Publications

[ML] Machine Learning, [FL] Federated Learning, [MM] Multimodal, [RL] Reinforcement Learning, [CV] Computer Vision, [AIX] AI+Application

Preprints

[ML] Weebum Yoo and Sung Whan Yoon, "A Flat Minima Perspective on Understanding Augmentations and Model Robustness," [arXiv]

[ML] SeungBum Ha, Serom Park, and Sung Whan Yoon, "Unlearning's Blind Spots: Over-Unlearning and Prototypical Relearning Attack," [arXiv]

Journals & Conferences

2025

[J-NER'25] Ga-Young Choi, Jeong-Gweon Seo, Kyoung Tae Kim, Won Kee Chang, Sung Whan Yoon, Nam-Jong Paik, Won-Seok Kim, and Han-Jeong Hwang, "Clinical Feasibility of A Motor Hotspot Localization Based on Electroencephalography Using Convolutional Neural Network in Patients with Stroke," accepted to Journal of NeuroEngineering and Rehabilitation (IF: 5.2, JCR'24 Top 4.4%) [AIX]

[PRL'25] SeungBum Ha*, Taehwan Lee*, Jiyoun Lim, and Sung Whan Yoon, "Benchmarking Federated Learning for Semantic Datasets: Federated Scene Graph Generation," Pattern Recognition Letters, vol. 197, Nov. 2025 [paper][github] *Equal contribution [FL] [CV]

[ICCV'25] Taehwan Lee*, Kyeongkook Seo*, Jaejun Yoo, and Sung Whan Yoon, "Understanding Flatness in Generative Models: Its Role and Benefits," accepted to International Conference on Computer Vision (ICCV), Honolulu, Hawaii, U.S., 2025 (acceptance rate: 24.0%) [paper][github] *Equal contribution [ML] [CV]

[JSAC'25] Jeunghun Park and Sung Whan Yoon, "Transmit What You Need: Task-Adaptive Semantic Communications for Visual Information," accepted to IEEE Journal on Selected Areas in Communications (JSAC) [arXiv][github] (IF: 17.2, JCR'24 Top 1.7%) [AIX]

[ICLR'25] Hyun Kyu Lee and Sung Whan Yoon, "Flat Reward in Policy Parameter Space Implies Robust Reinforcement Learning," Proceedings of the 13th International Conference on Learning Representations (ICLR), Singapore, 2025 (acceptance rate: 31.24%) [paper][slides][video][github] (Oral, Top 1.8%) [ML] [RL]

[ICLR'25] Jae-Jun Lee and Sung Whan Yoon, "Can One Modality Model Synergize Training of Other Modality Models?" Proceedings of the 13th International Conference on Learning Representations (ICLR), Singapore, 2025 (acceptance rate: 31.24%) [paper][slides][video][github] [ML] [MM]

2024

[ICML'24] Taehwan Lee and Sung Whan Yoon, "Rethinking the Flat Minima Searching in Federated Learning," Proceedings of the 41st International Conference on Machine Learning (ICML), Vienna, Austria, 2024 (acceptance rate: 27.5%) [paper][slides][video][github] (Qualcomm Innovation Fellowship Korea Finalist 2024) [FL]

[WoWMoM'24] Daulet Kurmantayev, Dohyun Kwun, Hyoil Kim, and Sung Whan Yoon, "RiSi: Spectro-temporal RAN-agnostic Modulation Identification for OFDMA Signals," Proceedings of the 25th IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM), Perth, Australia, 2024 (acceptance rate: 34.2%) [paper][slides] [AIX]

[AISTATS'24] Jae-Jun Lee and Sung Whan Yoon, "XB-MAML: Learning Expandable Basis Parameters for Effective Meta-Learning with Wide Task Coverage," Proceedings of the 27th International Conference on Artificial Intelligence and Statistics (AISTATS), Valencia, Spain, 2024 (acceptance rate: 27.5%) [paper][poster][github] [ML]

[WACV'24] Jin Hyuk Lim*, SeungBum Ha*, and Sung Whan Yoon, "MetaVers: Meta-Learned Versatile Representations for Personalized Federated Learning," Proceedings of IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Hawaii, U.S., 2024. *Equal contribution [paper][supp][slides][video][poster][github] [FL]

[WACV'24] Solang Kim, Yuho Jeong, Joon Sung Park, and Sung Whan Yoon, "MICS: Midpoint Interpolation to Learn Compact and Separated Representations for Few-Shot Class-Incremental Learning," Proceedings of IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Hawaii, U.S., 2024 [paper][supp][slides][video][poster][github] [ML] [CV]

