Publications

(C: peer-reviewed conference, J: peer-reviewed journal, W: peer-reviewed workshop, I: invited conference, T: technical report, * = equal contributions)

2026

[T1] RLDX-1 Technical Report (arXiv, code, site): Dongyoung Kim*, Huiwon Jang*, Myungkyu Koo*, Suhyeok Jang*, Taeyoung Kim*, Beomjun Kim, Byungjun Yoon, Changsung Jang, Daewon Choi, Dongsu Han, Donguk Lee, Heeseung Kwon, Hojin Jeon, Jaehyun Kang, Jaekyoung Bae, Jihyuk Lee, Jimin Lee, John Won, Joonwoo Ahn, Junhyeong Park, Junyoung Sung, Kyungmin Lee, Minseong Han, Minsung Yoon, Sejune Joo, Seonil Son, Seungcheol Park, Seunggeun Cho, Seungjun Moon, Seungku Kim, Yonghoon Dong, Yongjin Cho, Youngchan Kim, Chang Hwan Kim, Dohyeon Kim, Heecheol Kim, Heewon Lee, Hensen Ahn, Hyungkyu Ryu, Hyunsoo Choi, Hyunsoo Shin, Jaeheon Jung, Jaewoo Kim, Jinwook Kim, Joochul Chang, Joonsoo Kim, Junghun Park, Jungwoo Park, Junho Cho, Junhyeok Park, Junwon Lee, Kangwook Lee, Kwanghoon Kim, Kyoungwhan Choe, Manoj Bhadu, Nayoung Oh, Sangjun Kim, Sangwoo Kim, Seunghoon Shim, Seunghyun Kim, Seungjun Lee, Seungyup Ka, Sungryol Yang, Wook Jung, Yashu Shukla, Yeonjae Lee, Yeonwoo Bae, Jinwoo Shin
Technical Report (TR), 2026

[C233] Trust Region Q Adjoint Matching (arXiv, site): Yonghoon Dong, Kyungmin Lee, Changyeon Kim, Jaehyuk Kim and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2026 new

[C232] Pose6DAug: Physically Plausible Multi-view Object Swapping for Robot Data Augmentation (arXiv, site): Jonghoon Lee*, Seong Hyeon Park*, Byungwoo Jeon, Minha Lee and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2026 new

[C231] Latent Reasoning in Continuous Space for Unified Multimodal Models: Byungwoo Jeon, Yoonwoo Jeong, Hyunseok Lee, Minsu Cho and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2026 new

[C230] Example-Based Spatial Guidance for Training-Free Concept Erasure in Diffusion Models: Younghwan Kil, Joonhyeon Park, Giung Nam, Jinwoo Shin and Juho Lee
Conference on Neural Information Processing Systems (NeurIPS), 2026 new

[C229] ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scaling (arXiv): Woomin Song, Beomjun Kim, Daewon Choi, Sai Muralidhar Jayanthi, Saket Dingliwal, Jinwoo Shin and Aram Galstyan
Conference on Neural Information Processing Systems (NeurIPS), 2026 new
Oral Presentation (112/30709=0.36%)

[C228] Deep Barycentric Regression for Optimal Transport Map Estimation and its Statistical Optimality (arXiv, code): Kunwoong Kim, Insung Kong and Yongdai Kim
Conference on Neural Information Processing Systems (NeurIPS), 2026 new
Spotlight Presentation (292/30709=0.95%)

[C227] DoG: Sniffing Out Overconfidence in LLM Agents via Post-hoc Trajectory Restructuring: Hyunjun Jeon*, Dongha Lim*, Kunwoong Kim, Daewon Choi, Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2026 new

[C226] AtomMOF: All-Atom Flow Matching for MOF-Adsorbate Structure Prediction (arXiv, code): Nayoung Kim, Honghui Kim, Sihyun Yu, Minkyu Kim, Seungsu Kim and Sungsoo Ahn
Conference on Neural Information Processing Systems (NeurIPS), 2026 new

[C225] A Simple Unigram Cross-Entropy Lens on the Lexical Imprint of Pre-training Data: Jeonghoon Kim*, Woojin Chung*, Woomin Song, Cheonbok Park, Nako Sung, Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2026 new

[C224] World Action Models Are Zero-Shot Policies (arXiv, code, site): Seonghyeon Ye†, Yunhao Ge*, Kaiyuan Zheng*, Shenyuan Gao*, Sihyun Yu*, George Kurian*, Suneel Indupuru*, You Liang Tan*, Chuning Zhu, Jiannan Xiang, Ayaan Malik, Kyungmin Lee, William Liang, Nadun Ranawaka, Jiasheng Gu, Yinzhen Xu, Guanzhi Wang, Fengyuan Hu, Avnish Narayan, Johan Bjorck, Jing Wang, Gwanghyun Kim, Dantong Niu, Ruijie Zheng, Yuqi Xie, Jimmy Wu, Qi Wang, Ryan Julian, Danfei Xu, Yilun Du, Yevgen Chebotar, Scott Reed, Jan Kautz, Yuke Zhu†, Jim Fan†, Joel Jang†
Conference on Robot Learning (CoRL), 2026 new
Oral Presentation (21/2094=1.00%)

[C223] Modular Sensory Stream for Integrating Physical Feedback in Vision-Language-Action Models (arXiv, site): Jimin Lee, Huiwon Jang, Myungkyu Koo, Jungwoo Park and Jinwoo Shin
Conference on Robot Learning (CoRL), 2026 new

[C222] Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models (arXiv, code): Kyuyoung Kim, Kevin Wang, Yunfei Xie, Peiyang Xu, Peiyao Sheng, Chen Wei, Zhangyang Wang, Jinwoo Shin, Pramod Viswanath, Sewoong Oh
Conference on Language Modeling (COLM), 2026 new

[C221] SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning (arXiv, site): Byungwoo Jeon*, Dongyoung Kim*, Huiwon Jang, Insoo Kim and Jinwoo Shin
European Conference on Computer Vision (ECCV), 2026 new

[C220] Vision-aligned Latent Reasoning for Multi-Modal Large Language Model (arXiv, site): Byungwoo Jeon, Yoonwoo Jeong, Hyunseok Lee, Minsu Cho and Jinwoo Shin
International Conference on Machine Learning (ICML), 2026 new

[C219] DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos (arXiv, code, site): Shenyuan Gao, William Liang, Kaiyuan Zheng, Ayaan Malik, Seonghyeon Ye, Sihyun Yu, Wei-Cheng Tseng, Yuzhu Dong, Kaichun Mo, Chen-Hsuan Lin, Qianli Ma, Seungjun Nah, Loic Magne, Jiannan Xiang, Yuqi Xie, Ruijie Zheng, Dantong Niu, You Liang Tan, KR Zentner, George Kurian, Suneel Indupuru, Pooya Jannaty, Jinwei Gu, Jun Zhang, Jitendra Malik, Pieter Abbeel, Ming-Yu Liu, Yuke Zhu, Joel Jang and Jim Fan
International Conference on Machine Learning (ICML), 2026 new
Spotlight Presentation (536/23918=2.24%)

[C218] Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model (arXiv): John Won, Kyungmin Lee, Huiwon Jang, Dongyoung Kim and Jinwoo Shin
International Conference on Machine Learning (ICML), 2026 new

[C217] Contrastive Representation Regularization for Vision-Language-Action Models (arXiv): Taeyoung Kim, Jimin Lee, Myungkyu Koo, Dongyoung Kim, Kyungmin Lee, Changyeon Kim, Younggyo Seo and Jinwoo Shin
International Conference on Machine Learning (ICML), 2026 new

[C216] Rethinking Prompt Design for Inference-time Scaling in Text-to-Visual Generation (arXiv, site): Subin Kim, Sangwoo Mo, Mamshad Nayeem Rizve, Yiran Xu, Difan Liu, Jinwoo Shin and Tobias Hinz
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

[C215] Improving Motion in Image-to-Video Models via Adaptive Low-Pass Guidance (arXiv, code, site): June Suk Choi, Kyungmin Lee, Sihyun Yu, Yisol Choi, Jinwoo Shin and Kimin Lee
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
Highlight Presentation (575/16092=3.57%)

[C214] Verifier-free Test-Time Sampling for Vision Language Action Models (arXiv): Suhyeok Jang, Dongyoung Kim, Changyeon Kim, Youngsuk Kim and Jinwoo Shin
International Conference on Learning Representations (ICLR), 2026

[C213] RedacBench: Can AI Erase Your Secrets? (arXiv): Hyunjun Jeon, Kyuyoung Kim and Jinwoo Shin
International Conference on Learning Representations (ICLR), 2026

[C212] Learning Flexible Forward Trajectories for Masked Molecular Diffusion (arXiv): Hyunjin Seo, Taewon Kim, Sihyun Yu and Sungsoo Ahn
International Conference on Learning Representations (ICLR), 2026

[C211] HAMLET: Switch Your Vision-Language-Action Model into a History-Aware Policy (arXiv, code, site): Myungkyu Koo*, Daewon Choi*, Taeyoung Kim, Kyungmin Lee, Changyeon Kim, Younggyo Seo and Jinwoo Shin
International Conference on Learning Representations (ICLR), 2026

[C210] Decoupled MeanFlow: Turning Flow Models into Flow Maps for Accelerated Sampling (arXiv): Kyungmin Lee, Sihyun Yu and Jinwoo Shin
International Conference on Learning Representations (ICLR), 2026

[J37] DS-STAR: Data Science Agent for Solving Diverse Tasks across Heterogeneous Formats and Open-Ended Queries (arXiv, code, site): Jaehyun Nam, Jinsung Yoon, Jiefeng Chen, Rajarishi Sinha, Jinwoo Shin and Tomas Pfister
Transactions on Machine Learning Research (TMLR), 2026 new

[W59] Benchmarking Visual State Tracking in Multimodal Video Understanding (arXiv, code, site): Sihyun Yu†*, Nanye Ma†*, Pinzhi Huang†*, Hyunseok Lee*, Shusheng Yang, June Suk Choi, Ellis Brown, Oscar Michel, Boyang Zheng, Jinwoo Shin, Saining Xie
NeurIPS Workshop on VLM4RWD, 2026 new
Oral Presentation

2025

[C209] Track3R: Joint Point Map and Trajectory Prior for Spatiotemporal 3D Understanding: Seong Hyeon Park and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2025

[C208] Self-Refining Language Model Anonymizers via Adversarial Distillation: Kyuyoung Kim, Hyunjun Jeon and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2025

[C207] Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics: Dongyoung Kim, Huiwon Jang, Sumin Park, Jaehyung Kim, Younggyo Seo and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2025

[C206] MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement: Jaehyun Nam, Jinsung Yoon, Jiefeng Chen, Jinwoo Shin, Sercan O Arik and Tomas Pfister
Conference on Neural Information Processing Systems (NeurIPS), 2025

[C205] Exploiting Vocabulary Frequency Imbalance in Language Model Pre-training: Woojin Chung and Jeonghoon Kim
Conference on Neural Information Processing Systems (NeurIPS), 2025

[C204] Compress, Gather, and Recompute: REFORMing Long-Context Processing in Transformers: Woomin Song, Sai Muralidhar Jayanthi, Srikanth Ronanki, Kanthashree Mysore Sathyendra, Jinwoo Shin, Aram Galstyan, Shubham Katiyar and Sravan Babu Bodapati
Conference on Neural Information Processing Systems (NeurIPS), 2025

