Publications
ZO-Offloading: Fine-Tuning LLMs with 100 Billion Parameters on a Single GPU [pdf]
Liangyu Wang, Jie Ren, Hang Xu, Junxiao Wang, David E. Keyes, Di Wang
The NeurIPS Workshop on Adaptive Foundation Models (AFM) 2024
FlashDP: Memory-Efficient and High-Throughput DP-SGD Training for Large Language Models [pdf]
Liangyu Wang, Junxiao Wang, Jie Ren, Zihang Xiang, David E. Keyes, Di Wang
The NeurIPS Workshop on Adaptive Foundation Models (AFM) 2024
Towards Safe Concept Transfer of Multi-Modal Diffusion via Causal Representation Editing [pdf]
Peiran Dong, Bingjie Wang, Song Guo, Junxiao Wang, Jie Zhang, Zicong Hong
The Annual Conference on Neural Information Processing Systems (NeurIPS) 2024
Explore and Cure: Unveiling Sample Effectiveness with Context-Aware Federated Prompt Tuning [pdf]
Tao Guo, Song Guo, Junxiao Wang
IEEE Transactions on Mobile Computing (TMC) 2024
Autonomous Workflow for Multimodal Fine-Grained Training Assistants Towards Mixed Reality [pdf]
Jiahuan Pei, Irene Viola, Haochen Huang, Junxiao Wang, Moonisa Ahsan, Fanghua Ye, Jiang Yiming, Yao Sai, Di Wang, Zhumin Chen, Pengjie Ren, Pablo Cesar
Findings of the Association for Computational Linguistics (ACL) 2024
Exploring Amplified Heterogeneity Arising from Heavy-Tailed Distributions in Federated Learning [pdf]
Yizhi Zhou, Junxiao Wang†, Xiangyu Kong, Shan Wu, Xin Xie, Heng Qi
IEEE Transactions on Mobile Computing (TMC) 2024
Towards Light Adaptation of Large Language Models For Personal Hardware [pdf]
Liangyu Wang, Junxiao Wang, Di Wang
ACM MobiSys Workshop on Edge and Mobile Foundation Models (EdgeFM) 2024
Rethinking Personalized Client Collaboration in Federated Learning [pdf]
Leijie Wu, Song Guo, Yaohong Ding, Junxiao Wang, Wenchao Xu, Yufeng Zhan, Anne-Marie Kermarrec
IEEE Transactions on Mobile Computing (TMC) 2024
Faithful Vision-Language Interpretation via Concept Bottleneck Models [pdf]
Songning Lai, Lijie Hu, Junxiao Wang, Laure Berti-Equille, Di Wang
International Conference on Learning Representations (ICLR) 2024
Towards Test-Time Refusals via Concept Negation [pdf]
Peiran Dong, Song Guo, Junxiao Wang†, Bingjie Wang, Jiewei Zhang, Ziming Liu
The Annual Conference on Neural Information Processing Systems (NeurIPS) 2023
PromptFL: Let Federated Participants Cooperatively Learn Prompts Instead of Models — Federated Learning in Age of Foundation Model [pdf]
Tao Guo, Song Guo, Junxiao Wang†, Xueyang Tang, Wenchao Xu
IEEE Transactions on Mobile Computing (TMC) 2023
Investigating Trojan Attacks on Pre-trained Language Model-powered Database Middleware [pdf]
Peiran Dong, Song Guo, Junxiao Wang†
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2023
PMR: Prototypical Modal Rebalance for Multimodal Learning [pdf]
Yunfeng Fan, Wenchao Xu, Haozhao Wang, Junxiao Wang, Song Guo
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023
pFedPrompt: Learning Personalized Prompt for Vision-Language Models in Federated Learning [pdf]
Tao Guo, Song Guo, Junxiao Wang†
The ACM Web Conference (WWW) 2023
Federated Unlearning: Guarantee the Right of Clients to Forget [pdf]
Leijie Wu, Song Guo, Junxiao Wang†, Zicong Hong, Jie Zhang, Yaohong Ding
IEEE Network 2022
Efficient Integrity Authentication Scheme for Large-scale RFID Systems [pdf]
Xin Xie, Xiulong Liu, Junxiao Wang, Song Guo, Heng Qi, Keqiu Li
IEEE Transactions on Mobile Computing (TMC) 2022
A Survey on Gradient Inversion: Attacks, Defenses and Future Directions [pdf]
Rui Zhang, Song Guo, Junxiao Wang†, Xin Xie, Dacheng Tao
International Joint Conference on Artificial Intelligence (IJCAI) 2022
Federated Unlearning via Class-Discriminative Pruning [pdf]
Junxiao Wang, Song Guo, Xin Xie, Heng Qi
The ACM Web Conference (WWW) 2022
Protect Privacy from Gradient Leakage Attack in Federated Learning [pdf]
Junxiao Wang, Song Guo, Xin Xie, Heng Qi
IEEE International Conference on Computer Communications (INFOCOM) 2022
Click-UP: Toward the Software Upgrade of Click-Based Modular Network Function [pdf]
Junxiao Wang, Heng Qi, Keqiu Li, Steve Uhlig
IEEE Systems Journal (ISJ) 2020
CLICK-UP: Towards Software Upgrades of Click-driven Stateful Network Elements [pdf]
Junxiao Wang, Yuchen Huang, Heng Qi, Keqiu Li, Steve Uhlig
ACM SIGCOMM Conference 2018 (Demo)
On Knowledge Editing in Federated Learning: Perspectives, Challenges, and Future Directions [pdf]
Leijie Wu, Song Guo, Junxiao Wang, Zicong Hong, Jie Zhang, Jingren Zhou
arXiv:2306.01431, 2023
DualMix: Unleashing the Potential of Data Augmentation for Online Class-Incremental Learning [pdf]
Yunfeng Fan, Wenchao Xu, Haozhao Wang, Jiaqi Zhu, Junxiao Wang, Song Guo
arXiv:2303.07864, 2023
Demystify Self-Attention in Vision Transformers from a Semantic Perspective: Analysis and Application [pdf]
Leijie Wu, Song Guo, Yaohong Ding, Junxiao Wang, Wenchao Xu, Richard Yida Xu, Jie Zhang
arXiv:2211.08543, 2022
FedTune: A Deep Dive into Efficient Federated Fine-Tuning with Pre-trained Transformers [pdf]
Jinyu Chen, Wenchao Xu, Song Guo, Junxiao Wang, Jie Zhang, Haozhao Wang
arXiv:2211.08025, 2022
Vertical Machine Unlearning: Selectively Removing Sensitive Information From Latent Feature Space [pdf]
Tao Guo, Song Guo, Jiewei Zhang, Wenchao Xu, Junxiao Wang
arXiv:2202.13295, 2022