Related papers: QVRF: A Quantization-error-aware Variable Rate Fra…

Stabilizer states are a central resource in quantum information processing, underpinning a wide range of applications. While they can be efficiently generated via Clifford circuits, the presence of coherent errors, such as small-angle…

As the latest video coding standard, versatile video coding (VVC) has shown its ability in retaining pixel quality. To excavate more compression potential for video conference scenarios under ultra-low bitrate, this paper proposes a bitrate…

Analyzing large-scale data from simulations of turbulent flows is memory intensive, requiring significant resources. This major challenge highlights the need for data compression techniques. In this study, we apply a physics-informed Deep…

This paper introduces an end-to-end learned image compression system, termed ANFIC, based on Augmented Normalizing Flows (ANF). ANF is a new type of flow model, which stacks multiple variational autoencoders (VAE) for greater model…

Vision Transformer (ViT)-based models have shown state-of-the-art performance (e.g., accuracy) in vision-based AI tasks. However, realizing their capability in resource-constrained embedded AI systems is challenging due to their inherent…

In recent years, the task of video prediction-forecasting future video given past video frames-has attracted attention in the research community. In this paper we propose a novel approach to this problem with Vector Quantized Variational…

Quantization has become a predominant approach for model compression, enabling deployment of large models trained on GPUs onto smaller form-factor devices for inference. Quantization-aware training (QAT) optimizes model parameters with…

Fine-tuned transformer models have shown superior performances in many natural language tasks. However, the large model size prohibits deploying high-performance transformer models on resource-constrained devices. This paper proposes a…

With the growing demand for video applications, many advanced learned video compression methods have been developed, outperforming traditional methods in terms of objective quality metrics such as PSNR. Existing methods primarily focus on…

Despite impressive state-of-the-art performance on a wide variety of machine learning tasks, deep learning methods can produce over-confident predictions, particularly with limited training data. Therefore, quantifying uncertainty is…

Recent advances in federated learning have shown that asynchronous variants can be faster and more scalable than their synchronous counterparts. However, their design does not include quantization, which is necessary in practice to deal…

Quantum machine learning algorithms aim to take advantage of quantum computing to improve classical machine learning algorithms. In this paper, we have applied a quantum machine learning algorithm, the variational quantum classifier for the…

Inverse problems aim to determine model parameters of a mathematical problem from given observational data. Neural networks can provide an efficient tool to solve these problems. In the context of Bayesian inverse problems, Uncertainty…

How can we accurately quantize a pre-trained Vision Transformer model? Quantization algorithms compress Vision Transformers (ViTs) into low-bit formats, reducing memory and computation demands with minimal accuracy degradation. However,…

Reinforcement learning with verifiable rewards (RLVR) has become a trending paradigm for training reasoning large language models (LLMs). However, due to the autoregressive decoding nature of LLMs, the rollout process becomes the efficiency…

Recent neural compression methods have been based on the popular hyperprior framework. It relies on Scalar Quantization and offers a very strong compression performance. This contrasts from recent advances in image generation and…

Existing vector quantization (VQ) based autoregressive models follow a two-stage generation paradigm that first learns a codebook to encode images as discrete codes, and then completes generation based on the learned codebook. However, they…

This study introduces simple yet effective continuous- and discrete-variable quantum neural network (QNN) models as a transfer-learning approach for forecasting tasks. The CV-QNN features a single quantum layer with two qubits to establish…

Generally, adaptive bitrates for variable Internet bandwidths can be obtained through multi-pass coding. Referenceless prediction-based methods show practical benefits compared with multi-pass coding to avoid excessive computational…

Learning-based image compression has improved to a level where it can outperform traditional image codecs such as HEVC and VVC in terms of coding performance. In addition to good compression performance, device interoperability is essential…