41 citations · 229 across the 71 of their papers we have counts for
19 papers · 1 filter
Mobility Helps Learning: Unsupervised Model Adaptation for Object Recognition via Movement
Yanan Ma, Yihang Tao, Zhengru Fang +3
Movable agents, such as autonomous vehicles and robots, should be able to autonomously adapt their pre-trained object recognition models to new environments without human annotatio…
HO-FL: Hybrid-Order Federated Learning for Heterogeneous Edge Devices
Qiyuan Chen, Xian Wu, Yanan Ma +1
Federated learning (FL) on memory-constrained edge devices faces a dilemma: first-order (FO) optimization (i.e., backpropagation) demands substantial memory, whereas zeroth-order (…
CFLoRA: Federated Fine-tuning of LLMs with Complementary Factors for Error-free Aggregation
Yanan Ma, Qiyuan Chen, Zihan Fang +2
Federated low-rank adaptation (LoRA) enables collaborative fine-tuning of large language models without centralizing private client data. Its factorized update, however, creates a…
SplitLite: Low-Rank Residual Compression for Split Learning
Tao Li, Yulin Tang, Qi Guo +1
Federated fine-tuning of on-device large language models (LLMs) faces a significant computing burden. To overcome this limitation, split learning (SL) has emerged as a promising so…
Just Talk Once: Communication-Efficient Split Federated LLM Fine-Tuning on Edge Devices
Jiaxiang Geng, Xianhao Chen, Bing Luo
Large language model (LLM) fine-tuning is increasingly shifting toward data generated on edge devices, where memory, computation, bandwidth, and connectivity constraints make conve…
Efficient Resource Optimization for Split Federated Learning
Wei Wei, Xianhao Chen
Split federated learning (SFL) has emerged as a powerful paradigm for model training at the edge. However, SFL inherently involves discrete decision variables for model splitting a…
BALANCE: Hybrid Autoregressive-Speculative LLM Inference at the Network Edge
Guanqiao Qu, Shuo Chen, Qian Chen +2
Edge inference is a promising paradigm to provide large language model (LLM) inference services in next-generation mobile networks. LLM inference mainly relies on two approaches: A…
Update the Unseen Only: Minimizing AoI for Collaborative Perception through Online Learning
Yanan Ma, Zhuoyi Zhao, Zhengru Fang +3
While collaborative perception (CP) enhances the safety of autonomous driving, limited bandwidth can cause severe shared data staleness in CP systems. Existing age-of-information (…
Collaborative Air-Ground Sensing, Communication, Computing, Storage, and Intelligence for Low-Altitude Economy
Yiqin Deng, Junhui Gao, Zihan Fang +3
Low-altitude economy (LAE) is transforming low-altitude airspace into a new cyber-physical infrastructure. Although air-ground communications have been widely studied, LAE is funda…
SpaceMoE: Towards Orbital General Intelligence with Distributed Mixture-of-Experts Inference
Qian Chen, Xianhao Chen, Min Sheng +1
As satellite networks evolve to support increasingly diverse services and artificial general intelligence (AGI), large language models (LLMs) are emerging as a critical foundation…
Birdcast: Interest-aware BEV Multicasting for Infrastructure-assisted Collaborative Perception
Yanan Ma, Zhengru Fang, Yihang Tao +4
Vehicle-to-infrastructure collaborative perception (V2I-CP) leverages a high-vantage node to transmit supplementary information, i.e., bird's-eye-view (BEV) feature maps, to vehicl…
Rateless DeepJSCC for Broadcast Channels: a Rate-Distortion-Complexity Tradeoff
Zijun Qin, Jingxuan Huang, Zesong Fei +3
In recent years, numerous data-intensive broadcasting applications have emerged at the wireless edge, calling for a flexible tradeoff between distortion, transmission rate, and pro…
Federated Mixture-of-Experts Alignment on Mobile Edge Networks under Data Heterogeneity
Zihan Fang, Qianru Wang, Haonan An +5
The growing demand for on-device large language model (LLM) services on mobile edge devices has driven the adoption of Mixture-of-Experts (MoE) architectures, which scale model cap…
Shatter Throughput Ceilings: Leveraging Reflection Surfaces to Enhance Transmissions for Vehicular Fast Data Exchange
Qianyao Ren, Qingxiao Huang, Yiqin Deng +3
Rapid emergence of smart mobility necessitates high-volume bursty data transmission over a single link between a target vehicle and its designated edge computing-enabled Base Stati…
SiftMoE: Similarity-Aware Energy-Efficient Expert Selection for Wireless Distributed MoE Inference
Qian Chen, Xianhao Chen, Kaibin Huang
Mixture-of-Experts (MoE) architectures leverage sparse activation to enhance the scalability of large language models (LLMs), making them suitable for deployment in resource-constr…
GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems
Zheng Lin, Ons Aouedi, Zihan Fang +4
The increasing complexity of neural networks poses significant challenges for democratizing federated learning (FL) on resource-constrained edge devices. Parallel split learning (P…
HO-SFL: Hybrid-Order Split Federated Learning with Backprop-Free Clients and Dimension-Free Aggregation
Qiyuan Chen, Xian Wu, Yi Wang +1
Fine-tuning large models on edge devices is severely hindered by the memory-intensive backpropagation (BP) in standard frameworks like federated learning and split learning. While…
SplitCom: Communication-efficient Split Federated Fine-tuning of LLMs via Temporal Compression
Tao Li, Yulin Tang, Yiyang Song +4
Federated fine-tuning of on-device large language models (LLMs) mitigates privacy concerns by preventing raw data sharing. However, the intensive computational and memory demands p…
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…