[48] Rethinking LLM Fine-Tuning via Weight Space Reparameterization: Preserving Safety during Downstream Adaptation
Min-Seong Kim*, Jongbok Won*, Jeesup Park, Yonghee Choi, and Dong-Jun Han
NeurIPS 2026 [Spotlight, 5.1% of accepted papers] (Conference on Neural Information Processing Systems)
[47] MT-CC: Multi-Group Temperature Scaling for Asymmetric Calibration Behavior in Class-Incremental Learning
Sungjun Yun, Yonghee Choi, and Dong-Jun Han
NeurIPS 2026 [Spotlight, 5.1% of accepted papers] (Conference on Neural Information Processing Systems)
[46] Disentangled Sparse Representations for Concept-Separated Diffusion Unlearning [paper]
Hyeonjin Kim*, Hangyeol Jung*, Heechan Yun, Sungjun Yun, and Dong-Jun Han
NeurIPS 2026 (Conference on Neural Information Processing Systems)
[45] Iterative Critique-and-Routing Controller for Multi-Agent Systems with Heterogeneous LLMs [paper]
Wenzhi Fang, Liangqi Yuan, Guangchen Lan, Dong-Jun Han, and Christopher G. Brinton
NeurIPS 2026 (Conference on Neural Information Processing Systems)
[44] MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge [paper]
Guangchen Lan, Sipeng Zhang, Tianle Wang, Yuwei Zhang, Xinpeng Wei, Daoan Zhang, Xiaoman Pan, Hongming Zhang, Dong-Jun Han, Christopher G. Brinton
NeurIPS 2026 (Conference on Neural Information Processing Systems)
[43] Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training [paper]
Wenzhi Fang, Dong-Jun Han, Liangqi Yuan, Evan Chen, and Christopher G. Brinton
ICML 2026 (International Conference on Machine Learning)
[42] Federated Sketching LoRA: A Flexible Framework for Heterogeneous Collaborative Fine-Tuning of LLMs [paper]
Wenzhi Fang, Dong-Jun Han, Liangqi Yuan, Seyyedali Hosseinalipour, and Christopher G. Brinton
ICML 2026 (International Conference on Machine Learning)
[41] Device-Cloud Collaborative LLM Inference with Multi-Modal, Multi-Task, Multi-Turn Conversations [paper]
Liangqi Yuan, Dong-Jun Han, Shiqiang Wang, and Christopher G. Brinton
IEEE Transactions on Networking (ToN), 2026.
[40] Identifying Robust Neural Pathways: Few-Shot Adversarial Mask Tuning for Vision-Language Models [paper]
Wonjeong Choi, Sejong Ryu, Jungmoon Lee, Dong-Jun Han*, and Jaekyun Moon
ICLR 2026 (International Conference on Learning Representations)
[39] Decentralized Domain Generalization with Style Sharing: A Formal Modeling and Convergence Analysis [paper]
Shahryar Zehtabi, Dong-Jun Han, Seyyedali Hosseinalipour, and Christopher G. Brinton
IEEE INFOCOM 2026 (IEEE International Conference on Computer Communications)
[38] ProLoG: Hybrid Prompt and LoRA Based Adaptation of Vision-Language Models for OOD Generalization [paper]
Jungwuk Park, Dong-Jun Han*, and Jaekyun Moon
AAAI 2026 [Selected for Oral Presentation] (AAAI Conference on Artificial Intelligence)
[37] Communication-Efficient Multimodal Federated Learning: Joint Modality and Client Selection [paper]
Liangqi Yuan, Dong-Jun Han, Su Wang, Devesh Upadhyay, and Christopher G. Brinton
IEEE Transactions on Mobile Computing (TMC), 2026.
[36] Efficient Split Learning with Overlapping Areas: Handling Distribution Shifts in Multi-Cell Networks [paper]
Atif Rizwan, Dong-Jun Han, Md Ferdous Pervej, Christopher G. Brinton, Andreas F. Molisch, and Minseok Choi
IEEE Transactions on Networking (ToN), 2026.
[35] Differentially-Private Multi-Tier Federated Learning: A Formal Analysis and Evaluation [paper]
Frank Po-Chen Lin, Evan Chen, Dong-Jun Han, and Christopher G. Brinton
IEEE Transactions on Networking (ToN), 2026.
[34] Local-Cloud Inference Offloading for LLMs in Multi-Modal, Multi-Task, Multi-Dialogue Settings [paper]
Liangqi Yuan, Dong-Jun Han, Shiqiang Wang, and Christopher G. Brinton
ACM MobiHoc 2025 [Best Paper Award Runner-up]
[33] LLMAP: LLM-Assisted Multi-Objective Route Planning with User Preferences [paper]
Liangqi Yuan, Dong-Jun Han, Christopher G. Brinton, and Sabine Brunswicker
EMNLP Findings 2025 (Conference on Empirical Methods in Natural Language Processing)
[32] Federated Learning over Hierarchical Wireless Networks: Training Latency Minimization via Submodel Partitioning [paper]
Wenzhi Fang, Dong-Jun Han, and Christopher G. Brinton
IEEE Transactions on Networking (ToN), Aug. 2025.
