Related papers: Efficient And Scalable Neural Residual Waveform Co…

Recent neural audio codecs have achieved impressive reconstruction quality, typically relying on quantization methods such as Residual Vector Quantization (RVQ), Vector Quantization (VQ) and Finite Scalar Quantization (FSQ). However, these…

Inference for state-of-the-art deep neural networks is computationally expensive, making them difficult to deploy on constrained hardware environments. An efficient way to reduce this complexity is to quantize the weight parameters and/or…

This work investigates the application of quantum machine learning techniques for classical and quantum communication across different qubit channel models. By employing parameterized quantum circuits and a flexible channel noise model, we…

Quantum Reservoir Computing (QRC) harnesses quantum systems to tackle intricate computational problems with exceptional efficiency and minimized energy usage. This paper presents a QRC framework that utilizes a minimalistic quantum…

Post-training quantization (PTQ) has played a key role in compressing large language models (LLMs) with ultra-low costs. However, existing PTQ methods only focus on handling the outliers within one layer or one block, which ignores the…

Quantum compute is scaling fast, from cloud QPUs to high throughput GPU simulators, making it timely to prototype quantum NLP beyond toy tasks. However, devices remain qubit limited and depth limited, training can be unstable, and classical…

This paper accelerates video perception, such as semantic segmentation and human pose estimation, by levering cross-frame redundancies. Unlike the existing approaches, which avoid redundant computations by warping the past features using…

While neural networks have advanced the frontiers in many applications, they often come at a high computational cost. Reducing the power and latency of neural network inference is key if we want to integrate modern networks into edge…

Speech codecs are traditionally optimized for waveform fidelity, allocating bits to preserve acoustic detail even when much of it can be inferred from linguistic structure. This leads to inefficient compression and suboptimal performance on…

Quantum low-density parity-check (qLDPC) codes can achieve high encoding rates and good code distance scaling, providing a promising route to low-overhead fault-tolerant quantum computing. However, the long-range connectivity required to…

We employ quantum-volume random-circuit sampling to benchmark the two-QPU entanglement-assisted distributed quantum computing (DQC) and compare it with single-QPU quantum computing. We first specify a single-qubit depolarizing noise model…

Convolutional Neural Networks (CNNs) have proven to be a powerful state-of-the-art method for image classification tasks. One drawback however is the high computational complexity and high memory consumption of CNNs which makes them…

Quantization has been an effective technology in ANN (approximate nearest neighbour) search due to its high accuracy and fast search speed. To meet the requirement of different applications, there is always a trade-off between retrieval…

With the emergence of neural audio codecs, which encode multiple streams of discrete tokens from audio, large language models have recently gained attention as a promising approach for zero-shot Text-to-Speech (TTS) synthesis. Despite the…

We present *-CFQ ("star-CFQ"): a suite of large-scale datasets of varying scope based on the CFQ semantic parsing benchmark, designed for principled investigation of the scalability of machine learning systems in a realistic compositional…

Quantization lowers memory usage, computational requirements, and latency by utilizing fewer bits to represent model weights and activations. In this work, we investigate the generalization properties of quantized neural networks, a…

Neural audio codecs (NACs) typically encode the short-term energy (gain) and normalized structure (shape) of speech/audio signals jointly within the same latent space. As a result, they are poorly robust to a global variation of the input…

In this study, we propose a novel architecture, the Quantum Pointwise Convolution, which incorporates pointwise convolution within a quantum neural network framework. Our approach leverages the strengths of pointwise convolution to…

Neural codecs have demonstrated strong performance in high-fidelity compression of audio signals at low bitrates. The token-based representations produced by these codecs have proven particularly useful for generative modeling. While much…

Post-training model quantization is a widely adopted technique for reducing the memory and computational costs of large language models (LLMs). However, most existing methods rely on uniform or heuristic bitwidth assignments, failing to…