Large language models (LLMs) have unlocked a plethora of powerful applications at the network edge, such as intelligent personal assistants. Data privacy and security concerns have prompted a shift towards edge-based fine-tuning of personal LLMs, away from cloud reliance. However, this raises issues of computational intensity and resource scarcity, hindering training efficiency and feasibility. While current studies investigate parameter-efficient fine-tuning (PEFT) techniques to mitigate resource constraints, our analysis indicates that these techniques are not sufficiently resource-efficient for edge devices. Other studies focus on exploiting the potential of edge devices through resource management optimization, yet are ultimately bottlenecked by the resource wall of individual devices. To tackle these challenges, we proposePAC+, a resource efficient collaborative edge AI framework for in-situ personal LLMs fine-tuning.PAC+breaks the resource wall of personal LLMs fine-tuning with a sophisticated algorithm-system co-design. (1) Algorithmically,PAC+implements a personal LLMs fine-tuning technique that is efficient in terms of parameters, time, and memory. It utilizes Parallel Adapters to circumvent the need for a full backward pass through the LLM backbone. Additionally, an activation cache mechanism further streamlining the process by negating the necessity for repeated forward passes across multiple epochs. (2) Systematically,PAC+leverages edge devices in close proximity, pooling them as a collective resource for in-situ personal LLMs fine-tuning, utilizing a hybrid data and pipeline parallelism to orchestrate distributed training. The use of the activation cache eliminates the need for forward pass through the LLM backbone, enabling exclusive fine-tuning of the Parallel Adapters using data parallelism. Extensive evaluation of the prototype implementation demonstrates thatPAC+significantly outperforms existing collaborative edge training systems, achieving up to a$9.7\times$end-to-end speedup. Furthermore, compared to mainstream LLM fine-tuning algorithms,PAC+reduces memory footprint by up to$88.16\%$.

We introduce EgoLife, a project to develop an egocentric life assistant that accompanies and enhances personal efficiency through AI-powered wearable glasses. To lay the foundation for this assistant, we conducted a comprehensive data collection study where six participants lived together for one week, continuously recording their daily activities—including discussions, shopping, cooking, social-izing, and entertainment—using AI glasses for multimodal person-view video references. This effort resulted in EgoLife Dataset, a comprehensive 300-hour egocentric, terpersonal, multiview, and multimodal daily life with intensive annotation. Leveraging this dataset, we troduce EgoLifeQA, a suite of long-context, life-oriented question-answering tasks designed to provide meaningful sistance in daily life by addressing practical questions as recalling past relevant events, monitoring health and offering personalized recommendations.To address the key technical challenges of 1) developing robust visual-audio models for egocentric data, 2) enabling identity recognition, and 3) facilitating long-context question answering over extensive temporal information, we introduce EgoBulter, an integrated system comprising EgoGPT and EgoRAG. EgoGPT is an omni-modal model trained on egocentric datasets, achieving state-of-the-art performance on egocentric video understanding. EgoRAG is a retrieval-based component that supports answering ultra-long-context questions. Our experimental studies verify their working mechanisms and reveal critical factors and bottlenecks, guiding future improvements. By releasing our datasets, models, and benchmarks, we aim to stimulate further research in egocentric AI assistants.

Mobile Edge Computing (MEC) revolutionizes real-time applications by extending cloud capabilities to network edges, enabling efficient computation offloading from mobile devices. In recent years, the location privacy concern within MEC offloading has been recognized, prompting the proposal of various methodologies to mitigate this concern. However, this paper demonstrates that the prevailing privacy protection methods exhibit vulnerabilities. First, we analyze the shortcomings of current methodologies through both system modeling and evaluation metrics. Then, we introduce a Learning-based Trajectory Reconstruction Attack (LTRA) to expose the weaknesses, achieving up to 91.2% reconstruction accuracy against the state-of-the-art protection method. Further, based onw-event differential privacy, we propose an ℓ-trajectory differentially private mechanism, i.e., OffloadingBD. Compared to the existing works, OffloadingBD provides more flexible and enhanced protection with sound privacy theoretical guarantee. Lastly, we conduct extensive experiments to evaluate LTRA and OffloadingBD. The experiment results show that LTRA has good generalization ability and OffloadingBD showcases a superior balance between privacy and utility compared with baselines.

Transformer-based models have unlocked a plethora of powerful intelligent applications at the edge, such as voice assistant in smart home. Traditional deployment approaches offload the inference workloads to the remote cloud server, which would induce substantial pressure on the backbone network as well as raise users' privacy concerns. To address that, in-situ inference has been recently recognized for edge intelligence, but it still confronts significant challenges stemming from the conflict between intensive workloads and limited on-device computing resources. In this paper, we leverage our observation that many edge environments usually comprise a rich set of accompanying trusted edge devices with idle resources and proposeGalaxy+, a collaborative edge AI system that breaks the resource walls across heterogeneous edge devices for efficient Transformer inference acceleration.Galaxy+introduces a novel hybrid model parallelism to orchestrate collaborative inference, along with a heterogeneity and memory-aware parallelism planning for fully exploiting the resource potential. To mitigate the impact of tensor synchronizations on inference latency under bandwidth-constrained edge environments,Galaxy+devises a tile-based fine-grained overlapping of communication and computation. Furthermore, a fault-tolerant re-scheduling mechanism is developed to address device-level resource dynamics, ensuring stable and low-latency inference. Extensive evaluation based on prototype implementation demonstrates thatGalaxy+remarkably outperforms state-of-the-art approaches under various edge environment setups, achieving a$1.2\times$to$4.24\times$end-to-end latency reduction. Besides,Galaxy+can adapt to device-level resource dynamics, swiftly rescheduling and restoring inference in the presence of unexpected straggler devices.

Large language models (LLMs) have unlocked a plethora of powerful applications at the network edge, such as intelligent personal assistants. Data privacy and security concerns have prompted a shift towards edge-based fine-tuning of personal LLMs, away from cloud reliance. However, this raises issues of computational intensity and resource scarcity, hindering training efficiency and feasibility. While current studies investigate parameter-efficient fine-tuning (PEFT) techniques to mitigate resource constraints, our analysis indicates that these techniques are not sufficiently resource-efficient for edge devices. Other studies focus on exploiting the potential of edge devices through resource management optimization, yet are ultimately bottlenecked by the resource wall of individual devices.

Low Earth Orbit (LEO) satellite communication is essential for wireless communication. While manufacturing and launching LEO satellites have become efficient and cost-effective, ground stations remain expensive due to complex designs for handling severe path losses and precise beam tracking. Hence, it is important to develop low cost and high-performance ground stations for widespread adoption of LEO satellite communication. Towards realizing this goal, we design a passive metasurface-enhanced LEO ground station system, named PMSat, combining metasurface's fine-grained beamforming capability with a small-size phased array's adaptive steering and focusing. For uplink, we jointly optimize the phase array codebook and uplink metasurface phase profile, and realize electronic steering by switching the codeword. We further jointly optimize the downlink metasurface phase profile to improve the focusing performance and enhance the received signal strength (RSS) over a wide range of incident angles. Our PMSat prototype consists of a single passive metasurface with 21 × 21 elements for uplink and 22 × 22 for downlink, along with 1 × 4 receiving and 1 × 4 transmitting phased array antennas. The effectiveness of our proposed PMSat is validated through extensive experiments, and results demonstrate that the optimized metasurface improves the SNR by 8.32 dB and 16.57 dB for uplink and downlink, respectively.