Related papers: Local Hessian Spectral Filtering for Robust Intrin…
Traditional speech enhancement methods often oversimplify the task of restoration by focusing on a single type of distortion. Generative models that handle multiple distortions frequently struggle with phone reconstruction and…
One of the most often implied benefits of high-dimensional (HD) quantum systems is to lead to stronger forms of correlations, featuring increased robustness to noise. Here, we experimentally demonstrate the $n$-setting linear HD quantum…
Learning probabilistic models over strings is an important issue for many applications. Spectral methods propose elegant solutions to the problem of inferring weighted automata from finite samples of variable-length strings drawn from an…
In traditional reversible data hiding (RDH) methods, researchers pay attention to enlarge the embedding capacity (EC) and to reduce the embedding distortion (ED). Recently, a completely novel RDH algorithm was developed to embed secret data…
Standard Latent Diffusion Models rely on a complex, three-part architecture consisting of a separate encoder, decoder, and diffusion network, which are trained in multiple stages. This modular design is computationally inefficient, leads to…
Denoising is a crucial step for hyperspectral image (HSI) applications. Though witnessing the great power of deep learning, existing HSI denoising methods suffer from limitations in capturing the non-local self-similarity. Transformers have…
Video anomaly detection (VAD) mainly refers to identifying anomalous events that have not occurred in the training set where only normal samples are available. Existing works usually formulate VAD as a reconstruction or prediction problem.…
We introduce new finite-dimensional spaces specifically designed to approximate the solutions to high-frequency Helmholtz problems with smooth variable coefficients in dimension $d$. These discretization spaces are spanned by Gaussian…
We present the first provable method for identifying symmetric linear dynamical systems (LDS) with accuracy guarantees that are independent of the systems' state dimension or effective memory. Our approach builds upon recent work that…
Hyperspectral imaging, capturing detailed spectral information for each pixel, is pivotal in diverse scientific and industrial applications. Yet, the acquisition of high-resolution (HR) hyperspectral images (HSIs) often needs to be…
Latent diffusion models (LDMs) have achieved remarkable success in a variety of image tasks, yet achieving fine-grained, disentangled control over global structures versus fine details remains challenging. This paper explores…
With multiple iterations of updates, local statistical gradient descent (L-SGD) has been proven to be very effective in distributed machine learning schemes such as federated learning. In fact, many innovative works have shown that L-SGD…
Hyperdimensional (HD) computing offers an attractive alternative to deep networks for edge learning due to its simplicity, fast prototype-based inference, and compatibility with online updates. However, standard pixel-based HD encoders are…
Discrete diffusion models have emerged as a powerful class of models and a promising route to fast language generation, but practical implementations typically rely on factored reverse transitions ignoring cross-token dependencies and…
End-to-end text spotting has attached great attention recently due to its benefits on global optimization and high maintainability for real applications. However, the input scale has always been a tough trade-off since recognizing a small…
Early detection of head and neck tumors is crucial for patient survival. Often, diagnoses are made based on endoscopic examination of the larynx followed by biopsy and histological analysis, leading to a high inter-observer variability due…
To estimate a sparse linear model from data with Gaussian noise, consilience from lasso and compressed sensing literatures is that thresholding estimators like lasso and the Dantzig selector have the ability in some situations to identify…
LSTD is a popular algorithm for value function approximation. Whenever the number of features is larger than the number of samples, it must be paired with some form of regularization. In particular, L1-regularization methods tend to perform…
In this study, an implicit-explicit local differential transform method (IELDTM) based on Taylor series representations is produced for solving 2D and 3D advection-diffusion equations. The parabolic advection-diffusion equations are reduced…
This is a tutorial and survey paper on various methods for Sufficient Dimension Reduction (SDR). We cover these methods with both statistical high-dimensional regression perspective and machine learning approach for dimensionality…