相关论文: SAMA-IR: comprehensive input refinement methodolog…

The precision enhancement is demonstrated in an optical spatial measurement based on weak value amplification (WVA) system and split-like detection, by injecting a TEM$_{10}$ squeezed vacuum beam. It is the first time to experimentally…

Reconstruction-based methods, particularly those leveraging autoencoders, have been widely adopted for anomaly detection task in brain MRI. Unlike most existing works try to improve the task accuracy through architectural or algorithmic…

Sharpness-Aware Minimization (SAM) has proven highly effective in improving model generalization in machine learning tasks. However, SAM employs a fixed hyperparameter associated with the regularization to characterize the sharpness of the…

Sharpness-Aware Minimization (SAM) has recently emerged as a robust technique for improving the accuracy of deep neural networks. However, SAM incurs a high computational cost in practice, requiring up to twice as much computation as…

Targeting solutions over `flat' regions of the loss landscape, sharpness-aware minimization (SAM) has emerged as a powerful tool to improve generalizability of deep neural network based learning. While several SAM variants have been…

Perceptual image compression focuses on preserving high visual quality under low-bitrate constraints. Most existing approaches to perceptual compression leverage the strong generative capabilities of generative adversarial networks or…

We present a simple and efficient method for refining maps or correspondences by iterative upsampling in the spectral domain that can be implemented in a few lines of code. Our main observation is that high quality maps can be obtained even…

Flash memory-based processing-in-memory (flash-based PIM) offers high storage capacity and computational efficiency but faces significant reliability challenges due to noise in high-density multi-level cell (MLC) flash memories. Existing…

This study presents an innovative enhancement to retrieval-augmented generation (RAG) systems by seamlessly integrating fine-tuned large language models (LLMs) with vector databases. This integration capitalizes on the combined strengths of…

Improving multiparameter quantum estimation in magnonic systems via quantum noise suppression is a well-established and critical research objective. In this work, we propose an experimentally realistic scheme to improve the precision of…

Sharpness-aware minimization (SAM) improves generalization of various deep learning tasks. Motivated by popular architectures such as LoRA, we explore the implicit regularization of SAM for scale-invariant problems involving two groups of…

In this paper, a downlink intelligent reflecting surface (IRS) enhanced millimeter-wave (mmWave) non-orthogonal multiple access (NOMA) system is considered. A joint optimization problem over active beamforming, passive beamforming and power…

We address the problem of detecting the number of complex exponentials and estimating their parameters from a noisy signal using the Matrix Pencil (MP) method. We introduce the MP modes and present their informative spectral structure. We…

We propose a novel certified defense method for Image Quality Assessment (IQA) models based on randomized smoothing with noise applied in the feature space rather than the input space. Unlike prior approaches that inject Gaussian noise…

The latest industrial inference engines, such as FasterTransformer and TurboTransformers, have verified that half-precision floating point (FP16) and 8-bit integer (INT8) quantization can greatly improve model inference speed. However, the…

One persistent challenge in Speech Emotion Recognition (SER) is the ubiquitous environmental noise, which frequently results in deteriorating SER performance in practice. In this paper, we introduce a Two-level Refinement Network, dubbed…

Large Language Models (LLMs) often generate substantively relevant content but fail to adhere to formal constraints, leading to outputs that are conceptually correct but procedurally flawed. Traditional prompt refinement approaches focus on…

Multimodal large language models have demonstrated strong ability in capturing semantic representations for multimodal sentiment analysis. Their capacity to learn stable and generalizable multimodal features is limited, however, by the…

Quantum linear system algorithms (QLSA) have the potential to speed up Interior Point Methods (IPM). However, a major challenge is that QLSAs are inexact and sensitive to the condition number of the coefficient matrices of linear systems.…

Energy-efficient deep neural network (DNN) accelerators are prone to non-idealities that degrade DNN performance at inference time. To mitigate such degradation, existing methods typically add perturbations to the DNN weights during…