[31] Only Send What You Need: Learning to Communicate Efficiently in Federated Multilingual Machine Translation [paper]
Yun-Wei Chu, Dong-Jun Han, and Christopher G. Brinton
IEEE Transactions on Audio, Speech and Language Processing (TASLP), Apr. 2025.
[30] Decentralized Sporadic Federated Learning: A Unified Algorithmic Framework with Convergence Guarantees [paper]
Shahryar Zehtabi, Dong-Jun Han, Rohit Parasnis, Seyyedali Hosseinalipour, and Christopher G. Brinton
ICLR 2025 [Spotlight Paper] (International Conference on Learning Representations)
[29] Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence Analysis [paper]
Guangchen Lan, Dong-Jun Han, Abolfazl Hashemi, Vaneet Aggarwal, and Christopher G. Brinton
ICLR 2025 (International Conference on Learning Representations)
[28] Unlocking the Potential of Model Calibration in Federated Learning [paper]
Yun-Wei Chu, Dong-Jun Han, Seyyedali Hosseinalipour, and Christopher G. Brinton
ICLR 2025 (International Conference on Learning Representations)
[27] PRISM: Privacy-Preserving Improved Stochastic Masking for Federated Generative Models [paper]
Kyeongkook Seo, Dong-Jun Han*, and Jaejun Yoo*
ICLR 2025 (International Conference on Learning Representations)
[26] Adaptive Energy Alignment for Accelerating Test-Time Adaptation [paper]
Wonjeong Choi, Do-Yeon Kim, Jungwuk Park, Jungmoon Lee, Younghyun Park, Dong-Jun Han*, and Jaekyun Moon
ICLR 2025 (International Conference on Learning Representations)
[25] Rethinking the Starting Point: Collaborative Pre-Training for Federated Downstream Tasks [paper]
Yun-Wei Chu, Dong-Jun Han, Seyyedali Hosseinalipour, and Christopher G. Brinton
AAAI 2025 (AAAI Conference on Artificial Intelligence)
[24] Hierarchical Federated Learning with Multi-Timescale Gradient Correction [paper]
Wenzhi Fang, Dong-Jun Han, Evan Chen, Shiqiang Wang, and Christopher G. Brinton
NeurIPS 2024 (Conference on Neural Information Processing Systems)
[23] Orchestrating Federated Learning in Space-Air-Ground Integrated Networks: Adaptive Data Offloading and Seamless Handover [paper]
Dong-Jun Han, Wenzhi Fang, Seyyedali Hosseinalipour, Mung Chiang, and Christopher G. Brinton
IEEE Journal on Selected Areas in Communications (JSAC), Dec. 2024.
[22] Cooperative Federated Learning over Ground-to-Satellite Integrated Networks: Joint Local Computation and Data Offloading [paper]
Dong-Jun Han, Seyyedali Hosseinalipour, David J. Love, Mung Chiang, and Christopher G. Brinton
IEEE Journal on Selected Areas in Communications (JSAC), May 2024.
[21] Achieving Lossless Gradient Sparsification via Mapping to Alternative Space in Federated Learning [paper]
Do-Yeon Kim, Dong-Jun Han*, Jun Seo, and Jaekyun Moon
ICML 2024 (International Conference on Machine Learning)
[20] Federated Split Learning with Joint Personalization-Generalization for Inference-Stage Optimization in Wireless Edge Networks [paper]
Dong-Jun Han, Do-Yeon Kim, Minseok Choi, David Nickel, Jaekyun Moon, Mung Chiang, and Christopher G. Brinton
IEEE Transactions on Mobile Computing (TMC), June 2024.
