The recent shift in Generative AI (GenAI) applications from cloud-only environments to end-user devices introduces new challenges in resource management, system efficiency, and user experience. This paper presents ConsumerBench, a comprehensive benchmarking framework designed to evaluate the system efficiency and response time of GenAI models running on end-user devices. Unlike existing benchmarks that assume exclusive model access on dedicated GPUs, ConsumerBench simulates realistic multi-application scenarios executing concurrently on constrained hardware. Furthermore, ConsumerBench supports customizable workflows that simulate complex tasks requiring coordination among multiple applications. ConsumerBench captures both application-level metrics, including latency and Service Level Objective (SLO) attainment, and system-level metrics like CPU/GPU utilization and memory bandwidth. Through extensive experiments, ConsumerBench reveals inefficiencies in resource sharing, unfair scheduling under greedy allocation, and performance pitfalls of static model server configurations. The paper also provides practical insights for model developers and system designers, highlighting the benefits of custom kernels tailored to consumer-grade GPU architectures and the value of implementing SLO-aware scheduling strategies.

Future wireless communication networks are in a position to move beyond data-centric, device-oriented connectivity and offer intelligent, immersive experiences based on task-oriented connections, especially in the context of the thriving development of pre-trained foundation models (PFM) and the evolving vision of 6G native artificial intelligence (AI). Therefore, redefining modes of collaboration between devices and servers and constructing native intelligence libraries become critically important in 6G. In this paper, we analyze the challenges of achieving 6G native AI from the perspectives of data, intelligence, and networks. Then, we propose a 6G native AI framework based on foundation models, provide a customization approach for intent-aware PFM, present a construction of a task-oriented AI toolkit, and outline a novel cloud-edge-end collaboration paradigm. As a practical use case, we apply this framework for orchestration, achieving the maximum sum rate within a wireless communication system, and presenting preliminary evaluation results. Finally, we outline research directions for achieving native AI in 6G.

The biggest benchmarking data set to date for a machine learning technique designed with data privacy in mind has been released open source by researchers at the University of Michigan. Called federated learning, the approach trains learning models on end-user devices, like smartphones and laptops, rather than requiring the transfer of private data to central servers. "By training in-situ on data where it is generated, we can train on larger real-world data," explained Fan Lai, U-M doctoral student in computer science and engineering, who presents the FedScale training environment at the International Conference on Machine Learning this week. "This also allows us to mitigate privacy risks and high communication and storage costs associated with collecting the raw data from end-user devices into the cloud," Lai said. Still a new technology, federated learning relies on an algorithm that serves as a centralized coordinator.

Organizations need to understand user behavior using data to improve their market position. Therefore, businesses solicit user feedback in a variety of ways. For example, Garmin, a well-known technology business, has a dedicated page for customers to submit ideas and suggestions. Similarly, Hotjar utilizes usability testing, whereas Zapier focuses on user feedback surveys. Personalization is another important aspect linked to user experience.

This paper proposes a lightweight method to attract users and increase views of the video by presenting personalized artistic media -- i.e, static thumbnails and animated GIFs. This method analyzes lightweight thumbnail containers (LTC) using computational resources of the client device to recognize personalized events from full-length sports videos. In addition, instead of processing the entire video, small video segments are processed to generate artistic media. This makes the proposed approach more computationally efficient compared to the baseline approaches that create artistic media using the entire video. The proposed method retrieves and uses thumbnail containers and video segments, which reduces the required transmission bandwidth as well as the amount of locally stored data used during artistic media generation. When extensive experiments were conducted on the Nvidia Jetson TX2, the computational complexity of the proposed method was 3.57 times lower than that of the SoA method. In the qualitative assessment, GIFs generated using the proposed method received 1.02 higher overall ratings compared to the SoA method. To the best of our knowledge, this is the first technique that uses LTC to generate artistic media while providing lightweight and high-performance services even on resource-constrained devices.

Federated learning is a machine learning method that enables machine learning models obtain experience from different data sets located in different sites (e.g. This allows personal data to remain in local sites, reducing possibility of personal data breaches. Federated learning is used to train other machine learning algorithms by using multiple local datasets without exchanging data. This allows companies to create a shared global model without putting training data in a central location. In machine learning, there are 2 steps, training and inference.