Related papers: Extremely Large-scale Array Systems: Near-Field Co…
Large Language Models (LLMs) exhibit high inference latency due to their autoregressive decoding nature. While the draft head in speculative decoding mitigates this issue, its full potential remains unexplored. In this paper, we introduce…
Entity alignment (EA) aims to find equivalent entities between two Knowledge Graphs. Existing embedding-based EA methods usually encode entities as embeddings, triples as embeddings' constraint and learn to align the embeddings. However,…
This paper addresses the mobility problem in extremely large antenna array (ELAA) communication systems. In order to account for the performance loss caused by the spherical wavefront of ELAA in the mobility scenario, we propose a wavefront…
Finetuned LLMs often exhibit poor uncertainty quantification, manifesting as overconfidence, poor calibration, and unreliable prediction results on test data or out-of-distribution samples. One approach commonly used in vision for…
The beamforming performance of the uniform circular array (UCA) in near-field wideband communication systems is investigated. Compared to uniform linear array (ULA), UCA exhibits uniform effective array aperture in all directions, thus…
Democratization of AI is an important topic within the broader topic of the digital divide. This issue is relevant to LLMs, which are becoming popular as AI co-pilots but suffer from a lack of accessibility due to high computational demand.…
This paper investigates beam training techniques for near-field (NF) extremely large-scale antenna arrays (ELAAs). Existing NF beam training methods predominantly rely on beam focusing, where the base station (BS) transmits highly spatially…
The natural integration of extremely large antenna arrays (ELAAs) and terahertz (THz) communications can potentially achieve Tbps data rates in 6G networks. However, due to the extremely large array aperture and wide bandwidth, a new…
The growing demand for on-device large language model (LLM) inference highlights the need for efficient mobile edge computing (MEC) solutions, especially in resource-constrained settings. Speculative decoding offers a promising solution by…
Fine-tuning is the primary methodology for tailoring pre-trained large language models to specific tasks. As the model's scale and the diversity of tasks expand, parameter-efficient fine-tuning methods are of paramount importance. One of…
Coded caching is an effective technique to decongest the amount of traffic in the backhaul link. In such a scheme, each file hosted in the server is divided into a number of packets to pursue a low transmission rate based on the delicate…
Entity alignment (EA) aims to merge two knowledge graphs (KGs) by identifying equivalent entity pairs. While existing methods heavily rely on human-generated labels, it is prohibitively expensive to incorporate cross-domain experts for…
The distributed upper 6 GHz (U6G) extra-large scale antenna array (ELAA) is a key enabler for future wireless communication systems, offering higher throughput and wider coverage, similar to existing ELAA systems, while effectively…
Low-rank adaptation (LoRA) and its variants are widely employed in fine-tuning large models, including large language models for natural language processing and diffusion models for computer vision. This paper proposes a generalized…
In wireless networks, coded caching is an effective technique to reduce network congestion during peak traffic times. Recently, a new concept called placement delivery array (PDA) was proposed to characterize the coded caching scheme. So…
In this work, we study codebook designs for full-dimension multiple-input multiple-output (FD-MIMO) systems with a multi-panel array (MPA). We propose novel codebooks which allow precise beam structures for MPA FD-MIMO systems by…
Engineering composite materials and devices with desired topological properties is accelerating the development of topological physics and its applications. Approaches of realizing novel topological hybrids, including in-situ epitaxy…
The deployment of extremely large-scale array (ELAA) brings higher spectral efficiency and spatial degree of freedom, but triggers issues on near-field channel estimation. Existing near-field channel estimation schemes primarily exploit…
Speculative decoding accelerates LLM inference but suffers from performance degradation when target models are fine-tuned for specific domains. A naive solution is to retrain draft models for every target model, which is costly and…
Weight quantization effectively reduces memory consumption and enable the deployment of Large Language Models on edge devices, yet existing hardware-friendly methods often rely on uniform quantization, which suffers from poor…