INFOCOM 2025 Papers

We present the design, implementation, and evaluation of MiFly, a self-localization system for autonomous drones that works across indoor and outdoor environments, including low-visibility, dark, and GPS-denied settings. MiFly performs 6DoF self-localization by leveraging a single millimeter-wave (mmWave) anchor in its vicinity - even if that anchor is visually occluded. MiFly's core contribution is in its joint design of a mmWave anchor and localization algorithm. The low-power anchor features a novel dual-polarization dual-modulation architecture, which enables single-shot 3D localization. Mm Wave radars mounted on the drone perform 3D localization relative to the anchor and fuse this data with the drone's internal inertial measurement unit (IMU) to estimate its 6DoF trajectory. We implemented and evaluated MiFly on a DJI drone. We collected over 6,600 localization estimates across different trajectory patterns and demonstrate a median localization error of 7 cm and a 90thpercentile less than 15 cm, even in low-light conditions and when the anchor is fully occluded (visually) from the drone. Demo video: voutu.be/LfXfZ26tEok

Vision Transformers (ViTs) have outperformed traditional Convolutional Neural Network architectures and achieved state-of-the-art results in various computer vision tasks. Since ViTs are computationally expensive, the models either have to be pruned to run on resource-limited edge devices only or have to be executed on remote cloud servers after receiving the raw data transmitted over fluctuating networks. The resulting degraded performance or high latency all hinder their widespread applications. In this paper, we present Janus, the first framework for low-latency cloud-device collaborative Vision Transformer inference over dynamic networks. Janus overcomes the intrinsic model limitations of ViTs and realizes collaboratively executing ViT models on both cloud and edge devices, achieving low latency, high accuracy, and low communication overhead. Specifically, Janus judiciously combines token pruning techniques with a carefully designed fine-to-coarse model splitting policy and non-static mixed pruning policy. It attains a balance between accuracy and latency by dynamically selecting the optimal pruning level and split point. Experimental results across various tasks demonstrate that Janus enhances throughput by up to 5.15x and reduces latency violation ratios by up to 98.7% when compared with baseline approaches under various network environments.