution / ^: Equal advising

2024

[P2] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think (code, project)

• Sihyun Yu, Sangkyung Kwak, Huiwon Jang, Jongheon Jeong, Jonathan Huang, Jinwoo Shin^, Saining Xie^

[P1] Margin-aware Preference Optimization for Aligning Diffusion Models without Reference (code, project)

• Jiwoo Hong*, Sayak Paul*, Noah Lee, Kashif Rasul, James Thorne, Jongheon Jeong

[J2] Confidence-aware Denoised Fine-tuning of Off-the-shelf Models for Certified Robustness

• Suhyeok Jang, Seojin Kim, Jinwoo Shin, Jongheon Jeong

• Transactions on Machine Learning Research (TMLR)

[W10] DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing

• June Suk Choi, Kyungmin Lee, Jongheon Jeong, Saining Xie, Jinwoo Shin, Kimin Lee

• ICML 2024 Workshop on Next Generation of AI Safety (NextGenAISafety)

[C18] Adversarial Robustification via Text-to-Image Diffusion Models (code)

• Daewon Choi*, Jongheon Jeong*, Huiwon Jang, Jinwoo Shin

• European Conference on Computer Vision (ECCV) 2024 (Oral presentation; 200 / 8,585 = 2.3%)

[C17] Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models (code)

• Kyuyoung Kim, Jongheon Jeong, Minyong An, Mohammad Ghavamzadeh, Krishnamurth Dj Dvijotham, Jinwoo Shin, Kimin Lee

• International Conference on Learning Representations (ICLR) 2024

[J1/W9] Few-shot Anomaly Detection via Personalization

• Sangkyung Kwak, Jongheon Jeong, Hankook Lee, Woohyuck Kim, Dongho Seo, Woojin Yun, Wonjin Lee, Jinwoo Shin

• IEEE Access, vol. 12, pp. 11035-11051, 2024

• ICML 2023 Workshop on New Frontiers in Adversarial Machine Learning (AdvML)

2023

[C16] Multi-scale Diffusion Denoised Smoothing

• Jongheon Jeong, Jinwoo Shin

• Advances in Neural Information Processing Systems (NeurIPS) 2023

[C15] Modality-Agnostic Self-Supervised Learning with Meta-Learned Masked Auto-Encoder

• Huiwon Jang, Jihoon Tack, Daewon Choi, Jongheon Jeong, Jinwoo Shin

• Advances in Neural Information Processing Systems (NeurIPS) 2023

[C14/W8] Collaborative Score Distillation for Consistent Visual Synthesis

• Subin Kim, Kyungmin Lee, June Suk Choi, Jongheon Jeong, Kihyuk Sohn, Jinwoo Shin

• Advances in Neural Information Processing Systems (NeurIPS) 2023

• ICML 2023 Workshop on Structured Probabilistic Inference & Generative Modeling (SPIGM) 

[C13/W7] Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneck

• Jongheon Jeong, Sihyun Yu, Hankook Lee, Jinwoo Shin

• IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023

• ECCV 2022 Workshop on Out-of-Distribution Generalization in Computer Vision (OOD-CV)

[C12] WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation

• Jongheon Jeong*, Yang Zou*, Taewan Kim, Dongqing Zhang, Avinash Ravichandran, Onkar Dabeer

• IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023

[C11/W6] Guiding Energy-based Models via Contrastive Latent Variables

• Hankook Lee, Jongheon Jeong, Sejun Park, Jinwoo Shin

• International Conference on Learning Representations (ICLR) 2023 (Spotlight presentation; 280 / 4,956 = 5.6%)

• NeurIPS 2022 Workshop on Self-Supervised Learning (Oral presentation)

[C10/W5] Confidence-aware Training of Smoothed Classifiers for Certified Robustness

• Jongheon Jeong*, Seojin Kim*, Jinwoo Shin

• AAAI Conference on Artificial Intelligence (AAAI) 2023 (Oral presentation)

• ECCV 2022 Workshop on Adversarial Robustness in the Real World (AROW)

2022

[C9] NOTE: Robust Continual Test-time Adaptation Against Temporal Correlation

• Taesik Gong, Jongheon Jeong, Taewon Kim, Yewon Kim, Jinwoo Shin, Sung-Ju Lee

• Advances in Neural Information Processing Systems (NeurIPS) 2022

[C8] SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation (code)

• Yang Zou, Jongheon Jeong, Latha Pemula, Dongqing Zhang, Onkar Dabeer

• European Conference on Computer Vision (ECCV) 2022

[C7/W4] Consistency Regularization for Adversarial Robustness (code)

• Jihoon Tack, Sihyun Yu, Jongheon Jeong, Minseon Kim, Sung Ju Hwang, Jinwoo Shin

• AAAI Conference on Artificial Intelligence (AAAI) 2022

• ICML 2021 Workshop on Adversarial Machine Learning (AdvML) (Oral presentation)

• Best Paper Award, Korean Artificial Intelligence Association 2021

[W3] OpenCoS: Contrastive Semi-supervised Learning for Handling Open-set Unlabeled Data

• Jongjin Park*, Sukmin Yun*, Jongheon Jeong, Jinwoo Shin 

• ECCV 2022 Workshop on Learning from Limited and Imperfect Data (L2ID)

2021

[C6/W2] SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness (code)

• Jongheon Jeong, Sejun Park, Minkyu Kim, Heung-Chang Lee, Doguk Kim, Jinwoo Shin

• Advances in Neural Information Processing Systems (NeurIPS) 2021

• ICML 2021 Workshop on Adversarial Machine Learning (AdvML)

[C5] Training GANs with Stronger Augmentations via Contrastive Discriminator (code, slide, poster)

• Jongheon Jeong, Jinwoo Shin

• International Conference on Learning Representations (ICLR) 2021

2020

[C4/W1] Consistency Regularization for Certified Robustness of Smoothed Classifiers (code, slide, poster)

• Jongheon Jeong, Jinwoo Shin

• Advances in Neural Information Processing Systems (NeurIPS) 2020 

• ICML 2020 Workshop on Uncertainty & Robustness in Deep Learning (UDL) 

• Qualcomm Innovation Fellowship Korea 2020

[C3] CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances (code, slide, poster)

• Jihoon Tack*, Sangwoo Mo*, Jongheon Jeong, Jinwoo Shin

• Advances in Neural Information Processing Systems (NeurIPS) 2020 

• Qualcomm Innovation Fellowship Korea 2020

[C2] M2m: Imbalanced Classification via Major-to-minor Translation (code, slide, talk)

• Jaehyung Kim*, Jongheon Jeong*, Jinwoo Shin

• IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020

2019

[C1] Training CNNs with Selective Allocation of Channels (code, slide, poster, talk)

• Jongheon Jeong, Jinwoo Shin

• International Conference on Machine Learning (ICML) 2019