[C203] Training Text-to-Molecule Models with Context-Aware Tokenization: Seojin Kim*, Hyeontae Song*, Jaehyun Nam and Jinwoo Shin
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025 (findings)

[C202] Think Clearly: Improving Reasoning via Redundant Token Pruning (arXiv): Daewon Choi, Jimin Lee, Jihoon Tack, Woomin Song, Saket Dingliwal, Sai Muralidhar Jayanthi, Bhavana Ganesh, Jinwoo Shin, Aram Galstyan and Sravan Babu Bodapati
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025 (findings)

[C201] Personalized Language Models via Privacy-Preserving Evolutionary Model Merging (arXiv): Kyuyoung Kim, Jinwoo Shin and Jaehyung Kim
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025
Oral Presentation (325/8174=3.98%)

[C200] Mamba Drafters for Speculative Decoding (arXiv): Daewon Choi, Seunghyuk Oh, Saket Dingliwal, Jihoon Tack, Kyuyoung Kim, Woomin Song, Seojin Kim, Insu Han, Jinwoo Shin, Aram Galstyan, Shubham Katiyar and Sravan Babu Bodapati
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025 (findings)

[C199] Accelerated Test-Time Scaling with Model-Free Speculative Sampling (arXiv): Woomin Song, Saket Dingliwal, Sai Muralidhar Jayanthi, Bhavana Ganesh, Jinwoo Shin, Aram Galstyan and Sravan Babu Bodapati
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025 (based on the preliminary version [W54])
Oral Presentation (325/8174=3.98%)

[C198] Test-Time Adaptation with Binary Feedback: Taeckyung Lee, Sorn Chottananurak, Junsu Kim, Jinwoo Shin, Taesik Gong and Sung-Ju Lee
International Conference on Machine Learning (ICML), 2025

[C197] ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification: Hyunseok Lee*, Seunghyuk Oh*, Jaehyung Kim, Jinwoo Shin and Jihoon Tack
International Conference on Machine Learning (ICML), 2025

[C196] PRIME: Deep Imbalanced Regression with Proxies: Jongin Lim, Sucheol Lee, Daeho Um, Sung-Un Park and Jinwoo Shin
International Conference on Machine Learning (ICML), 2025

[C195] Peri-LN: Revisiting Layer Normalization in the Transformer Architecture: Jeonghoon Kim, Byeongchan Lee, Cheonbok Park, Yeontaek Oh, Beomjun Kim, Taehwan Yoo, Seongjin Shin, Dongyoon Han, Jinwoo Shin and Kang Min Yoo
International Conference on Machine Learning (ICML), 2025

[C194] StarFT: Robust Fine-tuning of Zero-shot Models via Spuriosity Alignment (arXiv): Younghyun Kim*, Jongheon Jeong*, Sangkyung Kwak, Kyungmin Lee, Juho Lee and Jinwoo Shin
International Joint Conference on Artificial Intelligence (IJCAI), 2025

[C193] Enhancing LLM Agent Safety via Causal Influence Prompting: Dongyoon Hahm, Woogyeol Jin, June Suk Choi, Sungsoo Ahn and Kimin Lee
Annual Meeting of the Association for Computational Linguistics (ACL), 2025 (findings)

[C192] Debiasing Online Preference Learning via Preference Feature Preservation: Dongyoung Kim, Jinsung Yoon, Jinwoo Shin and Jaehyung Kim
Annual Meeting of the Association for Computational Linguistics (ACL), 2025 (findings)

[C191] Silent Branding Attack: Trigger-free Data Poisoning Attack on Text-to-Image Diffusion Models (arXiv, site): Sangwon Jang, June Suk Choi, Jaehyeong Jo, Kimin Lee and Sung Ju Hwang
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

[C190] Efficient Long Video Tokenization via Coordinated-based Patch Reconstruction: Huiwon Jang, Sihyun Yu, Jinwoo Shin, Pieter Abbeel and Younggyo Seo
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

[C189] Closest Neighbors are Harmful for Lightweight Masked Auto-encoders: Jian Meng, Ahmed Hasssan, Li Yang, Deliang Fan, Jinwoo Shin and Jae-sun Seo
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

[C188] Calibrated Multi-Preference Optimization for Aligning Diffusion Models: Kyungmin Lee, Xiaohang Li, Qifei Wang, Junfeng He, Junjie Ke, Ming-Hsuan Yang, Irfan Essa, Jinwoo Shin, Feng Yang and Yinxiao Li
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

[C187] Controllable Human Image Generation with Personalized Multi-Garments: Yisol Choi, Sangkyung Kwak, Sihyun Yu, Hyungwon Choi and Jinwoo Shin
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

[C186] Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment (arXiv, code): Dongyoung Kim, Kimin Lee, Jinwoo Shin and Jaehyung Kim
International Conference on Learning Representations (ICLR), 2025
Oral Presentation (213/11672=1.82%)

[C185] Subtask-Aware Visual Reward Learning from Segmented Demonstrations (arXiv, site): Changyeon Kim, Minho Heo, Doohyun Lee, Honglak Lee, Jinwoo Shin, Joseph J Lim^, Kimin Lee^
International Conference on Learning Representations (ICLR), 2025

[C184] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think (arXiv, code, site): Sihyun Yu, Sangkyung Kwak, Huiwon Jang, Jongheon Jeong, Jonathan Huang, Jinwoo Shin^ and Saining Xie^
International Conference on Learning Representations (ICLR), 2025
Oral Presentation (213/11672=1.82%)

[C183] Learning to Contextualize Web Pages for Enhanced Decision Making by LLM Agents: Dongjun Lee, Juyong Lee, Kyuyoung Kim, Jihoon Tack, Jinwoo Shin, Yee Whye Teh and Kimin Lee
International Conference on Learning Representations (ICLR), 2025

[C182] DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing (arXiv, code, site): June Suk Choi, Kyungmin Lee, Jongheon Jeong, Saining Xie, Jinwoo Shin and Kimin Lee
International Conference on Learning Representations (ICLR), 2025 (based on the preliminary version [W50])

[C181] Controllable Blur Data Augmentation Using 3D-Aware Motion Estimation: Insoo Kim, Hana Lee, Hyong-Euk Lee and Jinwoo Shin
International Conference on Learning Representations (ICLR), 2025

[C180] DiffExp: Efficient Exploration in Reward Fine-tuning for Text-to-Image Diffusion Models (arXiv): Daewon Chae*, June Suk Choi*, Jinkyu Kim^ and Kimin Lee^
AAAI Conference on Artificial Intelligence (AAAI), 2025
Oral Presentation (547/12957=4.22%)

[J36] CLIP Meets Diffusion: A Synergistic Approach to Anomaly Detection (arXiv): Byeongchan Lee, John Won, Seunghyun Lee and Jinwoo Shin
Transactions on Machine Learning Research (TMLR), 2025

[J35] RefDeblur: Blind Motion Deblurring with Self-Generated Reference Image: Insoo Kim, Geonseok Seo, Hyong-Euk Lee and Jinwoo Shin
Transactions on Machine Learning Research (TMLR), 2025

[J34] Sparsified State-Space Models are Efficient Highway Networks: Woomin Song, Jihoon Tack, Sangwoo Mo, Seunghyuk Oh and Jinwoo Shin
Transactions on Machine Learning Research (TMLR), 2025 (based on the preliminary version [W51])

[J33] NeFL: Nested Model Scaling for Federated Learning with System Heterogeneous Clients: Honggu Kang, Seohyeon Cha, Jinwoo Shin, Jongmyeong Lee and Joonhyuk Kang
IEEE Transactions on Mobile Computing (TMC), 2025 (accepted to appear)

[W58] Tuning-Free Multi-Event Long Video Generation via Synchronized Coupled Sampling (arXiv, site): Subin Kim Kim, Seoung Wug Oh, Wang. Jui-Hsien, Joon-Young Lee and Jinwoo Shin
ICCV Workshop on the Findings, 2025

[W57] Think Clearly: Improving Reasoning via Redundant Token Pruning (arXiv): Daewon Choi, Jimin Lee, Jihoon Tack, Woomin Song, Saket Dingliwal, Sai Muralidhar Jayanthi, Bhavana Ganesh, Jinwoo Shin, Aram Galstyan and Sravan Babu Bodapati
ICML Workshop on Efficient Systems for Foundation Models III, 2025

[W56] Mamba Drafters for Speculative Decoding (arXiv): Daewon Choi, Seunghyuk Oh, Saket Dingliwal, Jihoon Tack, Kyuyoung Kim, Woomin Song, Seojin Kim, Insu Han, Jinwoo Shin, Aram Galstyan, Shubham Katiyar and Sravan Babu Bodapati
ICML Workshop on Efficient Systems for Foundation Models III, 2025

[W55] Compress, Gather, and Recompute: REFORMing Long-Context Processing in Transformers (arXiv): Woomin Song, Sai Muralidhar Jayanthi, Srikanth Ronanki, Kanthashree Mysore Sathyendra, Jinwoo Shin, Aram Galstyan, Shubham Katiyar and Sravan Babu Bodapati
ICML Workshop on Efficient Systems for Foundation Models III, 2025

[W54] Accelerated Test-Time Scaling with Model-Free Speculative Sampling (arXiv): Woomin Song, Saket Dingliwal, Sai Muralidhar Jayanthi, Bhavana Ganesh, Jinwoo Shin, Aram Galstyan and Sravan Babu Bodapati
ICML Workshop on Efficient Systems for Foundation Models III, 2025 (the newer version [C199] available at EMNLP 2025)

[W53] MALT Diffusion: Memory-Augmented Latent Transformers for Any-Length Video Generation (arXiv): Sihyun Yu, Meera Hahn, Dan Kondratyuk, Jinwoo Shin, Agrim Gupta, Jose Lezama, Irfan Essa, David A Ross and Jonathan Huang
CVPR Workshop on AI for Content Creation, 2025
Best Presentation Award

2024

[C179] TrackIME: Enhanced Video Point Tracking via Instance Motion Estimation (arXiv, poster): Seong Hyeon Park, Huiwon Jang, Byungwoo Jeon, Sukmin Yun, Paul Hongsuck Seo and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2024
Spotlight Presentation (326/15671=2%)

[C178] ReMoDetect: Reward Models Recognize Aligned LLM's Generations (arXiv, code, site, demo): Hyunseok Lee*, Jihoon Tack* and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2024

[C177] Online Adaptation of Language Models with a Memory of Amortized Contexts (arXiv, code, site): Jihoon Tack, Jaehyung Kim, Eric Mitchell, Jinwoo Shin, Yee Whye Teh and Jonathan Richard Schwarz
Conference on Neural Information Processing Systems (NeurIPS), 2024

[C176] Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning (arXiv, code): Jaehyun Nam*, Kyuyoung Kim*, Seunghyuk Oh, Jihoon Tack, Jaehyung Kim and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2024

[C175] Direct Consistency Optimization for Robust Customization of Text-to-Image Diffusion models (arXiv, code, site): Kyungmin Lee, Sangkyung Kwak, Kihyuk Sohn and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2024

[C174] Conditional Synthesis of 3D Molecules with Time Correction Sampler (arXiv): Hojung Jung, Youngrok Park, Laura Schmid, Jaehyeong Jo, Dongkyu Lee, Bongsang Kim, Se-Young Yun and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2024

[C173] Margin Matching Preference Optimization: Enhanced Model Alignment with Granular Feedback (arXiv): Kyuyoung Kim, Ah Jeong Seo, Hao Liu, Jinwoo Shin and Kimin Lee
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024 (findings)

