Related papers: Communication-Efficient Collaborative LLM Inferenc…
Large language models deliver strong generative performance but at the cost of massive parameter counts, memory use, and decoding latency. Prior work has shown that pruning and structured sparsity can preserve accuracy under substantial…
The construction of Low Earth Orbit (LEO) satellite constellations has recently spurred tremendous attention from academia and industry. 5G and 6G standards have specified LEO satellite network as a key component of 5G and 6G networks.…
Low Earth Orbit (LEO) constellations, each comprising a large number of satellites, have become a new source of big data "from the sky". Downloading such data to a ground station (GS) for big data analytics demands very high bandwidth and…
This work develops an analytical framework for downlink low Earth orbit (LEO) or medium Earth orbit (MEO) satellite communications, leveraging tools from stochastic geometry. We propose a tractable approach to the analysis of such satellite…
Federated inference enhances LLM performance in edge computing through weighted averaging of distributed model predictions. However, autoregressive LLM inference requires frequent full-model forward passes across workers, severely limiting…
This paper investigates compact large language model (LLM) deployment and world-model-assisted inference offloading in mobile edge computing (MEC) networks. We first propose an edge compact LLM deployment (ECLD) framework that jointly…
Large language models (LLMs) have been applied in various applications due to their astonishing capabilities. With advancements in technologies such as chain-of-thought (CoT) prompting and in-context learning (ICL), the prompts fed to LLMs…
With the rapid development of sixth-generation (6G) communication technology, global communication networks are moving towards the goal of comprehensive and seamless coverage. In particular, low earth orbit (LEO) satellites have become a…
Federated learning (FL) has emerged as a promising distributed training paradigm for Low Earth Orbit (LEO) networks by significantly reducing communication overhead. However, its deployment faces critical challenges, e.g., topology-induced…
Low Earth Orbit (LEO) satellites are emerging as key components of 6G networks, with many already deployed to support large-scale Earth observation and sensing related tasks. Federated Learning (FL) presents a promising paradigm for…
Driven by the growing demand for intelligent remote sensing applications, large artificial intelligence (AI) models pre-trained on large-scale unlabeled datasets and fine-tuned for downstream tasks have significantly improved learning…
The computational complexity of large language model (LLM) inference significantly constrains their deployment efficiency on edge devices. In contrast, small language models offer faster decoding and lower resource consumption but often…
This paper investigates joint device identification, channel estimation, and symbol detection for LEO satellite-enabled grant-free random access systems, specifically targeting scenarios where remote Internet-of-Things (IoT) devices operate…
Low-earth-orbit (LEO) satellite communication systems that use millimeter-wave frequencies rely on large antenna arrays with hybrid analog-digital architectures for rapid beam steering. LEO satellites are only visible from the ground for…
Recent advancements in large language models (LLMs) have catalyzed a substantial surge in demand for LLM services. While traditional cloud-based LLM services satisfy high-accuracy requirements, they fall short in meeting critical demands…
Massive multiple-input multiple-output (MIMO) is promising for low earth orbit (LEO) satellite communications due to the potential in enhancing the spectral efficiency. However, the conventional fully digital precoding architectures might…
The low-altitude economy (LAE) is gaining significant attention from academia and industry. Fortunately, LAE naturally aligns with near-field communications in extremely large-scale MIMO (XL-MIMO) systems. By leveraging near-field…
The high mobility of satellites in Low Earth Orbit (LEO) mega-constellations induces a highly dynamic network topology, leading to many problems like frequent service disruptions. To mitigate this, Packet-based Load Balancing (PBLB) is…
Integrated sensing and communication (ISAC) and ubiquitous connectivity are two usage scenarios of sixth generation (6G) networks. In this context, low earth orbit (LEO) satellite constellations, as an important component of 6G networks, is…
We present the first distributed optimization algorithm with lazy communication for collaborative geometric estimation, the backbone of modern collaborative simultaneous localization and mapping (SLAM) and structure-from-motion (SfM)…