Related papers: DySCo: Dynamic Semantic Compression for Effective …

tempdisagg is a modern, extensible, and production-ready Python framework for temporal disaggregation of time series data. It transforms low-frequency aggregates into consistent, high-frequency estimates using a wide array of econometric…

Diffusion models (DMs) represent state-of-the-art generative models for continuous inputs. DMs work by constructing a Stochastic Differential Equation (SDE) in the input space (ie, position space), and using a neural network to reverse it.…

Latent representations are critical for the performance and robustness of machine learning models, as they encode the essential features of data in a compact and informative manner. However, in vision tasks, these representations are often…

Text-to-speech (TTS) methods have shown promising results in voice cloning, but they require a large number of labeled text-speech pairs. Minimally-supervised speech synthesis decouples TTS by combining two types of discrete speech…

Our work tackles the fundamental challenge of image segmentation in computer vision, which is crucial for diverse applications. While supervised methods demonstrate proficiency, their reliance on extensive pixel-level annotations limits…

Modern technological advances have expanded the scope of applications requiring analysis of large-scale datastreams that comprise multiple indefinitely long time series. There is an acute need for statistical methodologies that perform…

Many real-world datasets, such as healthcare, climate, and economics, are often collected as irregular time series, which poses challenges for accurate modeling. In this paper, we propose the Amortized Control of continuous State Space…

Multivariate time-series forecasting holds immense value across diverse applications, requiring methods to effectively capture complex temporal and inter-variable dynamics. A key challenge lies in uncovering the intrinsic patterns that…

Time series forecasting is vital in diverse sectors such as energy and transportation, where non-stationary dynamics are deeply intertwined with external events in other modalities such as texts. However, incorporating natural…

Remote sensing image segmentation faces persistent challenges in distinguishing morphologically similar categories and adapting to diverse scene variations. While existing methods rely on implicit representation learning paradigms, they…

The availability of reliable, high-resolution climate and weather data is important to inform long-term decisions on climate adaptation and mitigation and to guide rapid responses to extreme events. Forecasting models are limited by…

Process simulation is gaining attention for its ability to assess potential performance improvements and risks associated with business process changes. The existing literature presents various techniques, generally grounded in process…

Machine Learning models should ideally be compact and robust. Compactness provides efficiency and comprehensibility whereas robustness provides resilience. Both topics have been studied in recent years but in isolation. Here we present a…

Test-time scaling improves the inference performance of Large Language Models (LLMs) but also incurs substantial computational costs. Although recent studies have reduced token consumption through dynamic self-consistency, they remain…

Recently, deep learning has driven significant advancements in multivariate time series forecasting (MTSF) tasks. However, much of the current research in MTSF tends to evaluate models from a holistic perspective, which obscures the…

Stochastic differential equations (SDEs) or diffusions are continuous-valued continuous-time stochastic processes widely used in the applied and mathematical sciences. Simulating paths from these processes is usually an intractable problem,…

The dynamic mode decomposition (DMD) is a data-driven approach that extracts the dominant features from spatiotemporal data. In this work, we introduce sparse-mode DMD, a new variant of the optimized DMD framework that specifically…

Modeling multiscale patterns is crucial for long-term time series forecasting (TSF). However, redundancy and noise in time series, together with semantic gaps between non-adjacent scales, make the efficient alignment and integration of…

Embodied 3D Semantic Scene Completion (SSC) infers dense geometry and semantics from continuous egocentric observations. Most existing Gaussian-based methods rely on random initialization of many primitives within predefined spatial bounds,…

Local climate information is crucial for impact assessment and decision-making, yet coarse global climate simulations cannot capture small-scale phenomena. Current statistical downscaling methods infer these phenomena as temporally…