[19] Consistency-Guided Temperature Scaling using Style and Content Information for Out-of-Domain Calibration [paper]
Wonjeong Choi, Jungwuk Park, Dong-Jun Han*, Younghyun Park, and Jaekyun Moon
AAAI 2024 (AAAI Conference on Artificial Intelligence)
[18] StableFDG: Style and Attention Based Learning for Federated Domain Generalization [paper]
Jungwuk Park*, Dong-Jun Han*, Jinho Kim, Shiqiang Wang, Christopher G. Brinton, and Jaekyun Moon
NeurIPS 2023 (Conference on Neural Information Processing Systems)
[17] NEO-KD: Knowledge-Distillation-Based Adversarial Training for Robust Multi-Exit Neural Networks [paper]
Seokil Ham, Jungwuk Park, Dong-Jun Han*, and Jaekyun Moon
NeurIPS 2023 (Conference on Neural Information Processing Systems)
[16] Test-Time Style Shifting: Handling Arbitrary Styles in Domain Generalization [paper]
Jungwuk Park*, Dong-Jun Han*, Soyeong Kim, and Jaekyun Moon
ICML 2023 (International Conference on Machine Learning)
[15] SplitGP: Achieving Both Generalization and Personalization in Federated Learning [paper]
Dong-Jun Han, Do-Yeon Kim, Minseok Choi, Christopher G. Brinton, and Jaekyun Moon
IEEE INFOCOM 2023 (IEEE International Conference on Computer Communications)
[14] Improving Low-Latency Predictions in Multi-Exit Neural Networks via Block-Dependent Losses [paper]
Dong-Jun Han*, Jungwuk Park*, Seokil Ham, Namjin Lee, and Jaekyun Moon
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), accepted, 2023.
[13] Warping the Space: Weight Space Rotation for Class-Incremental Few-Shot Learning [paper]
Do-Yeon Kim, Dong-Jun Han*, Jun Seo, and Jaekyun Moon
ICLR 2023 [Spotlight Paper] (International Conference on Learning Representations)
[12] Active Learning for Object Detection with Evidential Deep Learning and Hierarchical Uncertainty Aggregation [paper]
Younghyun Park, Wonjeong Choi, Soyeong Kim, Dong-Jun Han*, and Jaekyun Moon
ICLR 2023 (International Conference on Learning Representations)
[11] FedMes: Speeding Up Federated Learning with Multiple Edge Servers [paper]
Dong-Jun Han, Minseok Choi, Jungwuk Park, and Jaekyun Moon
IEEE Journal on Selected Areas in Communications (JSAC), Dec. 2021.
[10] Coded Wireless Distributed Computing with Packet Losses and Retransmissions [paper]
Dong-Jun Han, Jy-yong Sohn, and Jaekyun Moon
IEEE Transactions on Wireless Communications (TWC), Dec. 2021.
[9] Few-Round Learning for Federated Learning [paper]
Younghyun Park*, Dong-Jun Han*, Do-Yeon Kim, Jun Seo, and Jaekyun Moon
NeurIPS 2021 (Conference on Neural Information Processing Systems)
[8] Sageflow: Robust Federated Learning against Both Stragglers and Adversaries [paper]
Jungwuk Park*, Dong-Jun Han*, Minseok Choi, and Jaekyun Moon
NeurIPS 2021 (Conference on Neural Information Processing Systems)
[7] TiBroco: A Fast and Secure Distributed Learning Framework for Tiered Wireless Edge Networks [paper]
Dong-Jun Han, Jy-yong Sohn, and Jaekyun Moon
IEEE INFOCOM 2021 (IEEE International Conference on Computer Communications)
[6] Hierarchical Broadcast Coding: Expediting Distributed Learning at the Wireless Edge [paper]
Dong-Jun Han, Jy-yong Sohn, and Jaekyun Moon
IEEE Transactions on Wireless Communications (TWC), Apr. 2021. [Qualcomm-KAIST Innovation Award]
[5] Probabilistic Caching and Dynamic Delivery Policies for Categorized Contents and Consecutive User Demands [paper]
Minseok Choi, Andreas F. Molisch, Dong-Jun Han, Dongjae Kim, Joongheon Kim, and Jaekyun Moon
IEEE Transactions on Wireless Communications (TWC), Apr. 2021.
[4] Election Coding for Distributed Learning: Protecting SignSGD against Byzantine Attacks [paper]
Jy-yong Sohn, Dong-Jun Han, Beongjun Choi, and Jaekyun Moon
NeurIPS 2020 (Conference on Neural Information Processing Systems)
[3] Bi-Directional Cooperative NOMA Without Full CSIT [paper]
Minseok Choi, Dong-Jun Han, and Jaekyun Moon
IEEE Transactions on Wireless Communications (TWC), Nov. 2018.
[2] Combined Window-Filter Waveform Design With Transmitter-Side Channel State Information [paper]
Dong-Jun Han, Jaekyun Moon, Jy-yong Sohn, Sunyoung Jo, and Jang Hun Kim
IEEE Transactions on Vehicular Technology (TVT), Sep. 2018.
[1] Combined Subband-Subcarrier Spectral Shaping in Multi-Carrier Modulation under the Excess Frame Length Constraint [paper]
Dong-Jun Han, Jaekyun Moon, Dongjae Kim, Sae-Young Chung, and Yong H. Lee
IEEE Journal on Selected Areas in Communications (JSAC), June 2017.