[C172] Learning to Correct for QA Reasoning with Black-box LLMs (arXiv, code): Jaehyung Kim, Dongyoung Kim and Yiming Yang
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024

[C171] Safeguard Text-to-Image Diffusion Models with Human Feedback Inversion (arXiv, code): Sanghyun Kim, Seohyeon Jung, Balhae Kim, Moonseok Choi, Jinwoo Shin and Juho Lee
European Conference on Computer Vision (ECCV), 2024

[C170] Improving Diffusion Models for Authentic Virtual Try-on in the Wild (arXiv, code, site): Yisol Choi, Sangkyung Kwak, Kyungmin Lee, Hyungwon Choi and Jinwoo Shin
European Conference on Computer Vision (ECCV), 2024

[C169] Adversarial Robustification via Text-to-Image Diffusion Models (arXiv, code): Daewon Choi*, Jongheon Jeong*, Huiwon Jang, Jinwoo Shin
European Conference on Computer Vision (ECCV), 2024
Oral Presentation (200/8585=2.3%)

[C168] Tabular Transfer Learning via Prompting LLMs (arXiv, code): Jaehyun Nam, Woomin Song, Seong Hyeon Park, Jihoon Tack, Sukmin Yun, Jaehyung Kim, Kyu Hwan Oh, and Jinwoo Shin
Conference on Language Modeling (COLM), 2024 (based on the preliminary version [W43])

[C167] Visual Representation Learning with Stochastic Frame Prediction (arXiv, code, site): Huiwon Jang, Dongyoung Kim, Junsu Kim, Jinwoo Shin, Pieter Abbeel, Younggyo Seo
International Conference on Machine Learning (ICML), 2024

[C166] Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts (arXiv, code): Shengzhuang Chen, Jihoon Tack, Yunqiao Yang, Yee Whye Teh, Jonathan Richard Schwarz and Ying Wei
International Conference on Machine Learning (ICML), 2024

[C165] Data-Efficient Molecular Generation with Hierarchical Textual Inversion: Seojin Kim, Jaehyun Nam, Sihyun Yu, Younghoon Shin, Jinwoo Shin
International Conference on Machine Learning (ICML), 2024 (based on the preliminary version [W48])

[C164] Real-World Efficient Blind Motion Deblurring via Blur Pixel Discretization: Insoo Kim, Jae Seok Choi, Geonseok Seo, Kinam Kwon, Jinwoo Shin and Hyong-Euk Lee
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

[C163] Discovering and Mitigating Visual Biases through Keyword Explanation (arXiv, code): Younghyun Kim*, Sangwoo Mo*, Minkyu Kim, Kyungmin Lee, Jaeho Lee and Jinwoo Shin
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024 (based on the preliminary version [W45])
Highlight (324/11532=2.8%)

[C162] SuRe: Improving Open-domain Question Answering of LLMs via Summarized Retrieval (arXiv, code): Jaehyung Kim, Jaehyun Nam, Sangwoo Mo, Jongjin Park, Sang-Woo Lee, Minjoon Seo, Jung-Woo Ha and Jinwoo Shin
International Conference on Learning Representations (ICLR), 2024

[C161] Querying Easily Flip-flopped Samples for Deep Active Learning: Seong Jin Cho, Gwangsu Kim, Junghyun Lee, Jinwoo Shin and Chang D. Yoo
International Conference on Learning Representations (ICLR), 2024

[C160] Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs: Woomin Song*, Seunghyuk Oh*, Sangwoo Mo, Jaehyung Kim, Sukmin Yun, Jung-Woo Ha, and Jinwoo Shin
International Conference on Learning Representations (ICLR), 2024

[C159] Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition (arXiv, code, site): Sihyun Yu, Weili Nie, De-An Huang, Boyi Li, Jinwoo Shin and Anima Anandkumar
International Conference on Learning Representations (ICLR), 2024

[C158] DreamFlow: High-quality text-to-3D generation by Approximating Probability Flow: Kyungmin Lee, Kihyuk Sohn and Jinwoo Shin
International Conference on Learning Representations (ICLR), 2024
Spotlight Presentation (366/7262=5%)

[C157] Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models: Kyuyoung Kim, Jongheon Jeong, Minyong An, Mohammad Ghavamzadeh, Krishnamurthy Dj Dvijotham, Jinwoo Shin and Kimin Lee
International Conference on Learning Representations (ICLR), 2024

[J32] Confidence-aware Denoised Fine-tuning of Off-the-shelf Models for Certified Robustness (arXiv, code): Suhyeok Jang*, Seojin Kim*, Jinwoo Shin, Jongheon Jeong
Transactions on Machine Learning Research (TMLR), 2024

[J31] Holistic Molecular Representation Learning via Multi-view Fragmentation: Seojin Kim*, Jaehyun Nam*, Junsu Kim, Hankook Lee, Sungsoo Ahn, Jinwoo Shin
Transactions on Machine Learning Research (TMLR), 2024 (based on the preliminary version [W36])

[W52] An Efficient Tokenization for Molecular Language Models: Seojin Kim, Jaehyun Nam and Jinwoo Shin
NeurIPS Workshop on AI for New Drug Modalities (AIDrugX), 2024

[W51] Sparsified State-Space Models are Efficient Highway Networks: Woomin Song, Jihoon Tack, Sangwoo Mo, Seunghyuk Oh and Jinwoo Shin
NeurIPS Workshop on Efficient Natural Language and Speech Processing (ENLSP), 2024 (the newer version [J34] available at Transactions on Machine Learning Research)
Oral Presentation

[W50] DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing (arXiv, code): June Suk Choi, Kyungmin Lee, Jongheon Jeong, Saining Xie, Jinwoo Shin and Kimin Lee
ICML Workshop on the Next Generation of AI Safety, 2024 (the newer version [C182] available at ICLR 2025)

[W49] MC^2: Multi-view Consistent Depth Estimation via Coordinated Image-based Neural Rendering (site): Subin Kim*, Seong Hyeon Park*, Sihyun Yu, Kihyuk Sohn, and Jinwoo Shin
CVPR Workshop on Neural Rendering Intelligence, 2024

2023

[C156] S-CLIP: Semi-supervised Vision-Language Learning using Few Specialist Captions (arXiv, code): Sangwoo Mo, Minkyu Kim, Kyungmin Lee and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2023

[C155] Slimmed Asymmetrical Contrastive Learning and Cross Distillation for Lightweight Model Training: Jian Meng, Li Yang, Kyungmin Lee, Jinwoo Shin, Deliang Fan and Jae-sun Seo
Conference on Neural Information Processing Systems (NeurIPS), 2023

[C154] Modality-Agnostic Self-Supervised Learning with Meta-Learned Masked Auto-Encoder (arXiv, code): Huiwon Jang*, Jihoon Tack*, Daewon Choi, Jongheon Jeong and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2023

[C153] Multi-scale Diffusion Denoised Smoothing (arXiv, code): Jongheon Jeong and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2023

[C152] Learning Large-scale Neural Fields via Context Pruned Meta-Learning (arXiv, code): Jihoon Tack, Subin Kim, Sihyun Yu, Jaeho Lee, Jinwoo Shin and Jonathan Richard Schwarz
Conference on Neural Information Processing Systems (NeurIPS), 2023 (based on the preliminary version [W35])

[C151] Guide Your Agent with Adaptive Multimodal Rewards (arXiv, code, site): Changyeon Kim, Younggyo Seo, Hao Liu, Lisa Lee, Jinwoo Shin, Honglak Lee and Kimin Lee
Conference on Neural Information Processing Systems (NeurIPS), 2023 (based on the preliminary version [W42])

[C150] Diffusion Probabilistic Models for Structured Node Classification (arXiv, code): Hyosoon Jang, Seonghyun Park, Sangwoo Mo and Sungsoo Ahn
Conference on Neural Information Processing Systems (NeurIPS), 2023 (based on the preliminary version [W40])

[C149] Collaborative Score Distillation for Consistent Visual Synthesis (arXiv, code, site): Subin Kim*, Kyungmin Lee*, June Suk Choi, Jongheon Jeong, Kihyuk Sohn, and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2023 (based on the preliminary version [W39])

[C148] Accelerating Reinforcement Learning with Value-Conditional State Entropy Exploration (arXiv, code, site): Dongyoung Kim, Jinwoo Shin, Pieter Abbeel and Younggyo Seo
Conference on Neural Information Processing Systems (NeurIPS), 2023

[C147] RoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training (arXiv, code): Jaehyung Kim, Yuning Mao, Rui Hou, Hanchao Yu, Davis Liang, Pascale Fung, Qifan Wang, Fuli Feng, Lifu Huang and Madian Khabsa
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023 (findings)

[C146] DAPPER: Label-Free Performance Estimation after Personalization for Heterogeneous Mobile Sensing (arXiv): Taesik Gong, Yewon Kim, Adiba Orzikulova, Yunxin Liu, Sung Ju Hwang, Jinwoo Shin and Sung-Ju Lee
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT), 2023 (will be presented at ACM UbiComp 2023)

[C145] Prefer to Classify: Improving Text Classifiers via Auxiliary Preference Learning (arXiv, code): Jaehyung Kim, Jinwoo Shin and Dongyeop Kang
International Conference on Machine Learning (ICML), 2023

[C144] Modality-Agnostic Variational Compression of Implicit Neural Representations (arXiv): Jonathan Richard Schwarz*, Jihoon Tack*, Yee Whye Teh, Jaeho Lee, and Jinwoo Shin
International Conference on Machine Learning (ICML), 2023

[C143] Multi-View Masked World Models for Visual Robotic Manipulation (arXiv, code, site): Younggyo Seo*, Junsu Kim*, Stephen James, Kimin Lee, Jinwoo Shin, Pieter Abbeel
International Conference on Machine Learning (ICML), 2023

[C142] infoVerse: A Universal Framework for Dataset Characterization with Multidimensional Meta-information (arXiv, code): Jaehyung Kim, Yekyung Kim, Karin Johanna, Denton de Langis, Jinwoo Shin and Dongyeop Kang
Annual Meeting of the Association for Computational Linguistics (ACL), 2023

[C141] WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation (arXiv): Jongheon Jeong*, Yang Zou*, Taewan Kim, DongQing Zhang, Avinash Ravichandran and Onkar Dabeer
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023

[C140] Video Probabilistic Diffusion Models in Projected Latent Space (arXiv, code, site): Sihyun Yu, Kihyuk Sohn, Subin Kim and Jinwoo Shin
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023

[C139] IFSeg: Image-free Semantic Segmentation via Vision-Language Model (arXiv, code, site): Sukmin Yun*, Seong Hyeon Park*, Paul Hongsuck Seo and Jinwoo Shin
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023

[C138] Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneck (arXiv, code): Jongheon Jeong, Sihyun Yu, Hankook Lee Lee and Jinwoo Shin
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023 (based on the preliminary version [W30])

[C137] BiasAdv: Bias-Adversarial Augmentation for Debiasing Classifier: Jongin Lim, Youngdong Kim, Byungjai Kim, Chanho Ahn, Jinwoo Shin, Eunho Yang and Seungju Han
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023

[C136] String-based Molecule Generation via Multi-decoder VAE (arXiv): Kisoo Kwon, Kuhwan Jeong, Junghyun Park Park, Hwidong Na and Jinwoo Shin
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023

