Related papers: Robust Retrospective Frequency and Phase Correctio…
Many particle-based Bayesian inference methods use a single global step size for all parts of the update. In Stein variational gradient descent (SVGD), however, each update combines two qualitatively different effects: attraction toward…
Time-series anomaly detection (TSAD) is a critical component in monitoring complex systems, yet modern deep learning-based detectors are often highly sensitive to localized input corruptions and structured noise. We propose ARTA…
Time-varying inhomogeneities on stellar surfaces constitute one of the largest sources of radial velocity (RV) error for planet detection and characterization. We show that stellar variations, because they manifest on coherent, rotating…
Reverberation as supervision (RAS) is a framework that allows for training monaural speech separation models from multi-channel mixtures in an unsupervised manner. In RAS, models are trained so that sources predicted from a mixture at an…
Large language models frequently commit unrecoverable reasoning errors mid-generation: once a wrong step is taken, subsequent tokens compound the mistake rather than correct it. We introduce $\textbf{Latent Phase-Shift Rollback}$ (LPSR): at…
Coordinate descent is one of the most popular approaches for solving Lasso and its extensions due to its simplicity and efficiency. When applying coordinate descent to solving Lasso, we update one coordinate at a time while fixing the…
Purpose: Develop a processing scheme for Gradient Echo (GRE) phase to enable restoration of susceptibility-related (SuR) features in regions affected by imperfect phase unwrapping, background suppression and low signal-to-noise ratio (SNR)…
Monocular depth estimation has seen significant advances through discriminative approaches, yet their performance remains constrained by the limitations of training datasets. While generative approaches have addressed this challenge by…
Time series augmentation is critical for training robust deep learning models, particularly in domains where labelled data is scarce and expensive to obtain. However, existing augmentation libraries for time series, mainly written in…
Time series data are collected in temporal order and are widely used to train systems for prediction, modeling and classification to name a few. These systems require large amounts of data to improve generalization and prevent over-fitting.…
Retrieval-Augmented Generation (RAG) enhances recency and factuality in answers. However, existing evaluations rarely test how well these systems cope with real-world noise, conflicting between internal and external retrieved contexts, or…
Multimodal time series (MTS) anomaly detection is crucial for maintaining the safety and stability of working devices (e.g., water treatment system and spacecraft), whose data are characterized by multivariate time series with diverse…
Sufficient dimension reduction (SDR) methods, which often rely on class precision matrices, are widely used in supervised statistical classification problems. However, when class-specific sample sizes are small relative to the original…
Purpose: Field monitoring measures field perturbations, which can be accounted for during image reconstructions. In certain field monitoring environments, significant phase deviations can arise far from isocenter due to the finite extent of…
Data assimilation performance can be significantly impacted by biased noise in observations, altering the signal magnitude and introducing fast oscillations or discontinuities when the system lacks smoothness. To mitigate these issues, this…
Single-shot time resolved Coherent Anti-Stokes Raman Scattering (CARS) is presented as a viable method for fast measurements of molecular spectra. The method is based on the short spatial extension of femtosecond pulses and maps time delays…
Multi-object tracking (MOT) is one of the most challenging tasks in computer vision, where it is important to correctly detect objects and associate these detections across frames. Current approaches mainly focus on tracking objects in each…
Recent advances in zero-shot text-to-speech (TTS), driven by language models, diffusion models and masked generation, have achieved impressive naturalness in speech synthesis. Nevertheless, stability and fidelity remain key challenges,…
Radar Cross Section measurement data is often analyzed using Inverse Synthetic Aperture Radar images. This paper compares backprojection and iterative smooth reweighted $\ell_1$-minimization as methods to analyze radar cross section…
The RTS smoother is widely used for state estimation and it is utilized here to increase the data quality with respect to physical coherence and to increase resolution. The purpose of this paper is to enhance the performance of the RTS…