collaborators

16 papers

cs.LG2026

Aggregation Alignment for Federated Learning with Mixture-of-Experts under Data Heterogeneity

Zihan Fang, Qianru Wang, Haonan An +4

Large language models (LLMs) increasingly adopt Mixture-of-Experts (MoE) architectures to scale model capacity while reducing computation. Fine-tuning these MoE-based LLMs often re…

cs.NI2026

MLFCIL: A Multi-Level Forgetting Mitigation Framework for Federated Class-Incremental Learning in LEO Satellites

Heng Zhang, Xiaohong Deng, Sijing Duan +4

Low-Earth-orbit (LEO) satellite constellations are increasingly performing on-board computing. However, the continuous emergence of new classes under strict memory and communicatio…

cs.CV2026

Task-Oriented Semantic Compression for Localization at the Network Edge

Zhengru Fang, Senkang Hu, Yu Guo +2

Achieving precise visual localization in GPS-limited urban environments poses significant challenges for resource-constrained mobile platforms, particularly under strict bandwidth,…

cs.CV2026

CP-uniGuard: A Unified, Probability-Agnostic, and Adaptive Framework for Malicious Agent Detection and Defense in Multi-Agent Embodied Perception Systems

Senkang Hu, Yihang Tao, Guowen Xu +5

Collaborative Perception (CP) has been shown to be a promising technique for multi-agent autonomous driving and multi-agent robotic systems, where multiple agents share their perce…

cs.LG2026

HFedMoE: Resource-aware Heterogeneous Federated Learning with Mixture-of-Experts

Zihan Fang, Zheng Lin, Senkang Hu +5

While federated learning (FL) enables fine-tuning of large language models (LLMs) without compromising data privacy, the substantial size of an LLM renders on-device training impra…

eess.SY2025

Minimizing Maximum Latency of Task Offloading for Multi-UAV-assisted Maritime Search and Rescue

Shuang Qi, Bin Lin, Yiqin Deng +2

Unmanned Aerial Vehicles (UAVs) play a crucial role in Maritime Search and Rescue (MSAR), contributing to the improvement of rescue efficiency and reduction of casualties. Typicall…