Feng Lyu

Shan Zhang, Jiayin Chen, Feng Lyu et al.

Embedded with advanced sensors, cameras and processors, the emerging automated driving vehicles are capable of sensing the environment and conducting automobile operation, paving the way to modern intelligent transportation systems (ITS) with high safety and efficiency. On the other hand, vehicular communication networks (VCNs) connect vehicles, infrastructures, clouds, and all other devices with communication modules, whereby vehicles can obtain local and global information to make intelligent operation decisions. Although the sensing-based automated driving technologies and VCNs have been investigated independently, their interactions and mutual benefits are still underdeveloped. In this article, we argue that VCNs have attractive potentials to enhance the on-board sensing-based automated vehicles from different perspectives, such as driving safety, transportation efficiency, as well as customer experiences. A case study is conducted to demonstrate that the traffic jam can be relieved at intersections with automated driving vehicles coordinated with each other through VCNs. Furthermore, we highlight the critical yet interesting issues for future research, based on the specific requirements posed by automated driving on VCNs.

Yuxin Liang, Peng Yang, Yuanyuan He et al.

The surging development of Artificial Intelligence-Generated Content (AIGC) marks a transformative era of the content creation and production. Edge servers promise attractive benefits, e.g., reduced service delay and backhaul traffic load, for hosting AIGC services compared to cloud-based solutions. However, the scarcity of available resources on the edge pose significant challenges in deploying generative AI models. In this paper, by characterizing the resource and delay demands of typical generative AI models, we find that the consumption of storage and GPU memory, as well as the model switching delay represented by I/O delay during the preloading phase, are significant and vary across models. These multidimensional coupling factors render it difficult to make efficient edge model deployment decisions. Hence, we present a collaborative edge-cloud framework aiming to properly manage generative AI model deployment on the edge. Specifically, we formulate edge model deployment problem considering heterogeneous features of models as an optimization problem, and propose a model-level decision selection algorithm to solve it. It enables pooled resource sharing and optimizes the trade-off between resource consumption and delay in edge generative AI model deployment. Simulation results validate the efficacy of the proposed algorithm compared with baselines, demonstrating its potential to reduce overall costs by providing feature-aware model deployment decisions.

Shuangwei Gao, Peng Yang, Yuxin Kong et al.

Artificial Intelligence Generated Content (AIGC) services can efficiently satisfy user-specified content creation demands, but the high computational requirements pose various challenges to supporting mobile users at scale. In this paper, we present our design of an edge-enabled AIGC service provisioning system to properly assign computing tasks of generative models to edge servers, thereby improving overall user experience and reducing content generation latency. Specifically, once the edge server receives user requested task prompts, it dynamically assigns appropriate models and allocates computing resources based on features of each category of prompts. The generated contents are then delivered to users. The key to this system is a proposed probabilistic model assignment approach, which estimates the quality score of generated contents for each prompt based on category labels. Next, we introduce a heuristic algorithm that enables adaptive configuration of both generation steps and resource allocation, according to the various task requests received by each generative model on the edge.Simulation results demonstrate that the designed system can effectively enhance the quality of generated content by up to 4.7% while reducing response delay by up to 39.1% compared to benchmarks.

Yuxin Kong, Peng Yang, Chongbin Yi et al.

Text-to-image (T2I) generation using multiple conditions enables fine-grained user control on the generated image. Yet, incorporating multi-condition inputs incurs substantial computation and communication overhead, due to additional preprocessing subtasks and control optimizations. It hence leads to unacceptable generation latency. In this paper, we propose an end-edge collaborative system design to accelerate multi-condition T2I generation through adaptive condition offloading and pruning. Extensive offline profiling reveal that, different conditions exhibit significant diversity in computation and communication costs. To this end, we propose a \textit{Subtask Manager} that jointly optimizes condition inference offloading and bandwidth allocation using a heuristic algorithm, balancing local and edge execution delays to minimize overall preprocessing latency. Then, we design a lightweight feature-driven \textit{Conditioning Scale Estimator} that evaluates the contribution of each condition by analyzing its feature activation strength and overlap with other conditions. This allows adaptive conditioning scale selection and pruning of insignificant conditions, thereby accelerating the denoising process. Extensive experimental results show that our system reduces latency by nearly 25\% and improves 6\% average generation quality, outperforming other benchmarks.