[17] Multi-Tier Split Federated Learning for Multi-Level Personalization
Yeonwoo Choi, Dong-Jun Han, Christopher G. Brinton, and Minseok Choi
IEEE WCNC 2026 (IEEE Wireless Communications and Networking Conference)
[16] Differentially-Private Multi-Tier Federated Learning [paper]
Evan Chen*, Frank Po-Chen Lin*, Dong-Jun Han, and Christopher G. Brinton
IEEE ICC 2025 (IEEE International Conference on Communications)
[15] FICDF: A Federated Incremental Learning Framework for IoT Device Fingerprinting [paper]
Shengli Ding, Dong-Jun Han, Christopher G. Brinton, and Keerthi Dasala
IEEE WiOpt 2024 (International Symposium on Modeling and Optimization in Mobile, Ad hoc, and Wireless Networks)
[14] Cooperative Federated Learning over Hybrid Terrestrial and Non-Terrestrial Networks [paper]
Dong-Jun Han, Seyyedali Hosseinalipour, David J. Love, Mung Chiang, and Christopher G. Brinton
IEEE ICC 2024 (IEEE International Conference on Communications)
[13] Submodel Partitioning in Hierarchical Federated Learning: Algorithm Design and Convergence Analysis [paper]
Wenzhi Fang, Dong-Jun Han, and Christopher G. Brinton
IEEE ICC 2024 (IEEE International Conference on Communications)
[12] FedMFS: Federated Multimodal Fusion Learning with Selective Modality Communication [paper]
Liangqi Yuan, Dong-Jun Han, Vishnu Pandi Chellapandi, Stanislaw H Żak, and Christopher G. Brinton
IEEE ICC 2024 (IEEE International Conference on Communications)
[11] Only Send What You Need: Learning to Communicate Efficiently in Federated Multilingual Machine Translation
Yun-Wei Chu, Dong-Jun Han, and Christopher G. Brinton
WWW Workshop 2024 (The Web Conference Workshop on Federated Foundation Models for the Web)
[10] Distribution Aware Active Learning via Gaussian Mixtures [paper]
Younghyun Park, Dong-Jun Han, Jungwuk Park, Wonjeong Choi, Humaira Kousar, and Jaekyun Moon
ICLR Workshop 2023 (ICLR Workshop on Pitfalls of Limited Data and Computation for Trustworthy ML)
[9] Style Balancing and Test-Time Style Shifting for Domain Generalization
Jungwuk Park*, Dong-Jun Han*, Soyeong Kim, and Jaekyun Moon
ICML Workshop 2022 (ICML Workshop on Principles of Distribution Shift)
[8] Training Multi-Exit Architectures via Block-Dependent Losses for Anytime Inference [paper]
Dong-Jun Han*, Jungwuk Park*, Seokil Ham, Namjin Lee ,and Jaekyun Moon
CVPR Workshop 2022 (CVPR Workshop on Dynamic Neural Networks Meet Computer Vision)
[7] Active Object Detection with Epistemic Uncertainty and Hierarchical Information Aggregation [paper]
Younghyun Park, Soyeong Kim, Wonjeong Choi, Dong-Jun Han, and Jaekyun Moon
CVPR Workshop 2022 (CVPR Workshop on Dynamic Neural Networks Meet Computer Vision)
[6] Accelerating Federated Learning with Split Learning on Locally Generated Losses [paper]
Dong-Jun Han, Hasnain Irshad Bhatti, Jungmoon Lee, and Jaekyun Moon
ICML Workshop 2021 (ICML Workshop on Federated Learning for User Privacy and Data Confidentiality)
[5] Handling Both Stragglers and Adversaries for Robust Federated Learning [paper]
Jungwuk Park*, Dong-Jun Han*, Minseok Choi, and Jaekyun Moon
ICML Workshop 2021 (ICML Workshop on Federated Learning for User Privacy and Data Confidentiality)
[4] Cache Allocations for Consecutive Requests of Categorized Contents: Service Provider’s Perspective [paper]
Minseok Choi, Andreas Molisch, Dong-Jun Han, Joongheon Kim, and Jaekyun Moon
IEEE WCNC 2020 (IEEE Wireless Communications and Networking Conference)
[3] Coded Distributed Computing over Packet Erasure Channels [paper]
Dong-Jun Han, Jy-yong Sohn, and Jaekyun Moon
IEEE ISIT 2019 (IEEE International Symposium on Information Theory)
[2] Scalable Network-Coded PBFT Consensus Algorithm [paper]
Beongjun Choi, Jy-yong Sohn, Dong-Jun Han, and Jaekyun Moon
IEEE ISIT 2019 (IEEE International Symposium on Information Theory)
[1] Probabilistic Caching Policy for Categorized Contents and Consecutive User Demands [paper]
Minseok Choi, Dongjae Kim, Dong-Jun Han, Joongheon Kim, and Jaekyun Moon
IEEE ICC 2019 (IEEE International Conference on Communications)