Related papers: Communication-Efficient Collaborative LLM Inferenc…
Mega-constellations of small-size Low Earth Orbit (LEO) satellites are currently planned and deployed by various private and public entities. While global connectivity is the main rationale, these constellations also offer the potential to…
Collaborative large language model (LLM) inference enables real-time, privacy-preserving AI services on resource-constrained edge devices by partitioning computational workloads between client devices and edge servers. However, this…
The advent of the sixth-generation (6G) wireless networks, enhanced by artificial intelligence, promises ubiquitous connectivity through Low Earth Orbit (LEO) satellites. These satellites are capable of collecting vast amounts of…
Low Earth orbit (LEO) satellite constellations are emerging as a key enabler of next-generation communications, offering global coverage and significantly lower latency compared to traditional terrestrial networks and geostationary…
Low earth orbit (LEO) satellite communication systems have gained increasing attention as a crucial supplement to terrestrial wireless networks due to their extensive coverage area. This letter presents a novel system design for LEO…
Low Earth orbit (LEO) satellite constellations play a pivotal role in sixth-generation (6G) wireless networks by providing global coverage, massive connections, and huge capacity. In this paper, we present a novel LEO satellite…
LLMs encounter significant challenges in resource consumption nowadays, especially with long contexts. Despite extensive efforts dedicate to enhancing inference efficiency, these methods primarily exploit internal sparsity within the…
Cooperative positioning with multiple low earth orbit (LEO) satellites is promising in providing location-based services and enhancing satellite-terrestrial communication. However, positioning accuracy is greatly affected by inter-beam…
Low-latency delivery of satellite imagery is essential for time-critical applications such as disaster response, intelligence, and infrastructure monitoring. However, traditional pipelines rely on downlinking all captured images before…
Low Earth orbit (LEO) satellites have been envisioned as a significant component of the sixth generation (6G) network architecture for achieving ubiquitous coverage and seamless access. However, the implementation of LEO satellites is…
Low earth orbit (LEO) satellite communications are expected to be incorporated in future wireless networks, in particular 5G and beyond networks, to provide global wireless access with enhanced data rates. Massive MIMO techniques, though…
Low earth orbit (LEO) satellite communication networks have been considered as promising solutions to providing high data rate and seamless coverage, where satellite beam management plays a key role. However, due to the limitation of beam…
Split-learning (SL) has recently gained popularity due to its inherent privacy-preserving capabilities and ability to enable collaborative inference for devices with limited computational power. Standard SL algorithms assume an ideal…
This paper investigates joint device identification, channel estimation, and signal detection for LEO satellite-enabled grant-free random access, where a multiple-input multipleoutput (MIMO) system with orthogonal time-frequency space…
Since local LLM inference on resource-constrained edge devices imposes a severe performance bottleneck, this paper proposes distributed prompt caching to enhance inference performance by cooperatively sharing intermediate processing states…
We investigate a multi-low Earth orbit (LEO) satellite system that simultaneously provides positioning and communication services to terrestrial user terminals. To address the challenges of accurately acquiring channel state information in…
Large language model (LLM) inference at the network edge is a promising serving paradigm that leverages distributed edge resources to run inference near users and enhance privacy. Existing edge-based LLM inference systems typically adopt…
Low Earth orbit (LEO) satellites are leveraged to support new position, navigation, and timing (PNT) service alternatives to GNSS. These alternatives require accurate propagation of satellite position and velocity with a realistic…
As dense low Earth orbit (LEO) constellations are being planned, the need for accurate synchronization schemes in high-speed environments remains a challenging problem to tackle. To further improve synchronization accuracy in channeling…
In this paper, we explore the integration of communication and synthetic aperture radar (SAR)-based remote sensing in low Earth orbit (LEO) satellite systems to provide real-time SAR imaging and information transmission. Considering the…