搜索结果：Goodbye

Long-horizon video generation suffers from two intertwined issues. First, there is drift, where video quality degrades over time. Second, there are continuity issues which manifest as object permanence issues, or improperly rendering transient content (e.g., an object that appears in non-consecutive frames changing color/style). Recent work has focused on autoregressive distillation techniques that attack both problems simultaneously. We instead choose to focus on drift directly and introduce \textbf{Anchored Tree Sampling (ATS)}: a training-free inference-time scheduler that replaces left-to-right rollout with sparse-to-dense, anchor-bounded imputation organized as a tree. A root call produces sparse anchors over the full horizon, recursive refinement generates intermediate anchors, and final leaf spans are synthesized between neighboring anchors. This reduces the critical path from $K$ sequential rollout steps to $L+1$ tree-hierarchical steps and converts horizon-compounding drift into anchor-bounded drift. We focus on V2V generation in the \emph{static-camera} regime, where sparse anchors over the horizon are well approximated by the dense conditioning signal, and the base model

While Wi-Fi positioning is still more common indoors, using magnetic field features has become widely known and utilized as an alternative or supporting source of information. Magnetometer bias presents significant challenge in magnetic field navigation and SLAM. Traditionally, magnetometers have been calibrated using standard sphere or ellipsoid fitting methods and by requiring manual user procedures, such as rotating a smartphone in a figure-eight shape. This is not always feasible, particularly when the magnetometer is attached to heavy or fast-moving platforms, or when user behavior cannot be reliably controlled. Recent research has proposed using map data for calibration during positioning. This paper takes a step further and verifies that a pre-collected map is not needed; instead, calibration can be done as part of a SLAM process. The presented solution uses a factorized particle filter that factors out calibration in addition to the magnetic field map. The method is validated using smartphone data from a shopping mall and mobile robotics data from an office environment. Results support the claim that magnetometer calibration can be achieved during SLAM with comparable accur

Introduction. Distributed data processing and storage systems require efficient methods to distribute keys across buckets. While simple and fast, the traditional modulo-based mapping is unstable when the number of buckets changes, leading to spikes in system resource utilization, such as network or database requests. Consistent hash algorithms minimize remappings but are either significantly slower, require floating-point arithmetic, or are based on a family of hash functions rarely available in standard libraries. This work introduces JumpBackHash, a consistent hash algorithm that overcomes those shortcomings. Methodology. JumpBackHash applies the concept of active indices borrowed from consistent weighted sampling, which inherently leads to consistency. It generates the active indices in reverse order, which avoids floating-point operations, enables the minimization of consumed random values and the use of a standard pseudorandom generator, and finally leads to a very efficient algorithm. Results. Theoretical analysis shows that JumpBackHash has an expected constant runtime. The expected value and the variance of the number of consumed random values perfectly agree with the exper

Traditional methods for solving physical equations in curved spaces, especially in fluid mechanics and general relativity, rely heavily on the use of Christoffel symbols. These symbols provide the necessary corrections to account for curvature in differential geometries but lead to significant computational complexity, particularly in numerical simulations. In this paper, we propose a novel, simplified approach that obviates the need for Christoffel symbols by symbolic programming and advanced numerical methods. Our approach is based on defining a symbolic mapping between Euclidean space and curved coordinate systems, enabling the transformation of spatial and temporal derivatives through Jacobians and their inverses. This eliminates the necessity of using Christoffel symbols for defining local bases and tensors, allowing for the direct application of physical laws in Cartesian coordinates even when solving problems in curved spaces. We demonstrate the robustness and flexibility of our method through several examples, including the derivation of the Navier-Stokes equations in cylindrical coordinates, the modeling of complex flows in bent cylindrical tubes, and the breakup of viscoe

Indicators of Compromise (IOCs), such as IP addresses, file hashes, and domain names associated with known malware or attacks, are cornerstones of cybersecurity, serving to identify malicious activity on a network. In this work, we leverage real data to compare different parameterizations of IOC aging models. Our dataset comprises traffic at a real environment for more than 1 year. Among our trace-driven findings, we determine thresholds for the ratio between miss over monitoring costs such that the system benefits from storing IOCs for a finite time-to-live (TTL) before eviction. To the best of our knowledge, this is the first real world evaluation of thresholds related to IOC aging, paving the way towards realistic IOC decaying models.

This paper presents a novel Diffusion-Wavelet (DiWa) approach for Single-Image Super-Resolution (SISR). It leverages the strengths of Denoising Diffusion Probabilistic Models (DDPMs) and Discrete Wavelet Transformation (DWT). By enabling DDPMs to operate in the DWT domain, our DDPM models effectively hallucinate high-frequency information for super-resolved images on the wavelet spectrum, resulting in high-quality and detailed reconstructions in image space. Quantitatively, we outperform state-of-the-art diffusion-based SISR methods, namely SR3 and SRDiff, regarding PSNR, SSIM, and LPIPS on both face (8x scaling) and general (4x scaling) SR benchmarks. Meanwhile, using DWT enabled us to use fewer parameters than the compared models: 92M parameters instead of 550M compared to SR3 and 9.3M instead of 12M compared to SRDiff. Additionally, our method outperforms other state-of-the-art generative methods on classical general SR datasets while saving inference time. Finally, our work highlights its potential for various applications.