[C135] Unsupervised Meta-learning via Few-shot Pseudo-supervised Contrastive Learning (arXiv, code): Huiwon Jang*, Hankook Lee* and Jinwoo Shin
International Conference on Learning Representations (ICLR), 2023 (based on the preliminary version [W34])
Spotlight Presentation (280/4956=5.6%)

[C134] STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables (arXiv, code): Jaehyun Nam, Jihoon Tack, Kyungmin Lee, Hankook Lee, and Jinwoo Shin
International Conference on Learning Representations (ICLR), 2023 (based on the preliminary version [W33])
Spotlight Presentation (280/4956=5.6%)

[C133] RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Data (arXiv, code, slide, poster): Sangwoo Mo, Jong-Chyi Su, Chih-Yao Ma, Mahmoud Assran, Ishan Misra, Licheng Yu and Sean Bell
International Conference on Learning Representations (ICLR), 2023

[C132] Preference Transformer: Modeling Human Preferences using Transformers for RL (arXiv, code, site): Changyeon Kim*, Jongjin Park*, Jinwoo Shin, Honglak Lee, Pieter Abbeel, and Kimin Lee
International Conference on Learning Representations (ICLR), 2023

[C131] Imitating Graph-Based Planning with Goal-Conditioned Policies (arXiv, code): Junsu Kim, Younggyo Seo, Sungsoo Ahn, Kyunghwan Son and Jinwoo Shin
International Conference on Learning Representations (ICLR), 2023

[C130] Guiding Energy-based Models via Contrastive Latent Variables (code): Hankook Lee, Jongheon Jeong, Sejun Park and Jinwoo Shin
International Conference on Learning Representations (ICLR), 2023 (based on the preliminary version [W31])
Spotlight Presentation (280/4956=5.6%)

[C129] Mosaic: Extremely Low-resolution RFID Vision for Visually-anonymized Action Recognition: Seungwoo Shim, Hyeonho Shin, Myeongkyun Cho, Youngki Lee, Jinwoo Shin and Song Min Kim
ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN), 2023

[C128] Contextual Linear Bandits under Noisy Features: Towards Bayesian Oracles: Jung-hun Kim, Se-Young Yun, Minchan Jeong, Junhyun Nam, Jinwoo Shin and Richard Combes
International Conference on Artificial Intelligence and Statistics (AISTATS), 2023

[C127] Rethinking the Entropy of Instance in Adversarial Training: Minseon Kim, Jihoon Tack, Jinwoo Shin and Sung Ju Hwang
IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), 2023 (based on the preliminary version [W20])

[C126] Everyone’s Voice Matters: Quantifying Annotation Disagreement Using Demographic Information (arXiv): Ruyuan Wan, Jaehyung Kim and Dongyeop Kang
AAAI Conference on Artificial Intelligence (AAAI), 2023
Oral Presentation

[C125] Confidence-aware Training of Smoothed Classifiers for Certified Robustness (arXiv, code): Jongheon Jeong*, Seojin Kim* and Jinwoo Shin
AAAI Conference on Artificial Intelligence (AAAI), 2023 (based on the preliminary version [W29])
Oral Presentation

[J30] Breaking the Spurious Causality of Conditional Generation via Fairness Intervention with Corrective Sampling (arXiv): Junhyun Nam, Sangwoo Mo, Jaeho Lee and Jinwoo Shin
Transactions on Machine Learning Research (TMLR), 2023 (based on the preliminary version [W44])

[W48] Data-Efficient Molecular Generation with Hierarchical Textual Inversion: Seojin Kim, Jaehyun Nam, Sihyun Yu, Younghoon Shin and Jinwoo Shin
NeurIPS Workshop on New Frontiers of AI for Drug Discovery and Development, 2023 (the newer version [C165] available at ICML 2024)

[W47] Fine-tuning protein Language Models by ranking protein fitness: Minji Lee, Kyungmin Lee and Jinwoo Shin
NeurIPS Workshop on Generative AI and Biology (GenBio), 2023

[W46] Multi-View Masked World Models for Visual Robotic Manipulation: Younggyo Seo*, Junsu Kim*, Stephen James, Kimin Lee, Jinwoo Shin, and Pieter Abbeel
RSS Workshop on Experiment-oriented Locomotion and Manipulation Research, 2023
Spotlight Presentation

[W45] Bias-to-Text: Debiasing Unknown Visual Biases by Language Interpretation (arXiv, code): Younghyun Kim*, Sangwoo Mo*, Minkyu Kim, Kyungmin Lee, Jaeho Lee, Jinwoo Shin
ICML Workshop on Spurious Correlations, Invariance and Stability, 2023 (the newer version [C163] available at CVPR 2024)

[W44] Breaking the Spurious Causality of Conditional Generation via Fairness Intervention with Corrective Sampling (arXiv): Junhyun Nam, Sangwoo Mo, Jaeho Lee and Jinwoo Shin
ICML Workshop on Spurious Correlations, Invariance and Stability, 2023 (the newer version [J30] available at Transactions on Machine Learning Research)

[W43] Semi-supervised Tabular Classification via In-context Learning of Large Language Models: Jaehyun Nam, Woomin Song, Seong Hyeon Park, Jihoon Tack, Sukmin Yun, Jaehyung Kim, and Jinwoo Shin
ICML Workshop on Efficient Systems for Foundation Models, 2023 (the newer version [C168] available at COLM 2024)

[W42] Guide Your Agent with Adaptive Multimodal Rewards: Changyeon Kim, Younggyo Seo, Hao Liu, Lisa Lee, Jinwoo Shin, Honglak Lee, and Kimin Lee
ICML Workshop on New Frontiers in Learning, Control, and Dynamical Systems, 2023 (the newer version [C151] available at NeurIPS 2023)

[W41] Few-shot Anomaly Detection via Personalization: Sangkyung Kwak, Jongheon Jeong, Hankook Lee, Woohyuck Kim, and Jinwoo Shin
ICML Workshop on New Frontiers in Adversarial Machine Learning, 2023

[W40] Diffusion Probabilistic Models for Structured Node Classification (arXiv, code): Hyosoon Jang, Seonghyun Park, Sangwoo Mo and Sungsoo Ahn
ICML Workshop on Structured Probabilistic Inference & Generative Modeling, 2023 (the newer version [C150] available at NeurIPS 2023)

[W39] Collaborative Score Distillation for Consistent Visual Synthesis: Subin Kim*, Kyungmin Lee*, June Suk Choi, Jongheon Jeong, Kihyuk Sohn, and Jinwoo Shin
ICML Workshop on Structured Probabilistic Inference & Generative Modeling, 2023 (the newer version [C149] available at NeurIPS 2023)

[W38] Towards Safe Self-Distillation of Internet-Scale Text-to-Image Diffusion Models: Sanghyun Kim, Seohyeon Jung, Balhae Kim Kim, Moonseok Choi Choi, Jinwoo Shin and Juho Lee
ICML Workshop on Deployable Generative AI, 2023

[W37] Modality-Agnostic Variational Compression of Implicit Neural Representations (arXiv): Jonathan Richard Schwarz*, Jihoon Tack*, Yee Whye Teh, Jaeho Lee, and Jinwoo Shin
ICLR Workshop on Neural Fields across Fields: Methods and Applications of Implicit Neural Representations, 2023

[W36] Fragment-based Multi-view Molecular Contrastive Learning: Seojin Kim*, Jaehyun Nam*, Junsu Kim, Hankook Lee, Sungsoo Ahn, and Jinwoo Shin
ICLR Workshop on Machine Learning for Materials: From Molecules to Materials, 2023 (the newer version [J31] available at Transactions on Machine Learning Research)

[W35] Efficient Meta-Learning via Error-based Context Pruning for Implicit Neural Representations (arXiv): Jihoon Tack, Subin Kim, Sihyun Yu, Jaeho Lee, Jinwoo Shin and Jonathan Richard Schwarz
ICLR Workshop on Neural Fields across Fields: Methods and Applications of Implicit Neural Representations, 2023 (the newer version [C152] available at NeurIPS 2023)

2022

[C124] Scalable Neural Video Representations with Learnable Positional Features (arXiv, code, site): Subin Kim*, Sihyun Yu*, Jaeho Lee, and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2022

[C123] RenyiCL: Contrastive Representation Learning with Skew Renyi Divergence (arXiv, code): Kyungmin Lee and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2022

[C122] NOTE: Robust Continual Test-time Adaptation Against Temporal Correlation (arXiv, code): Taesik Gong, Jongheon Jeong, Taewon Kim, Yewon Kim, Jinwoo Shin and Sung-Ju Lee
Conference on Neural Information Processing Systems (NeurIPS), 2022

[C121] Meta-Learning with Self-Improving Momentum Target (arXiv, code): Jihoon Tack, Jongjin Park, Hankook Lee, Jaeho Lee and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2022

[C120] Masked World Models for Visual Control (arXiv, code): Younggyo Seo, Danijar Hafner, Hao Liu, Fangchen Liu, Stephen James, Kimin Lee and Pieter Abbeel
Conference on Robot Learning (CoRL), 2022

[C119] SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation (arXiv, code): Yang Zou, Jongheon Jeong, Latha Pemula, Zhang Dongqing and Onkar Dabeer
European Conference on Computer Vision (ECCV), 2022

[C118] K-centered Patch Sampling for Efficient Video Recognition (code): Seong Hyeon Park, Jihoon Tack, Byeongho Heo, Jung-Woo Ha and Jinwoo Shin
European Conference on Computer Vision (ECCV), 2022

[C117] Time Is MattEr: Temporal Self-supervision for Video Transformers (arXiv, code): Sukmin Yun, Jaehyung Kim, Dongyoon Han, Hwanjun Song, Jung-Woo Ha and Jinwoo Shin
International Conference on Machine Learning (ICML), 2022

[C116] TSPipe: Learn from Teacher Faster with Pipelines: Hwijoon Lim, Yechan Kim, Sukmin Yun, Jinwoo Shin and Dongsu Han
International Conference on Machine Learning (ICML), 2022

[C115] Reinforcement Learning with Action-Free Pre-Training from Videos (arXiv, code, site): Younggyo Seo, Kimin Lee, Stephen James and Pieter Abbeel
International Conference on Machine Learning (ICML), 2022

[C114] Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning: Kyunghwan Son, Junsu Kim, Sungsoo Ahn, Roben Delos Reyes, Yung Yi and Jinwoo Shin
International Conference on Machine Learning (ICML), 2022

[C113] Self-Supervised Dense Consistency Regularization for Image-to-Image Translation: Minsu Ko, Eunju Cha, Sungjoo Suh, Huijin Lee, Jae-Joon Han, Jinwoo Shin and Bohyung Han
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022

[C112] Patch-level Representation Learning for Self-supervised Vision Transformers (arXiv, code): Sukmin Yun, Hankook Lee, Jaehyung Kim and Jinwoo Shin
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
Oral Presentation (342/8262=4.14%)

[C111] Contrastive Dual Gating: Learning Sparse Features With Contrastive Learning: Jian Meng, Li Yang, Jinwoo Shin, Deliang Fan and Jae-sun Seo
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022

[C110] What Makes Better Augmentation Strategies? Augment Difficult but Not too Different: Jaehyung Kim, Dongyeop Kang, Sungsoo Ahn and Jinwoo Shin
International Conference on Learning Representations (ICLR), 2022

