3 papers
cs.CR2025
BadMoE: Backdooring Mixture-of-Experts LLMs via Optimizing Routing Triggers and Infecting Dormant Experts
Qingyue Wang, Qi Pang, Xixun Lin +2
Mixture-of-Experts (MoE) have emerged as a powerful architecture for large language models (LLMs), enabling efficient scaling of model capacity while maintaining manageable computa…
cs.CV2024
Metadata-Driven Federated Learning of Connectional Brain Templates in Non-IID Multi-Domain Scenarios
Geng Chen, Qingyue Wang, Islem Rekik
A connectional brain template (CBT) is a holistic representation of a population of multi-view brain connectivity graphs, encoding shared patterns and normalizing typical variation…
cs.CV2024
DMAT: A Dynamic Mask-Aware Transformer for Human De-occlusion
Guoqiang Liang, Jiahao Hu, Qingyue Wang +1
Human de-occlusion, which aims to infer the appearance of invisible human parts from an occluded image, has great value in many human-related tasks, such as person re-id, and inten…