Related papers: Cross-Scale Vector Quantization for Scalable Neura…

Large language models have shown exceptional capabilities in a wide range of tasks, such as text generation and video generation, among others. However, due to their massive parameter count, these models often require substantial storage…

Multi-agent collaborative perception (CP) improves scene understanding by sharing information across connected agents such as autonomous vehicles, unmanned aerial vehicles, and robots. Communication bandwidth, however, constrains…

Large Language Models (LLMs) are increasingly used in applications requiring long context lengths, but the key-value (KV) cache often becomes a memory bottleneck on GPUs as context grows. To address this, we propose Commutative Vector…

This paper proposes a training method having multiple cyclic training for achieving enhanced performance in low-bit quantized convolutional neural networks (CNNs). Quantization is a popular method for obtaining lightweight CNNs, where the…

We propose TQCodec, a neural audio codec designed for high-bitrate, high-fidelity music streaming. Unlike existing neural codecs that primarily target ultra-low bitrates (<= 16kbps), TQCodec operates at 44.1 kHz and supports bitrates from…

Circuit cutting enables large quantum circuits to run on small NISQ devices, but it introduces an exponentially high sampling overhead. Here, we present CutVQA, a co-design framework that integrates circuit cutting with quantum architecture…

A status updating system is considered in which a variable length code is used to transmit messages to a receiver over a noisy channel. The goal is to optimize the codewords lengths such that successfully-decoded messages are timely. That…

Noise remains the major obstacle to scalable quantum computation. Quantum benchmarking provides key information on noise properties and is an important step for developing more advanced quantum processors. However, current benchmarking…

Vision-Language Models (VLMs) achieve outstanding performance, yet their huge model size severely hinders deployment on edge devices with limited resources. As an efficient model compression technique, vector quantization (VQ) excels in…

Vector Quantized Variational AutoEncoders (VQ-VAEs) are designed to compress a continuous input to a discrete latent space and reconstruct it with minimal distortion. They operate by maintaining a set of vectors -- often referred to as the…

Quantizing deep neural networks is an effective method for reducing memory consumption and improving inference speed, and is thus useful for implementation in resource-constrained devices. However, it is still hard for extremely low-bit…

In the current age, users consume multimedia content in very heterogeneous scenarios in terms of network, hardware, and display capabilities. A naive solution to this problem is to encode multiple independent streams, each covering a…

Recently, sequence-to-sequence (seq-to-seq) models have been successfully applied in text-to-speech (TTS) to synthesize speech for single-language text. To synthesize speech for multiple languages usually requires multi-lingual speech from…

Enhancing coded speech suffering from far-end acoustic background noise, quantization noise, and potentially transmission errors, is a challenging task. In this work we propose two postprocessing approaches applying convolutional neural…

Low and ultra-low-bitrate neural speech coding achieves unprecedented coding gain by generating speech signals from compact speech features. This paper introduces additional coding efficiency in neural speech coding by reducing the temporal…

VQ-VAE, as a mainstream approach of speech tokenizer, has been troubled by ``index collapse'', where only a small number of codewords are activated in large codebooks. This work proposes product-quantized (PQ) VAE with more codebooks but…

We propose a Multi-Stage, Multi-Codebook (MSMC) approach to high-performance neural TTS synthesis. A vector-quantized, variational autoencoder (VQ-VAE) based feature analyzer is used to encode Mel spectrograms of speech training data by…

Near term quantum computers suffer from the presence of different noise sources. In order to mitigate for this effect and acquire results with significantly better accuracy, there is the urge of designing efficient error correction or error…

We provide a speech coding scheme employing a generative model based on SampleRNN that, while operating at significantly lower bitrates, matches or surpasses the perceptual quality of state-of-the-art classic wide-band codecs. Moreover, it…

Large Language Model (LLM) inference is typically memory-intensive, especially when processing large batch sizes and long sequences, due to the large size of key-value (KV) cache. Vector Quantization (VQ) is recently adopted to alleviate…