[C109] Spread Spurious Attribute: Improving Worst-group Accuracy with Spurious Attribute Estimation: Junhyun Nam, Jaehyung Kim, Jaeho Lee and Jinwoo Shin
International Conference on Learning Representations (ICLR), 2022

[C108] SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning (arXiv, code): Jongjin Park, Younggyo Seo, Jinwoo Shin, Honglak Lee, Pieter Abbeel and Kimin Lee
International Conference on Learning Representations (ICLR), 2022 (based on the preliminary version [W26])

[C107] Model-augmented Prioritized Experience Replay: Youngmin Oh, Jinwoo Shin, Eunho Yang and Sung Ju Hwang
International Conference on Learning Representations (ICLR), 2022

[C106] Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks (arXiv, code, site): Sihyun Yu*, Jihoon Tack*, Sangwoo Mo*, Hyunsu Kim, Junho Kim, Jung-Woo Ha, and Jinwoo Shin
International Conference on Learning Representations (ICLR), 2022

[C105] Saliency Grafting: Innocuous Attribution-Guided Mixup with Calibrated Label Mixing (arXiv): Joonhyung Park, June Yong Yang, Jinwoo Shin, Sung Ju Hwang and Eunho Yang
AAAI Conference on Artificial Intelligence (AAAI), 2022

[C104] Consistency Regularization for Adversarial Robustness (arXiv, code, slide): Jihoon Tack, Sihyun Yu, Jongheon Jeong, Minseon Kim, Sung Ju Hwang and Jinwoo Shin
AAAI Conference on Artificial Intelligence (AAAI), 2022 (based on the preliminary version [W19])

[J29] Adapting to Unknown Conditions in Learning-based Mobile Sensing: Taesik Gong, Yeonsu Kim, Ryuhaerang Choi, Jinwoo Shin and Sung-Ju Lee
IEEE Transactions on Mobile Computing (TMC), vol. 21, no. 10, pp. 3470–3485, 2022

[W34] Unsupervised Meta-learning via Few-shot Pseudo-supervised Contrastive Learning: Huiwon Jang*, Hankook Lee* and Jinwoo Shin
NeurIPS Workshop on Meta-Learning, 2022 (the newer version [C135] available at ICLR 2023)

[W33] STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables: Jaehyun Nam, Jihoon Tack, Kyungmin Lee, Hankook Lee, and Jinwoo Shin
NeurIPS Workshop on Table Representation Learning, 2022 (the newer version [C134] available at ICLR 2023)

[W32] Dynamics-Augmented Decision Transformer for Offline Dynamics Generalization: Changyeon Kim*, Junsu Kim*, Younggyo Seo, Kimin Lee, Honglak Lee, and Jinwoo Shin
NeurIPS Workshop on Offline Reinforcement Learning, 2022

[W31] Guiding Energy-based Models via Contrastive Latent Variables: Hankook Lee, Jongheon Jeong, Sejun Park and Jinwoo Shin
NeurIPS Workshop on Self-Supervised Learning: Theory and Practice, 2022 (the newer version [C130] available at ICLR 2023)
Oral Presentation

[W30] Learning Robust Representations via Nuisance-extended Information Bottleneck: Jongheon Jeong, Sihyun Yu, Hankook Lee and Jinwoo Shin
ECCV Workshop on Out-of-distribution Generalization in Computer Vision, 2022 (the newer version [C138] available at CVPR 2023)

[W29] Confidence-aware Training of Smoothed Classifiers for Certified Robustness: Jongheon Jeong*, Seojin Kim* and Jinwoo Shin
ECCV Workshop on Adversarial Robustness in the Real World, 2022 (the newer version [C125] available at AAAI 2023)

[W28] OpenCoS: Contrastive Semi-supervised Learning for Handling Open-set Unlabeled Data (arXiv, code): Jongjin Park*, Sukmin Yun*, Jongheon Jeong, and Jinwoo Shin
ECCV Workshop on Learning from Limited and Imperfect Data, 2022

[W27] ReMixer: Object-aware Mixing Layer for Vision Transformers and Mixers: Hyunwoo Kang*, Sangwoo Mo* and Jinwoo Shin
ICLR Workshop on the Elements of Reasoning: Objects, Structure and Causality, 2022

2021

[C103] Scaling Neural Tangent Kernels via Sketching and Random Features (arXiv, code): Amir Zandieh*, Insu Han*, Haim Avron, Neta Shoham, Chaewon Kim and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2021

[C102] SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness (arXiv, code): Jongheon Jeong, Sejun Park, Minkyu Kim, Heung-Chang Lee, Doguk Kim and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2021 (based on the preliminary version [W21])

[C101] RoMA: Robust Model Adaptation for Offline Model-based Optimization (arXiv, code, slide): Sihyun Yu, Sungsoo Ahn, Le Song and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2021

[C100] Object-aware Contrastive Learning for Debiased Scene Representation (arXiv, code, slide): Sangwoo Mo*, Hyunwoo Kang*, Kihyuk Sohn, Chun-Liang Li and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2021

[C99] Object-Aware Regularization for Addressing Causal Confusion in Imitation Learning (arXiv, code): Jongjin Park*, Younggyo Seo*, Chang Liu, Li Zhao, Tao Qin, Jinwoo Shin and Tie-Yan Liu
Conference on Neural Information Processing Systems (NeurIPS), 2021

[C98] Meta-Learning Sparse Implicit Neural Representations (arXiv, code): Jaeho Lee*, Jihoon Tack*, Namhoon Lee, and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2021 (based on the preliminary version [W25])

[C97] Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning (arXiv, code, slide): Junsu Kim, Younggyo Seo and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2021

[C96] Improving Transferability of Representations via Augmentation-Aware Self-Supervision (arXiv, code, slide): Hankook Lee, Kibok Lee, Kimin Lee, Honglak Lee and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2021 (based on the preliminary version [W23])

[C95] Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble (arXiv): Seunghyun Lee*, Younggyo Seo*, Kimin Lee, Pieter Abbeel and Jinwoo Shin
Conference on Robot Learning (CoRL), 2021 (based on the preliminary version [W13])

[C94] Co²L: Contrastive Continual Learning (arXiv, code): Hyuntak Cha, Jaeho Lee and Jinwoo Shin
IEEE/CVF International Conference on Computer Vision (ICCV), 2021

[C93] RetCL: A Selection-based Approach for Retrosynthesis via Contrastive Learning (arXiv): Hankook Lee, Sungsoo Ahn, Seung-Woo Seo, You Young Song, Sung Ju Hwang, Eunho Yang and Jinwoo Shin
International Joint Conference on Artificial Intelligence (IJCAI), 2021 (based on the preliminary version [W16])

[C92] Provable Memorization via Deep Neural Networks using Sub-linear Parameters (arXiv): Sejun Park, Jaeho Lee, Chulhee Yun and Jinwoo Shin
Conference on Learning Theory (COLT), 2021

[C91] State Entropy Maximization with Random Encoders for Efficient Exploration (arXiv, code, site): Younggyo Seo*, Lili Chen*, Jinwoo Shin, Honglak Lee, Pieter Abbeel and Kimin Lee
International Conference on Machine Learning (ICML), 2021 (based on the preliminary version [W17])

[C90] Self-Improved Retrosynthetic Planning (arXiv, code, slide, poster): Junsu Kim, Sungsoo Ahn, Hankook Lee and Jinwoo Shin
International Conference on Machine Learning (ICML), 2021

[C89] Learning to Generate Noise for Multi-Attack Robustness: Divyam Madaan, Jinwoo Shin and Sung Ju Hwang
International Conference on Machine Learning (ICML), 2021 (based on the preliminary version [W15])

[C88] Quality-Agnostic Image Recognition via Invertible Decoder: Insoo Kim, Seungju Han, Ji-won Baek, Seong-Jin Park, Jae-Joon Han and Jinwoo Shin
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021

[C87] Training GANs with Stronger Augmentations via Contrastive Discriminator (arXiv, code, slide, poster): Jongheon Jeong and Jinwoo Shin
International Conference on Learning Representations (ICLR), 2021

[C86] Minimum Width for Universal Approximation (arXiv): Sejun Park, Chulhee Yun, Jaeho Lee and Jinwoo Shin
International Conference on Learning Representations (ICLR), 2021
Spotlight Presentation (114/2997=3.8%)

[C85] Learning to Sample with Local and Global Contexts in Experience Replay Buffer (arXiv): Youngmin Oh, Kimin Lee, Jinwoo Shin, Eunho Yang and Sung Ju Hwang
International Conference on Learning Representations (ICLR), 2021 (based on the preliminary version [W14])

[C84] Layer-adaptive Sparsity for the Magnitude-based Pruning (arXiv): Jaeho Lee, Sejun Park, Sangwoo Mo, Sungsoo Ahn and Jinwoo Shin
International Conference on Learning Representations (ICLR), 2021

[C83] i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning (arXiv): Kibok Lee, Yian Zhu, Kihyuk Sohn, Chun-Liang Li, Jinwoo Shin and Honglak Lee
International Conference on Learning Representations (ICLR), 2021 (based on the preliminary version [W12])

[C82] MASKER: Masked Keyword Regularization for Reliable Text Classification (arXiv, code, slide, poster): Seung Jun Moon*, Sangwoo Mo*, Kimin Lee, Jaeho Lee and Jinwoo Shin
AAAI Conference on Artificial Intelligence (AAAI), 2021

[C81] GTA: Graph Truncated Attention for Retrosynthesis: Seung-Woo Seo, You Young Song, June Yong Yang, Seohui Bae, Hankook Lee, Jinwoo Shin, Sung Ju Hwang and Eunho Yang
AAAI Conference on Artificial Intelligence (AAAI), 2021

[C80] Elastic Resource Sharing for Distributed Deep Learning: Changho Hwang, Taehyun Kim, Sunghyun Kim, Jinwoo Shin and KyoungSoo Park
USENIX Symposium on Networked Systems Design and Implementation (NSDI), 2021

[J28] Deep Neural Network Based Electrical Impedance Tomographic Sensing Methodology for Large-Area Robotic Tactile Sensing: Hyunkyu Park, Kyungseo Park, Sangwoo Mo and Jung Kim
IEEE Transactions on Robotics (T-RO), vol. 37, no. 5, pp. 1570–1583, 2021

[W26] SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning: Jongjin Park, Younggyo Seo, Jinwoo Shin, Honglak Lee, Pieter Abbeel and Kimin Lee
NeurIPS Workshop on Deep Reinforcement Learning, 2021 (the newer version [C108] available at ICLR 2022)

[W25] Meta-Learning Sparse Implicit Neural Representations: Jaeho Lee, Jihoon Tack, Namhoon Lee and Jinwoo Shin
Workshop on Sparsity in Neural Networks: Advancing Understanding and Practice, 2021 (the newer version [C98] available at NeurIPS 2021)

[W24] GreedyPrune: Layer-wise optimization algorithms for magnitude-based pruning: Vinoth Nandakumar and Jaeho Lee
Workshop on Sparsity in Neural Networks: Advancing Understanding and Practice, 2021

[W23] Improving Transferability of Representations via Augmentation-Aware Self-Supervision: Hankook Lee, Kibok Lee, Kimin Lee, Honglak Lee and Jinwoo Shin
ICML Workshop on Self-Supervised Learning for Reasoning and Perception, 2021 (the newer version [C96] available at NeurIPS 2021)