2023

[PHYCOM'23] Hong-Jae Lee, Dohyn Kwon, Sung Whan Yoon, and Jin-Ho Chung "Analysis and Optimization for Non-Orthogonal Pilot Sequence Sets in Massive MIMO Systems," Physical Communication, vol. 60, 102169, Oct. 2023 [paper] [AIX]

[AAAI'23] Sang-Yeong Jo and Sung Whan Yoon, "POEM: Polarization of Embeddings for Domain-Invariant Representations," Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI), 37(7): 8150-8158, Washington D.C., U.S., 2023 (acceptance rate: 19.6%) [paper][supp][slides][github] (Oral) [ML] [CV]

[AAAI'23 Workshop] Jin Hyuk Lim, and Sung Whan Yoon, "MetaVerSe: Federated Meta-Learning for Versatile and Secure Representations with Dynamic Margins in Embedding Space," Workshop on Privacy-Preserving AI Workshop in AAAI 2023, Washington D.C.

Before 2023

[ICML'20] Sung Whan Yoon*, Do-Yeon Kim*, Jun Seo, and Jaekyun Moon "XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learning," Proceedings of the 37th International Conference on Machine Learning (ICML), Vienna, Austria (virtual), 2020. (acceptance rate: 22.6%), *Equal contribution. [paper][supp][slides][github] [ML]

[T-IT'19] Beongjun Choi, Jy-yong Sohn, Sung Whan Yoon, and Jaekyun Moon "Secure clustered distributed storage against eavesdropping," IEEE Transactions on Information Theory, vol. 65, no. 11, pp. 7646-7668, Nov. 2019 [paper].

[ICML'19] Sung Whan Yoon, Jun Seo, and Jaekyun Moon "TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning," Proceedings of the 36th International Conference on Machine Learning (ICML), Long Beach, CA, U.S., 2019 (acceptance rate: 21.8%) [paper][supp][slides][github].

[T-IT'19] Jy-yong Sohn, Beongjun Choi, Sung Whan Yoon, and Jaekyun Moon, “Capacity of Clustered Distributed Storage,” IEEE Transactions on Information Theory, vol. 65, no. 1, pp. 81-107, Jan. 2019 [paper].

[NeurIPS'18 Workshop] Sung Whan Yoon, Seo Jun, and Jaekyun Moon "Meta-learner with linear nulling," 2018 Neural Information Processing Systems (NeurIPS, NIPS) Workshop on Meta-Learning, Montreal, Canada, Dec. 2018 [paper]

[T-WC'17] Jy-yong Sohn, Sung Whan Yoon, and Jaekyun Moon, "On Reusing pilots among interfering cells in massive MIMO," IEEE Transactions on Wireless Communications, vol. 16, no. 12, pp. 8092-8104, Dec. 2017 [paper].

[JSAC'17] Jy-yong Sohn, Sung Whan Yoon, and Jaekyun Moon, "Pilot reuse strategy maximizing the weighted-sum-rate in massive MIMO system," IEEE Journal on Selected Areas in Communications (JSAC), vol. 35, no. 8, pp. 1728-1740, Aug. 2017 [paper].

[ICC'17] Beongjun Choi, Jy-yong Sohn, Sung Whan Yoon, and Jaekyun Moon, "Secure clustered distributed storage against eavesdroppers," IEEE International Conference on Communications (ICC), Paris, France, May 2017 [paper].

[ICC'17] Jy-yong Sohn, Beongjun Choi, Sung Whan Yoon, and Jaekyun Moon, "Capacity of clustered distributed storage," IEEE International Conference on Communications (ICC), Paris, France, May 2017 (won the Best Paper Award for Communication Theory Symposium) [paper]

[ICC'17 Workshop] Sung Whan Yoon and Jaekyun Moon, "Low-complexity concatenated polar codes with excellent scaling behavior," IEEE International Conference on Communications (ICC) Workshop, Paris, France, May 2017 [paper].

[ICC'17 Workshop] Jy-yong Sohn, Sung Whan Yoon, and Jaekyun Moon, "When pilots should not be reused across interfering cells in massive MIMO," IEEE International Conference on Communications (ICC) Workshop, London, UK, June 2015 [paper].

[T-COM'15] Sung Whan Yoon and Jaekyun Moon, "Two-dimensional error-pattern-correcting codes," IEEE Transactions on Communications, vol. 63, no. 8, pp. 2725-2740, Aug. 2015 [paper].

[GLOBECOM'12] Sung Whan Yoon and Jaekyun Moon, "Two-dimensional cyclic codes correcting known error patterns," IEEE Global Communications Conference (GLOBECOM), Anaheim, CA, USA, Dec. 2012 [paper].