We present a robust methodology for identifying photometric binaries in star clusters. Using Gaia DR3, Pan-STARRS and 2MASS data, we self-consistently define the cluster parameters and binary demographics for the open clusters (OCs) NGC 2168 (M35), NGC 7789, NGC 6819, NGC 2682 (M67), NGC 188, and NGC 6791. These clusters span in age from ~200 Myr (NGC 2168) to more than ~8 Gyr (NGC 6791) and have all been extensively studied in the literature. We use the Bayesian Analysis of Stellar Evolution software suite (BASE-9) to derive the age, distance, reddening, metallicity, binary fraction, and binary mass-ratio posterior distributions for each cluster. We perform a careful analysis of our completeness and also compare our results to previous spectroscopic surveys. For our sample of main-sequence stars with masses between 0.6 - 1 M_Sun, we find that these OCs have similar binary fractions that are also broadly consistent with the field multiplicity fraction. Within the clusters, the binary fraction increases dramatically toward the cluster centers, likely a result of mass segregation. Furthermore nearly all clusters show evidence of mass segregation within the single and binary populatio

Tracking is a highly privacy-invasive data collection practice that has been ubiquitous in mobile apps for many years due to its role in supporting advertising-based revenue models. In response, Apple introduced two significant changes with iOS 14: App Tracking Transparency (ATT), a mandatory opt-in system for enabling tracking on iOS, and Privacy Nutrition Labels, which disclose what kinds of data each app processes. So far, the impact of these changes on individual privacy and control has not been well understood. This paper addresses this gap by analysing two versions of 1,759 iOS apps from the UK App Store: one version from before iOS 14 and one that has been updated to comply with the new rules. We find that Apple's new policies, as promised, prevent the collection of the Identifier for Advertisers (IDFA), an identifier for cross-app tracking. Smaller data brokers that engage in invasive data practices will now face higher challenges in tracking users - a positive development for privacy. However, the number of tracking libraries has roughly stayed the same in the studied apps. Many apps still collect device information that can be used to track users at a group level (cohort

A common technique for compressing a neural network is to compute the $k$-rank $\ell_2$ approximation $A_{k,2}$ of the matrix $A\in\mathbb{R}^{n\times d}$ that corresponds to a fully connected layer (or embedding layer). Here, $d$ is the number of the neurons in the layer, $n$ is the number in the next one, and $A_{k,2}$ can be stored in $O((n+d)k)$ memory instead of $O(nd)$. This $\ell_2$-approximation minimizes the sum over every entry to the power of $p=2$ in the matrix $A - A_{k,2}$, among every matrix $A_{k,2}\in\mathbb{R}^{n\times d}$ whose rank is $k$. While it can be computed efficiently via SVD, the $\ell_2$-approximation is known to be very sensitive to outliers ("far-away" rows). Hence, machine learning uses e.g. Lasso Regression, $\ell_1$-regularization, and $\ell_1$-SVM that use the $\ell_1$-norm. This paper suggests to replace the $k$-rank $\ell_2$ approximation by $\ell_p$, for $p\in [1,2]$. We then provide practical and provable approximation algorithms to compute it for any $p\geq1$, based on modern techniques in computational geometry. Extensive experimental results on the GLUE benchmark for compressing BERT, DistilBERT, XLNet, and RoBERTa confirm this theoretical

The detection of a stochastic background of long-wavelength gravitational waves (tensors) in the cosmic microwave background (CMB) anisotropy would be an invaluable probe of the high energy physics of the early universe. Unfortunately a combination of factors now makes such a detection seem unlikely: the vast majority of the CMB signal appears to come from density perturbations (scalars) - detailed fits to current observations indicate a tensor-to-scalar quadrupole ratio of T/S < 0.5 for the simplest models; and on the theoretical side the best-motivated inflationary models seem to require very small T/S. Unfortunately CMB temperature anisotropies can only probe a gravity wave signal down to T/S \sim 10% and optimistic assumptions about polarization of the CMB only lower this another order of magnitude.

Spectral functions of large matrices contains important structural information about the underlying data, and is thus becoming increasingly important. Many times, large matrices representing real-world data are \emph{sparse} or \emph{doubly sparse} (i.e., sparse in both rows and columns), and are accessed as a \emph{stream} of updates, typically organized in \emph{row-order}. In this setting, where space (memory) is the limiting resource, all known algorithms require space that is polynomial in the dimension of the matrix, even for sparse matrices. We address this challenge by providing the first algorithms whose space requirement is \emph{independent of the matrix dimension}, assuming the matrix is doubly-sparse and presented in row-order. Our algorithms approximate the Schatten $p$-norms, which we use in turn to approximate other spectral functions, such as logarithm of the determinant, trace of matrix inverse, and Estrada index. We validate these theoretical performance bounds by numerical experiments on real-world matrices representing social networks. We further prove that multiple passes are unavoidable in this setting, and show extensions of our primary technique, including

We obtain the first strong coresets for the $k$-median and subspace approximation problems with sum of distances objective function, on $n$ points in $d$ dimensions, with a number of weighted points that is independent of both $n$ and $d$; namely, our coresets have size $\text{poly}(k/ε)$. A strong coreset $(1+ε)$-approximates the cost function for all possible sets of centers simultaneously. We also give efficient $\text{nnz}(A) + (n+d)\text{poly}(k/ε) + \exp(\text{poly}(k/ε))$ time algorithms for computing these coresets. We obtain the result by introducing a new dimensionality reduction technique for coresets that significantly generalizes an earlier result of Feldman, Sohler and Schmidt \cite{FSS13} for squared Euclidean distances to sums of $p$-th powers of Euclidean distances for constant $p\ge1$.