[W22] Abstract Reasoning via Logic-guided Generation (arXiv): Sihyun Yu, Sangwoo Mo, Sungsoo Ahn and Jinwoo Shin
ICML Workshop on Self-Supervised Learning for Reasoning and Perception, 2021
Oral Presentation

[W21] SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Adversarial Robustness: Jongheon Jeong, Sejun Park, Minkyu Kim, Heung-Chang Lee, Doguk Kim and Jinwoo Shin
ICML Workshop on Adversarial Machine Learning, 2021 (the newer version [C102] available at NeurIPS 2021)

[W20] Entropy Weighted Adversarial Training: Minseon Kim, Jihoon Tack, Jinwoo Shin and Sung Ju Hwang
ICML Workshop on Adversarial Machine Learning, 2021 (the newer version [C127] available at SaTML 2023)

[W19] Consistency Regularization for Adversarial Robustness (arXiv, code, slide): Jihoon Tack, Sihyun Yu, Jongheon Jeong, Minseon Kim, Sung Ju Hwang and Jinwoo Shin
ICML Workshop on Adversarial Machine Learning, 2021 (the newer version [C104] available at AAAI 2022)
Oral Presentation

[W18] Consistency Regularization for Training Confidence-Calibrated Classifiers: Youngbum Hur*, Jihoon Tack*, Eunho Yang, Sung Ju Hwang and Jinwoo Shin
ICML Workshop on Uncertainty & Robustness in Deep Learning, 2021

[W17] State Entropy Maximization with Random Encoders for Efficient Exploration (arXiv): Younggyo Seo*, Lili Chen*, Jinwoo Shin, Honglak Lee, Pieter Abbeel and Kimin Lee
ICLR Workshop on Self-Supervision on Reinforcement Learning, 2021 (the newer version [C91] available at ICML 2021)

2020

[C79] Time-Reversal Symmetric ODE Network (arXiv, code): In Huh, Eunho Yang, Sung Ju Hwang and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2020

[C78] Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning (arXiv, code, site): Younggyo Seo*, Kimin Lee*, Ignasi Clavera, Thanard Kurutach, Jinwoo Shin and Pieter Abbeel
Conference on Neural Information Processing Systems (NeurIPS), 2020

[C77] Learning from Failure: De-biasing Classifier from Biased Classifier (arXiv, code): Junhyun Nam, Hyuntak Cha, Sungsoo Ahn, Jaeho Lee and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2020

[C76] Learning Bounds for Risk-sensitive Learning (arXiv, code, slide): Jaeho Lee, Sejun Park and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2020

[C75] Guiding Deep Molecular Optimization with Genetic Exploration (arXiv, code): Sungsoo Ahn, Junsu Kim, Hankook Lee and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2020

[C74] Few-shot Visual Reasoning with Meta-Analogical Contrastive Learning (arXiv): Youngsung Kim, Jinwoo Shin, Eunho Yang and Sung Ju Hwang
Conference on Neural Information Processing Systems (NeurIPS), 2020

[C73] Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning (arXiv, code, slide): Jaehyung Kim, Youngbum Hur, Sejun Park, Eunho Yang, Sung Ju Hwang and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2020

[C72] CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances (arXiv, code, slide, poster): Jihoon Tack*, Sangwoo Mo*, Jongheon Jeong and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2020

[C71] Consistency Regularization for Certified Robustness of Smoothed Classifiers (arXiv, code): Jongheon Jeong and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2020 (based on the preliminary version [W10])

[C70] Adversarial Self-Supervised Contrastive Learning (arXiv, code, site): Minseon Kim, Jihoon Tack and Sung Ju Hwang
Conference on Neural Information Processing Systems (NeurIPS), 2020

[C69] DiscFace: Minimum Discrepancy Learning for Deep Face Recognition: Insoo Kim, Seungju Han, Seong-Jin Park, Ji-won Baek, Jinwoo Shin, Jae-Joon Han and Changkyu Choi
Asian Conference on Computer Vision (ACCV), 2020

[C68] MAP Inference for Customized Determinantal Point Processes via Maximum Inner Product Search: Insu Han and Jennifer Gillenwater
International Conference on Artificial Intelligence and Statistics (AISTATS), 2020

[C67] Self-supervised Label Augmentation via Input Transformations (arXiv, code, talk): Hankook Lee, Sung Ju Hwang and Jinwoo Shin
International Conference on Machine Learning (ICML), 2020

[C66] Polynomial Tensor Sketch for Element-wise Function of Low-Rank Matrix (arXiv, talk): Insu Han, Haim Avron and Jinwoo Shin
International Conference on Machine Learning (ICML), 2020

[C65] Learning What to Defer for Maximum Independent Sets (arXiv, code, talk): Sungsoo Ahn, Younggyo Seo and Jinwoo Shin
International Conference on Machine Learning (ICML), 2020

[C64] Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning (arXiv, code, site, talk): Kimin Lee*, Younggyo Seo*, Seunghyun Lee, Honglak Lee and Jinwoo Shin
International Conference on Machine Learning (ICML), 2020

[C63] Adversarial Neural Pruning with Latent Vulnerability Suppression (arXiv, code, talk): Divyam Madaan, Jinwoo Shin and Sung Ju Hwang
International Conference on Machine Learning (ICML), 2020

[C62] Regularizing Class-Wise Predictions via Self-Knowledge Distillation (arXiv, code): Sukmin Yun*, Jongjin Park*, Kimin Lee and Jinwoo Shin
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020

[C61] M2m: Imbalanced Classification via Major-to-Minor Translation (arXiv, code, slide): Jaehyung Kim*, Jongheon Jeong* and Jinwoo Shin
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020

[C60] Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning (arXiv, code): Kimin Lee*, Kibok Lee*, Jinwoo Shin and Honglak Lee
International Conference on Learning Representations (ICLR), 2020 (based on the preliminary version [W8])

[C59] Lookahead: A Far-sighted Alternative of Magnitude-based Pruning (arXiv, code, slide): Sejun Park*, Jaeho Lee*, Sangwoo Mo and Jinwoo Shin
International Conference on Learning Representations (ICLR), 2020

[J27] Information Source Finding in Networks: Querying With Budgets (arXiv): Jaeyoung Choi, Sangwoo Moon, Jiin Woo, Kyunghwan Son, Jinwoo Shin and Yung Yi
IEEE/ACM Transactions on Networking (TON), vol. 28, no. 5, pp. 2271–2284, 2020

[J26] Dynamic Control for On-Demand Interference-Managed WLAN Infrastructures: Seokhyun Kim, Kimin Lee, Yeonkeun Kim, Jinwoo Shin, Seungwon Shin and Song Chong
IEEE/ACM Transactions on Networking (TON), vol. 28, no. 1, pp. 84–97, 2020

[W16] RetCL: A Selection-based Approach for Retrosynthesis via Contrastive Learning (arXiv): Hankook Lee, Sungsoo Ahn, Seung-Woo Seo, You Young Song, Sung Ju Hwang, Eunho Yang and Jinwoo Shin
NeurIPS Workshop on Machine Learning for Molecules, 2020 (the newer version [C93] available at IJCAI 2021)

[W15] Learning to Generate Noise for Multi-Attack Robustness: Divyam Madaan, Jinwoo Shin and Sung Ju Hwang
NeurIPS Workshop on Meta-Learning, 2020 (the newer version [C89] available at ICML 2021)

[W14] Learning to Sample with Local and Global Contexts in Experience Replay Buffer (arXiv): Youngmin Oh, Kimin Lee, Jinwoo Shin, Eunho Yang and Sung Ju Hwang
NeurIPS Workshop on Deep Reinforcement Learning, 2020 (the newer version [C85] available at ICLR 2021)

[W13] Addressing Distribution Shift in Online Reinforcement Learning with Offline Datasets: Seunghyun Lee*, Younggyo Seo*, Kimin Lee, Pieter Abbeel and Jinwoo Shin
NeurIPS Workshop on Offline Reinforcement Learning, 2020 (the newer version [C95] available at CoRL 2021)
Oral Presentation

[W12] i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning (arXiv): Kibok Lee, Yian Zhu, Kihyuk Sohn, Chun-Liang Li, Jinwoo Shin and Honglak Lee
NeurIPS Workshop on Self-Supervised Learning: Theory and Practice, 2020 (the newer version [C83] available at ICLR 2021)

[W11] Platform-Agnostic Lightweight Deep Learning for Garbage Collection Scheduling in SSDs (talk): Junhyeok Jang, Donghyun Gouk, Jinwoo Shin and Myoungsoo Jung
USENIX Workshop on Hot Topics in Storage and File Systems, 2020

[W10] Consistency Regularization for Certified Robustness of Smoothed Classifiers (arXiv): Jongheon Jeong and Jinwoo Shin
ICML Workshop on Uncertainty & Robustness in Deep Learning, 2020 (the newer version [C71] available at NeurIPS 2020)

[W9] Freeze Discriminator: A Simple Baseline for Fine-tuning GANs (arXiv, code, slide, talk): Sangwoo Mo, Minsu Cho and Jinwoo Shin
CVPR Workshop on AI for Content Creation, 2020

2019

[C58] Mining GOLD Samples for Conditional GANs (arXiv, code, poster): Sangwoo Mo, Chiheon Kim, Sungwoong Kim, Minsu Cho and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2019

[C57] Deep Neural Network Approach in Electrical Impedance Tomography-based Real-time Soft Tactile Sensor: Hyunkyu Park, Hyosang Lee, Kyungseo Park, Sangwoo Mo and Jung Kim
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019

[C56] MetaSense: Few-Shot Adaptation to Untrained Conditions in Deep Mobile Sensing (talk): Taesik Gong, Yeonsu Kim, Jinwoo Shin and Sung-Ju Lee
Conference on Embedded Networked Sensor Systems (SenSys), 2019 (based on the preliminary version [C54])

[C55] Overcoming Catastrophic Forgetting With Unlabeled Data in the Wild (arXiv): Kibok Lee, Kimin Lee, Jinwoo Shin and Honglak Lee
IEEE/CVF International Conference on Computer Vision (ICCV), 2019 (based on the preliminary version [W7])

[C54] Towards Condition-Independent Deep Mobile Sensing: Taesik Gong, Yeonsu Kim, Jinwoo Shin and Sung-Ju Lee
International Conference on Mobile Systems, Applications, and Services (MobiSys), 2019 (poster track)

[C53] Variational Information Distillation for Knowledge Transfer (arXiv, code): Sungsoo Ahn, Shell Xu Hu, Andreas Damianou, Neil D. Lawrence and Zhenwen Dai
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019 (based on the preliminary version [W6])

[C52] Using Pre-Training Can Improve Model Robustness and Uncertainty (arXiv, code): Dan Hendrycks, Kimin Lee and Mantas Mazeika
International Conference on Machine Learning (ICML), 2019

[C51] Training CNNs with Selective Allocation of Channels (arXiv, code): Jongheon Jeong and Jinwoo Shin
International Conference on Machine Learning (ICML), 2019

[C50] Spectral Approximate Inference (arXiv, code): Sejun Park, Eunho Yang, Se-Young Yun and Jinwoo Shin
International Conference on Machine Learning (ICML), 2019

[C49] Robust Inference via Generative Classifiers for Handling Noisy Labels (arXiv, code): Kimin Lee, Sukmin Yun, Kibok Lee, Honglak Lee, Bo Li and Jinwoo Shin
International Conference on Machine Learning (ICML), 2019 (based on the preliminary version [W5])
Long Oral Presentation (159/3424=4.6%)