Xueying Li, Feng Lyu, Hao Wu et al.

Training-free Vision-Language Navigation (VLN) agents powered by foundation models can follow instructions and explore 3D environments. However, existing approaches rely on greedy frontier selection and passive spatial memory, leading to inefficient behaviors such as local oscillation and redundant revisiting. We argue that this stems from a lack of metacognitive capabilities: the agent cannot monitor its exploration progress, diagnose strategy failures, or adapt accordingly. To address this, we propose MetaNav, a metacognitive navigation agent integrating spatial memory, history-aware planning, and reflective correction. Spatial memory builds a persistent 3D semantic map. History-aware planning penalizes revisiting to improve efficiency. Reflective correction detects stagnation and uses an LLM to generate corrective rules that guide future frontier selection. Experiments on GOAT-Bench, HM3D-OVON, and A-EQA show that MetaNav achieves state-of-the-art performance while reducing VLM queries by 20.7%, demonstrating that metacognitive reasoning significantly improves robustness and efficiency.

Yanhao Dong, Yubo Miao, Weinan Li et al.

Large Language Models (LLMs) exhibit pronounced memory-bound characteristics during inference due to High Bandwidth Memory (HBM) bandwidth constraints. In this paper, we propose an L2 Cache-oriented asynchronous KV Cache prefetching method to break through the memory bandwidth bottleneck in LLM inference through computation-load overlap. By strategically scheduling idle memory bandwidth during active computation windows, our method proactively prefetches required KV Cache into GPU L2 cache, enabling high-speed L2 cache hits for subsequent accesses and effectively hiding HBM access latency within computational cycles. Extensive experiments on NVIDIA H20 GPUs demonstrate that the proposed method achieves 2.15x improvement in attention kernel efficiency and up to 1.97x end-to-end throughput enhancement, surpassing state-of-the-art baseline FlashAttention-3. Notably, our solution maintains orthogonality to existing optimization techniques and can be integrated with current inference frameworks, providing a scalable latency-hiding solution for next-generation LLM inference engines.

Conghao Zhou, Lulu Sun, Xiucheng Wang et al.

Mobile augmented reality (MAR) is envisioned as a key immersive application in 6G, enabling virtual content rendering aligned with the physical environment through device pose estimation. In this paper, we propose a novel agent-driven communication service provisioning approach for edge-assisted MAR, aiming to reduce communication overhead between MAR devices and the edge server while ensuring the quality of experience (QoE). First, to address the inaccessibility of MAR application-specific information to the network controller, we establish a digital agent powered by large language models (LLMs) on behalf of the MAR service provider, bridging the data and function gap between the MAR service and network domains. Second, to cope with the user-dependent and dynamic nature of data traffic patterns for individual devices, we develop a user-level QoE modeling method that captures the relationship between communication resource demands and perceived user QoE, enabling personalized, agent-driven communication resource management. Trace-driven simulation results demonstrate that the proposed approach outperforms conventional LLM-based QoE-aware service provisioning methods in both user-level QoE modeling accuracy and communication resource efficiency.

Conghao Zhou, Wen Wu, Hongli He et al.

In this paper, we investigate a computing task scheduling problem in space-air-ground integrated network (SAGIN) for delay-oriented Internet of Things (IoT) services. In the considered scenario, an unmanned aerial vehicle (UAV) collects computing tasks from IoT devices and then makes online offloading decisions, in which the tasks can be processed at the UAV or offloaded to the nearby base station or the remote satellite. Our objective is to design a task scheduling policy that minimizes offloading and computing delay of all tasks given the UAV energy capacity constraint. To this end, we first formulate the online scheduling problem as an energy-constrained Markov decision process (MDP). Then, considering the task arrival dynamics, we develop a novel deep risk-sensitive reinforcement learning algorithm. Specifically, the algorithm evaluates the risk, which measures the energy consumption that exceeds the constraint, for each state and searches the optimal parameter weighing the minimization of delay and risk while learning the optimal policy. Extensive simulation results demonstrate that the proposed algorithm can reduce the task processing delay by up to 30% compared to probabilistic configuration methods while satisfying the UAV energy capacity constraint.