7 papers
Attributing HOW, Not Just WHICH: Counterfactual Response Trajectories for Diffusion Models
Haoqian Zhang, Ziyuan Yang, Zerui Shao +1
Diffusion models have achieved remarkable success in image generation, yet tracing their outputs to individual training examples remains challenging. Existing attribution methods o…
EvoOMG: An Evolution-Oriented Multi-Agent Guidance Framework for Heterogeneous Legacy-and-MLO Wi-Fi Networks
Junjie Wu, Lingjian Zhou, Zerui Shao +4
The gradual deployment of Wi-Fi 7/8 multi-link operation (MLO) will lead to long-term coexistence between legacy non-MLO stations (STAs) and MLO-capable STAs in WLANs. This mixed d…
PolyJailbreak: Cross-Modal Jailbreaking Attacks on Black-Box Multimodal LLMs
Xinkai Wang, Beibei Li, Zerui Shao +3
Multimodal large language models (MLLMs) have become integral to a wide range of real-world applications by jointly reasoning over text and visual inputs. However, despite recent a…
FedRIR: Rethinking Information Representation in Federated Learning
Yongqiang Huang, Zerui Shao, Ziyuan Yang +2
Mobile and Web-of-Things (WoT) devices at the network edge generate vast amounts of data for machine learning applications, yet privacy concerns hinder centralized model training.…
Energizing Federated Learning via Filter-Aware Attention
Ziyuan Yang, Zerui Shao, Huijie Huangfu +5
Federated learning (FL) is a promising distributed paradigm, eliminating the need for data sharing but facing challenges from data heterogeneity. Personalized parameter generation…
FedCliP: Federated Learning with Client Pruning
Beibei Li, Zerui Shao, Ao Liu +1
The prevalent communication efficient federated learning (FL) frameworks usually take advantages of model gradient compression or model distillation. However, the unbalanced local…
Hyper RPCA: Joint Maximum Correntropy Criterion and Laplacian Scale Mixture Modeling On-the-Fly for Moving Object Detection
Zerui Shao, Yifei Pu, Jiliu Zhou +2
Moving object detection is critical for automated video analysis in many vision-related tasks, such as surveillance tracking, video compression coding, etc. Robust Principal Compon…