[C48] Learning What and Where to Transfer (arXiv, code): Yunhun Jang*, Hankook Lee*, Sung Ju Hwang and Jinwoo Shin
International Conference on Machine Learning (ICML), 2019

[C47] Bitcoin vs. Bitcoin Cash: Coexistence or Downfall of Bitcoin Cash? (arXiv, site): Yujin Kwon, Hyoungshick Kim, Jinwoo Shin and Yongdae Kim
IEEE Symposium on Security and Privacy (S&P), 2019

[C46] InstaGAN: Instance-aware Image-to-Image Translation (arXiv, code, poster, media1, media2, media3, media4): Sangwoo Mo, Minsu Cho and Jinwoo Shin
International Conference on Learning Representations (ICLR), 2019

[C45] Iterative Bayesian Learning for Crowdsourced Regression (arXiv, code): Jungseul Ok, Sewoong Oh, Yunhun Jang, Jinwoo Shin and Yung Yi
International Conference on Artificial Intelligence and Statistics (AISTATS), 2019

[J25] Gauging Variational Inference (arXiv): Sung-Soo Ahn, Michael Chertkov and Jinwoo Shin
Journal of Statistical Mechanics: Theory and Experiment (JSTAT), vol. 2019, no. 12, pp. 124015, 2019

[J24] Bucket Renormalization for Approximate Inference (arXiv): Sungsoo Ahn, Michael Chertkov, Adrian Weller and Jinwoo Shin
Journal of Statistical Mechanics: Theory and Experiment (JSTAT), vol. 2019, no. 12, pp. 124022, 2019

[J23] Simulation-Based Distributed Coordination Maximization Over Networks (arXiv): Hyeryung Jang, Jinwoo Shin and Yung Yi
IEEE Transactions on Control of Network Systems (TCNS), vol. 6, no. 2, pp. 713–726, 2019

[J22] Information source localization with protector diffusion in networks: Jaeyoung Choi, Jinwoo Shin and Yung Yi
Journal of Communications and Networks (JCN), vol. 21, no. 2, pp. 136–147, 2019

[W8] Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning (arXiv): Kimin Lee*, Kibok Lee*, Jinwoo Shin and Honglak Lee
NeurIPS Workshop on Deep Reinforcement Learning, 2019 (the newer version [C60] available at ICLR 2020)
Oral Presentation

[W7] Incremental Learning with Unlabeled Data in the Wild: Kibok Lee, Kimin Lee, Jinwoo Shin and Honglak Lee
CVPR Workshop on Uncertainty and Robustness in Deep Visual Learning, 2019 (the newer version [C55] available at ICCV 2019)

2018

[C44] Stochastic Chebyshev Gradient Descent for Spectral Optimization (arXiv, poster, talk): Insu Han, Haim Avron and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2018
Spotlight Presentation (168/4856=3.5%)

[C43] Learning to Specialize with Knowledge Distillation for Visual Question Answering: Jonghwan Mun, Kimin Lee, Jinwoo Shin and Bohyung Han
Conference on Neural Information Processing Systems (NeurIPS), 2018

[C42] A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks (arXiv, code, poster, talk): Kimin Lee, Kibok Lee, Honglak Lee and Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2018 (based on the preliminary version [W4])
Spotlight Presentation (168/4856=3.5%)

[C41] Neural Adaptive Content-aware Internet Video Delivery (site): Hyunho Yeo, Youngmok Jung, Jaehong Kim, Jinwoo Shin and Dongsu Han
USENIX Symposium on Operating Systems Design and Implementation (OSDI), 2018
First Paper from KAIST in the history of OSDI

[C40] Bucket Renormalization for Approximate Inference (arXiv, poster): Sungsoo Ahn, Michael Chertkov, Adrian Weller and Jinwoo Shin
International Conference on Machine Learning (ICML), 2018 (also invited as [J24] to Journal of Statistical Mechanics: Theory and Experiment)

[C39] Exact Topology and Parameter Estimation in Distribution Grids with Minimal Observability (arXiv): Sejun Park, Deepjyoti Deka and Michael Chcrtkov
Power Systems Computation Conference (PSCC), 2018

[C38] Hierarchical Novelty Detection for Visual Object Recognition (arXiv, poster): Kibok Lee, Kimin Lee, Kyle Min, Yuting Zhang, Jinwoo Shin and Honglak Lee
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018

[C37] Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples (arXiv, code, slide, poster): Kimin Lee, Honglak Lee, Kibok Lee and Jinwoo Shin
International Conference on Learning Representations (ICLR), 2018 (based on the preliminary version [W3])

[C36] Gauged Mini-Bucket Elimination for Approximate Inference (arXiv, poster): Sungsoo Ahn, Michael Chertkov, Jinwoo Shin and Adrian Weller
International Conference on Artificial Intelligence and Statistics (AISTATS), 2018

[C35] Multi-Armed Bandit with Additional Observations: Donggyu Yun, Alexandre Proutiere, Sumyeong Ahn, Jinwoo Shin and Yung Yi
ACM International Conference on Measurement and Modeling of Computer Systems (SIGMETRICS), 2018

[J21] Optimal Inference in Crowdsourced Classification via Belief Propagation (arXiv): Jungseul Ok, Sewoong Oh, Jinwoo Shin and Yung Yi
IEEE Transactions on Information Theory (TIT), vol. 64, no. 9, pp. 6127–6138, 2018 (based on the preliminary version [C24])

[J20] Maximum Weight Matching Using Odd-Sized Cycles: Max-Product Belief Propagation and Half-Integrality (arXiv): Sungsoo Ahn, Michael Chertkov, Andrew E. Gelfand, Sejun Park and Jinwoo Shin
IEEE Transactions on Information Theory (TIT), vol. 64, no. 3, pp. 1471–1480, 2018 (based on the preliminary version [C13])

[J19] Game Theoretic Perspective of Optimal CSMA: Hyeryung Jang, Se-Young Yun, Jinwoo Shin and Yung Yi
IEEE Transactions on Wireless Communications (TWC), vol. 17, no. 1, pp. 194–209, 2018 (based on the preliminary version [C25])

[I3] Learning in Power Distribution Grids under Correlated Injections: Sejun Park, Deepjyoti Deka and Michael Chertkov
Asilomar Conference on Signals, Systems and Computers (ACSSC), 2018

[W6] Variational Mutual Information Distillation for Transfer Learning: Sungsoo Ahn, Shell Xu Hu, Andreas Damianou, Neil D. Lawrence and Zhenwen Dai
NeurIPS Workshop on Continual Learning, 2018 (the newer version [C53] available at CVPR 2019)

[W5] Robust Determinantal Generative Classifier for Noisy Labels and Adversarial Attacks: Kimin Lee, Sukmin Yun, Kibok Lee, Honglak Lee, Bo Li and Jinwoo Shin
NeurIPS Workshop on Bayesian Deep Learning, 2018 (the newer version [C49] available at ICML 2019)

[W4] A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks (arXiv): Kimin Lee, Kibok Lee, Honglak Lee and Jinwoo Shin
ICML Workshop on Theoretical Foundations and Applications of Deep Generative Models, 2018 (the newer version [C42] available at NeurIPS 2018)

2017

[C34] Gauging Variational Inference (arXiv, poster): Sung-Soo Ahn, Michael Chertkov and Jinwoo Shin
Conference on Neural Information Processing Systems (NIPS), 2017 (also invited as [J25] to Journal of Statistical Mechanics: Theory and Experiment)

[C33] Faster Greedy MAP Inference for Determinantal Point Processes (arXiv, code, poster, talk, slide): Insu Han, Prabhanjan Kambadur, Kyoungsoo Park and Jinwoo Shin
International Conference on Machine Learning (ICML), 2017

[C32] Confident Multiple Choice Learning (arXiv): Kimin Lee, Changho Hwang, KyoungSoo Park and Jinwoo Shin
International Conference on Machine Learning (ICML), 2017

[C31] Adiabatic Persistent Contrastive Divergence learning (arXiv): Hyeryung Jang, Hyungwon Choi, Yung Yi and Jinwoo Shin
IEEE International Symposium on Information Theory (ISIT), 2017

[C30] On the Delay Scaling Laws of Cache Networks (arXiv): Boram Jin, Daewoo Kim, Se-Young Yun, Jinwoo Shin, Seongik Hong, Byoung-Joon B.J. Lee and Yung Yi
International Conference on Future Internet Technologies (CFI), 2017

[C29] Rumor Source Detection under Querying with Untruthful Answers (arXiv): Jaeyoung Choi, Sangwoo Moon, Jiin Woo, Kyunghwan Son, Jinwoo Shin and Yung Yi
IEEE International Conference on Computer Communications (INFOCOM), 2017

[C28] Incentivizing strategic users for social diffusion: Quantity or quality?: Jungseul Ok, Jinwoo Shin and Yung Yi
IEEE International Conference on Computer Communications (INFOCOM), 2017

[C27] Rapid Mixing Swendsen-Wang Sampler for Stochastic Partitioned Attractive Models (arXiv, poster): Sejun Park, Yunhun Jang, Andreas Galanis, Jinwoo Shin, Daniel Stefankovic and Eric Vigoda
International Conference on Artificial Intelligence and Statistics (AISTATS), 2017

[J18] Convergence and Correctness of Max-Product Belief Propagation for Linear Programming (arXiv): Sejun Park and Jinwoo Shin
SIAM Journal on Discrete Mathematics (SIDMA), vol. 31, no. 3, pp. 2228–2246, 2017

[J17] Approximating Spectral Sums of Large-Scale Matrices using Stochastic Chebyshev Approximations (arXiv): Insu Han, Dmitry Malioutov, Haim Avron and Jinwoo Shin
SIAM Journal on Scientific Computing (SISC), vol. 39, no. 4, pp. A1558–A1585, 2017

[J16] Scheduling Using Interactive Optimization Oracles for Constrained Queueing Networks (arXiv): Tonghoon Suk and Jinwoo Shin
Mathematics of Operations Research (MOR), vol. 42, no. 3, pp. 723–744, 2017 (based on the preliminary version [C17])

[W3] Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples (arXiv): Kimin Lee, Honglak Lee, Kibok Lee and Jinwoo Shin
NeurIPS Workshop on Bayesian Deep Learning, 2017 (the newer version [C37] available at ICLR 2018)

2016

[C26] Synthesis of MCMC and Belief Propagation (arXiv, code): Sung-Soo Ahn, Michael Chertkov and Jinwoo Shin
Conference on Neural Information Processing Systems (NIPS), 2016
Full Oral Presentation (46/2500=1.8%)

[C25] Distributed Coordination Maximization over Networks: A Stochastic Approximation Approach: Hyeryung Jang, Se-Young Yun, Jinwoo Shin and Yung Yi
ACM International Symposium on Mobile Ad Hoc Networking and Computing (MOBIHOC), 2016 (the newer version [J19] available at IEEE Transactions on Wireless Communications)

[C24] Optimality of Belief Propagation for Crowdsourced Classification (arXiv, code): Jungseul Ok, Sewoong Oh, Jinwoo Shin and Yung Yi
International Conference on Machine Learning (ICML), 2016 (the newer version [J21] available at IEEE Transactions on Information Theory)

[C23] Just-in-time WLANs: On-demand interference-managed WLAN infrastructures: Kimin Lee, Yeonkeun Kim, Seokhyun Kim, Jinwoo Shin, Seungwon Shin and Song Chong
IEEE International Conference on Computer Communications (INFOCOM), 2016

