While Vision Transformers (ViTs) have emerged as foundation models for visual recognition, their high computational demands hinder deployment on edge platforms. Temporal redundancy across video frames offers a natural opportunity to reuse prior computations; however, existing methods remain far from ideal, often relying on simple frame-difference signals. To address this, we propose Ouroboros, a framework that encompasses geometric redundancy from spatial displacement of content. We achieve this by aligning invariant content to consistent coordinates across frames, enabled by warping each frame into a global coordinate system via motion vectors from a hardware-accelerated encoder. Yet, this design raises two key challenges: (i) preserving content that drifts out of the limited coordinate system and (ii) maintaining spatial continuity at frame borders. Ouroboros resolves these challenges by introducing a toroidal (i.e., wrap-around) input space and reassigning positional encodings to track displaced content. Leveraging the significant patch reduction via a system-efficient partial computation scheme, our approach accelerates inference by up to 2.61× and reduces energy consumption by 64.5% on NVIDIA Jet-son Orin devices, with <1% accuracy loss on object detection and instance segmentation, outperforming prior methods. Designed to process only non-redundant patches, Ouroboros also excels as an offloading system, yielding higher accuracy at lower bandwidth compared to prior schemes. The source code is available at https://github.com/ckswjd99-lab/Ouroboros.

The end-to-end latency requirement in mobile applications is not limited to the time taken from the server to the user device. The perceived latency by the users also includes the time taken for the data to traverse from the mobile operating system's kernel to the application layer. The kernels of modern mobile devices are designed to reduce the network packet processing delay by enqueuing incoming data in socket buffer and quickly dequeueing socket buffer for immediate data delivery to the application layer. However, this approach results in unnecessary CPU load on the mobile device due to the frequent execution of socket buffer dequeueing. We propose ADQ, which utilizes Application Data Unit (ADU) information—the smallest data unit interpretable by the application—in the mobile kernel to conduct minimal socket buffer dequeueing, aiming to reduce unnecessary CPU load without degrading delay performance. Our evaluation in a real-time video streaming scenario shows that ADQ can maintain a minimal level of latency using a restricted amount of CPU resources. Furthermore, in the presence of high CPU loads from competing tasks, we demonstrate that ADQ can improve delay performance compared to the default mobile kernel.

In this work, we explore a new communication paradigm for immersive 3D video conferencing, termed parameterized communication, which dramatically reduces bandwidth usage by eliminating the need to exchange excessive volumetric data. Instead, this approach extracts a compact set of informative parameters representing key elements in the 3D space, transmits only these parameters, and reconstructs the scene on the receiving end. Translating this concept into practice, we present Empilo, a mobile 3D conferencing system composed of a face parameter extractor and a neural rendering-based scene generator. However, while neural rendering excels at synthesizing arbitrary views of objects without explicit 3D models, its heavy computational demands present a major obstacle for mobile deployment. To overcome this challenge, we propose a novel technique called truncated ray marching, which significantly reduces computational overhead by replacing iterative MLP inferences with a single-pass of a shallow neural network. Furthermore, to ensure a consistently immersive experience, we structure the neural-free lightweight renderer as a decoupled component, dedicated to delivering rapid responsiveness to dynamic viewpoint changes. These breakthroughs on computation together enable Empilo to rely entirely on mobile resources, achieving real-time performance with a frame generation time of 30.3 ms and a re-rendering latency of just 6.6 ms—all while operating at an exceptionally low bitrate of 24 kbps. Our approach provides valuable guidance for the practical deployment of 3D conferencing, envisioning accessibility on par with platforms like FaceTime and Zoom.

With the rapid advances of deep learning and the commercialization of high-definition cameras in mobile and embedded devices, the demands from latency-critical applications such as AR and XR for high-quality video analytics (HVA) are soaring. By the nature of HVA aiming at enabling detailed analytics even for small objects, its on-device implementation is suffering from thermal and battery issues, which makes offloaded HVA an attractive solution. This work provides unique observations on the tradeoff pertaining to offloaded HVA: the frame encoding time, the frame transmission time, and the HVA accuracy. Our observations pose a fundamental question: given a latency budget, how to choose the encoding option that properly combines between the encoding time and the transmission time to maximize the HVA accuracy. To answer this question, we propose an offloaded HVA system, ENTRO, which exploits this tradeoff in real-time to maximize the HVA accuracy under the latency budget. Our extensive evaluations with ENTRO implemented on Nvidia AGX Xavier and Samsung Galaxy S20 Ultra over WiFi networks show 8.8× improvement in latency without accuracy loss compared to DDS, the state-of-the-art offloaded video analytics. Our evaluation over commercial 5G and LTE networks also indicates that ENTRO flexibly adapts its encoding option under the tradeoff and enables the latency-bounded HVA with 4K frames.