Related papers: Rate-Adaptive Semantic Communication via Multi-Sta…
Quantization is an effective way to reduce the memory cost of large-scale model training. However, most existing methods adopt fixed-precision policies, which ignore the fact that optimizer-state distributions vary significantly across…
Transformers generalize to novel compositions of structures and entities after being trained on a complex dataset, but easily overfit on datasets of insufficient complexity. We observe that when the training set is sufficiently complex, the…
Large language models (LLMs) excel at natural language tasks but face deployment challenges due to their growing size outpacing GPU memory advancements. Model quantization mitigates this issue by lowering weight and activation precision,…
Semantic communications are expected to accomplish various semantic tasks with relatively less spectrum resource by exploiting the semantic feature of source data. To simultaneously serve both the data transmission and semantic tasks, joint…
With advances in deep learning, neural network based speech enhancement (SE) has developed rapidly in the last decade. Meanwhile, the self-supervised pre-trained model and vector quantization (VQ) have achieved excellent performance on many…
This paper adapts a Multiple-Model Coding (MMC) approach for sampled electrical signal waveforms to satisfy reconstructed signal quality constraints. The baseline MMC approach consists of two stages processing vectors of Voltage and Current…
Wireless extended reality (XR) has attracted wide attentions as a promising technology to improve users' mobility and quality of experience. However, the ultra-high data rate requirement of wireless XR has hindered its development for many…
Semantic communication is recognized for its high compression efficiency and robust resistance to noise. However, utilizing a fixed transmission rate in environments with dynamic signal-to-noise ratios (SNR) often results in inefficient use…
Utilizing low-resolution analog-to-digital converters (ADCs) in uplink massive multiple-input multiple-output (MIMO) systems is a practical solution to decrease power consumption. The performance gap between the low and high-resolution…
Transformer models have been successful in various sequence processing tasks, but the self-attention mechanism's computational cost limits its practicality for long sequences. Although there are existing attention variants that improve…
Traditional joint source-channel coding employs static learned semantic representations that cannot dynamically adapt to evolving source distributions. Shared semantic memories between transmitter and receiver can potentially enable…
Vector Quantization (VQ) underpins many modern generative frameworks such as VQ-VAE, VQ-GAN, and latent diffusion models. Yet, it suffers from the persistent problem of codebook collapse, where a large fraction of code vectors remains…
This letter introduces a multi-rate task-oriented communication (MR-ToC) framework. This framework dynamically adapts to variations in affordable data rate within the communication pipeline. It conceptualizes communication pipelines as…
Modern communications are usually designed to pursue a higher bit-level precision and fewer bits while transmitting a message. This article rethinks these two major features and introduces the concept and advantage of semantics that…
Semantic Communication (SemCom) has emerged as a promising paradigm for 6G networks, aiming to extract and transmit task-relevant information rather than minimizing bit errors. However, applying SemCom to realistic downlink Multi-User…
The rapid rise of real-time communication and large language models has significantly increased the importance of speech compression. Deep learning-based neural speech codecs have outperformed traditional signal-level speech codecs in terms…
We propose an optimization method for rate-adaptive CV-QKD systems, improving the SKR by up to 15%. A single information reconciliation setup can generate secret keys up to a distance of 112 km. This enables a unified reconciliation system,…
The communication overhead has become a significant bottleneck in data-parallel network with the increasing of model size and data samples. In this work, we propose a new algorithm LPC-SVRG with quantized gradients and its acceleration…
Recent neural audio compression models often rely on residual vector quantization for high-fidelity coding, but using a fixed number of per-frame codebooks is suboptimal for the wide variability of audio content-especially for signals that…
For a large number of tasks, quantum computing demonstrates the potential for exponential acceleration over classical computing. In the NISQ era, variable-component subcircuits enable applications of quantum computing. To reduce the…