[J15] On Maximizing Diffusion Speed Over Social Networks With Strategic Users: Jungseul Ok, Youngmi Jin, Jinwoo Shin and Yung Yi
IEEE/ACM Transactions on Networking (TON), vol. 24, no. 6, pp. 3798–3811, 2016 (based on the preliminary version [C16])

[J14] Delay Optimal CSMA With Linear Virtual Channels Under a General Topology: Donggyu Yun, Dongmyung Lee, Se-Young Yun, Jinwoo Shin and Yung Yi
IEEE/ACM Transactions on Networking (TON), vol. 24, no. 5, pp. 2847–2857, 2016 (based on the preliminary version [C15])

[J13] Distributed Medium Access Over Time-Varying Channels (arXiv): Se-Young Yun, Jinwoo Shin and Yung Yi
IEEE/ACM Transactions on Networking (TON), vol. 24, no. 5, pp. 3000–3013, 2016 (based on the preliminary version [C8])

[J12] Breaking the Trapping Sets in LDPC Codes: Check Node Removal and Collaborative Decoding: Soonyoung Kang, Jaekyun Moon, Jeongseok Ha and Jinwoo Shin
IEEE Transactions on Communications (TCOM), vol. 64, no. 1, pp. 15–26, 2016

[W2] Estimating the rumor source with anti-rumor in social networks: Jaeyoung Choi, Sangwoo Moon, Jinwoo Shin and Yung Yi
ICNP Workshop on Machine Learning in Computer Networks, 2016

2015

[C22] Minimum Weight Perfect Matching via Blossom Belief Propagation (arXiv): Sung-Soo Ahn, Sejun Park, Michael Chertkov and Jinwoo Shin
Conference on Neural Information Processing Systems (NIPS), 2015
Spotlight Presentation (82/1838=4.5%)

[C21] Practical message-passing framework for large-scale combinatorial optimization: Inho Cho, Soya Park, Sejun Park, Dongsu Han and Jinwoo Shin
IEEE International Conference on Big Data (IEEE BigData), 2015

[C20] Large-scale log-determinant computation through stochastic Chebyshev expansions (arXiv, code, talk): Insu Han, Dmitry Malioutov and Jinwoo Shin
International Conference on Machine Learning (ICML), 2015

[C19] Max-Product Belief Propagation for Linear Programming: Applications to Combinatorial Optimization (arXiv): Sejun Park and Jinwoo Shin
Conference on Uncertainty in Artificial Intelligence (UAI), 2015

[C18] On the progressive spread over strategic diffusion: Asymptotic and computation: Jungseul Ok, Jinwoo Shin and Yung Yi
IEEE International Conference on Computer Communications (INFOCOM), 2015

[J11] Impacts of Selfish Behaviors on the Scalability of Hybrid Client–Server and Peer-to-Peer Caching Systems: Youngmi Jin, George Kesidis, Jinwoo Shin, Fatih Kocak and Yung Yi
IEEE/ACM Transactions on Networking (TON), vol. 23, no. 6, pp. 1818–1831, 2015 (based on the preliminary version [C10])

[J10] CSMA Using the Bethe Approximation: Scheduling and Utility Maximization (arXiv): Se-Young Yun, Jinwoo Shin and Yung Yi
IEEE Transactions on Information Theory (TIT), vol. 61, no. 9, pp. 4776–4787, 2015 (based on the preliminary version [C12])

2014

[C17] Scheduling Using Interactive Oracles: Connection between Iterative Optimization and Low-Complexity Scheduling (arXiv): Jinwoo Shin and Tonghoon Suk
ACM International Conference on Measurement and Modeling of Computer Systems (SIGMETRICS), 2014 (short paper)

[C16] On Maximizing Diffusion Speed in Social Networks: Impact of Random Seeding and Clustering: Jungseul Ok, Youngmi Jin, Jinwoo Shin and Yung Yi
ACM International Conference on Measurement and Modeling of Computer Systems (SIGMETRICS), 2014 (the newer version [J15] available at IEEE/ACM Transactions on Networking)

[C15] Provable per-link delay-optimal CSMA for general wireless network topology: Dongmyung Lee, Donggyu Yun, Jinwoo Shin, Yung Yi and Se-Young Yun
IEEE International Conference on Computer Communications (INFOCOM), 2014 (the newer version [J14] available at IEEE/ACM Transactions on Networking)

[C14] Distributed learning for utility maximization over CSMA-based wireless multihop networks: Hyeryung Jang, Se-Young Yun, Jinwoo Shin and Yung Yi
IEEE International Conference on Computer Communications (INFOCOM), 2014

[J9] Near-Optimality in Covering Games by Exposing Global Information (arXiv): Maria-Florina Balcan, Sara Krehbiel, Georgios Piliouras and Jinwoo Shin
ACM Transactions on Economics and Computation (TEAC), vol. 2, no. 3, pp. 13:1–13:22, 2014 (based on the preliminary version [C7])

[J8] The Complexity of Approximating a Bethe Equilibrium (arXiv): Jinwoo Shin
IEEE Transactions on Information Theory (TIT), vol. 60, no. 7, pp. 3959–3969, 2014 (based on the preliminary version [C6])

[I2] Influence Maximization Over Strategic Diffusion in Social Networks: Jungseul Ok, Youngmi Jin, Jaeyoung Choi, Jinwoo Shin and Yung Yi
Annual Conference in Information Sciences and Systems (CISS), 2014

2013

[C13] A Graphical Transformation for Belief Propagation: Maximum Weight Matchings and Odd-Sized Cycles (arXiv): Jinwoo Shin, Andrew E Gelfand and Misha Chertkov
Conference on Neural Information Processing Systems (NIPS), 2013 (the newer version [J20] available at IEEE Transactions on Information Theory)

[C12] CSMA using the Bethe approximation for utility maximization (arXiv): Se-Young Yun, Jinwoo Shin and Yung Yi
IEEE International Symposium on Information Theory (ISIT), 2013 (the newer version [J10] available at IEEE Transactions on Information Theory)

[C11] Belief Propagation for Linear Programming (arXiv): Andrew E. Gelfand, Jinwoo Shin and Michael Chertkov
IEEE International Symposium on Information Theory (ISIT), 2013

[C10] Hybrid Client-Server and Peer-to-Peer Caching Systems with Selfish Peers: Youngmi Jin, Yung Yi, George Kesidis, Fatih Kocak and Jinwoo Shin
IEEE International Conference on Computer Communications (INFOCOM), 2013 (the newer version [J11] available at IEEE/ACM Transactions on Networking)

[C9] Loop Calculus and Bootstrap-Belief Propagation for Perfect Matchings on Arbitrary Graphs (arXiv): Michael Chertkov, Andrew Gelfand and Jinwoo Shin
ELC International Meeting on Inference, Computation, and Spin Glasses (ICSG), 2013

[C8] CSMA over Time-varying Channels: Optimality, Uniqueness and Limited Backoff Rate (arXiv): Se-Young Yun, Jinwoo Shin and Yung Yi
ACM International Symposium on Mobile Ad Hoc Networking and Computing (MOBIHOC), 2013 (the newer version [J13] available at IEEE/ACM Transactions on Networking)
Best Paper Award

[J7] From Local to Global Stability in Stochastic Processing Networks Through Quadratic Lyapunov Functions (arXiv): Antonius B. Dieker and Jinwoo Shin
Mathematics of Operations Research (MOR), vol. 38, no. 4, pp. 638–664, 2013

[J6] Improved Mixing Condition on the Grid for Counting and Sampling Independent Sets (arXiv): Ricardo Restrepo, Jinwoo Shin, Prasad Tetali, Eric Vigoda and Linji Yang
Probability Theory and Related Fields (PTRF), vol. 156, no. 1, pp. 75–99, 2013 (based on the preliminary version [C4])

[W1] On the Impact of Global Information on Diffusion of Innovations over Social Networks: Youngmi Jin, Jungseul Ok, Yung Yi and Jinwoo Shin
IEEE International Workshop on Network Science for Communication Networks, 2013

2009 – 2012

[C7] Minimally invasive mechanism design: Distributed covering with carefully chosen advice (arXiv): Maria-Florina Balcan, Sara Krehbiel, Georgios Piliouras and Jinwoo Shin
IEEE Conference on Decision and Control (CDC), 2012 (the newer version [J9] available at ACM Transactions on Economics and Computation)

[C6] Complexity of Bethe Approximation (arXiv): Jinwoo Shin
International Conference on Artificial Intelligence and Statistics (AISTATS), 2012 (the newer version [J8] available at IEEE Transactions on Information Theory)

[C5] Medium Access Using Queues (arXiv): Devavrat Shah, Jinwoo Shin and Prasad Tetali
IEEE Symposium on Foundations of Computer Science (FOCS), 2011

[C4] Improved Mixing Condition on the Grid for Counting and Sampling Independent Sets (arXiv): Ricardo Restrepo, Jinwoo Shin, Prasad Tetali, Eric Vigoda and Linji Yang
IEEE Symposium on Foundations of Computer Science (FOCS), 2011 (the newer version [J6] available at Probability Theory and Related Fields)

[C3] Dynamics in Congestion Games: Devavrat Shah and Jinwoo Shin
ACM International Conference on Measurement and Modeling of Computer Systems (SIGMETRICS), 2010

[C2] Delay optimal queue-based CSMA: Devavrat Shah and Jinwoo Shin
ACM International Conference on Measurement and Modeling of Computer Systems (SIGMETRICS), 2010 (short paper)

[C1] Network Adiabatic Theorem: An Efficient Randomized Protocol for Contention Resolution: Shreevatsa Rajagopalan, Devavrat Shah and Jinwoo Shin
ACM International Conference on Measurement and Modeling of Computer Systems (SIGMETRICS), 2009
Kenneth C. Sevcik (Best Student Paper) Award
ACM SIGMETRICS Test of Time Award

[J5] DRAM Scheduling Policy for GPGPU Architectures Based on a Potential Function: Nagesh B. Lakshminarayana, Jaekyu Lee, Hyesoon Kim and Jinwoo Shin
IEEE Computer Architecture Letters (CAL), vol. 11, no. 2, pp. 33–36, 2012

[J4] Randomized Scheduling Algorithm for Queueing Networks (arXiv): Devavrat Shah and Jinwoo Shin
The Annals of Applied Probability (AAP), vol. 22, no. 1, pp. 128–171, 2012
Best Publication Award from INFORMS Applied Probability Society

[J3] Counting Independent Sets Using the Bethe Approximation: Venkat Chandrasekaran, Misha Chertkov, David Gamarnik, Devavrat Shah and Jinwoo Shin
SIAM Journal on Discrete Mathematics (SIDMA), vol. 25, no. 2, pp. 1012–1034, 2011

[J2] Distributed Random Access Algorithm: Scheduling and Congestion Control (arXiv): Libin Jiang, Devavrat Shah, Jinwoo Shin and Jean Walrand
IEEE Transactions on Information Theory (TIT), vol. 56, no. 12, pp. 6183–6207, 2010

[J1] Distributed Averaging Via Lifted Markov Chains (arXiv): Kyomin Jung, Devavrat Shah and Jinwoo Shin
IEEE Transactions on Information Theory (TIT), vol. 56, no. 1, pp. 634–647, 2010

[I1] Optimal CSMA: A survey: Se-Young Yun, Yung Yi, Jinwoo Shin and Do Young Eun
IEEE International Conference on Communication Systems (ICCS), 2012