Tootfinder

Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs
Jeongseok Hyun, Sukjun Hwang, Su Ho Han, Taeoh Kim, Inwoong Lee, Dongyoon Wee, Joon-Young Lee, Seon Joo Kim, Minho Shim
https://arxiv.org/abs/2507.07990

Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs
Video large language models (LLMs) achieve strong video understanding by leveraging a large number of spatio-temporal tokens, but suffer from quadratic computational scaling with token count. To address this, we propose a training-free spatio-temporal token merging method, named STTM. Our key insight is to exploit local spatial and temporal redundancy in video data which has been overlooked in prior work. STTM first transforms each frame into multi-granular spatial tokens using a coarse-to-fine…

sp_high_school: High school temporal contacts (2013)
These data sets correspond to the contacts and friendship relations between students in a high school in Marseilles, France, in December 2013, as measured through several techniques.
This network has 329 nodes and 668 edges.
Tags: Social, Offline, Unweighted, Weighted, Temporal, Metadata

Stream DaQ: Stream-First Data Quality Monitoring
Vasileios Papastergios, Anastasios Gounaris
https://arxiv.org/abs/2506.06147 https://

Stream DaQ: Stream-First Data Quality Monitoring
Data quality is fundamental to modern data science workflows, where data continuously flows as unbounded streams feeding critical downstream tasks, from elementary analytics to advanced artificial intelligence models. Existing data quality approaches either focus exclusively on static data or treat streaming as an extension of batch processing, lacking the temporal granularity and contextual awareness required for true streaming applications. In this paper, we present a novel data quality monit…

Bridging Logic and Learning: Decoding Temporal Logic Embeddings via Transformers
Sara Candussio, Gaia Saveri, Gabriele Sarti, Luca Bortolussi
https://arxiv.org/abs/2507.07808

Bridging Logic and Learning: Decoding Temporal Logic Embeddings via Transformers
Continuous representations of logic formulae allow us to integrate symbolic knowledge into data-driven learning algorithms. If such embeddings are semantically consistent, i.e. if similar specifications are mapped into nearby vectors, they enable continuous learning and optimization directly in the semantic space of formulae. However, to translate the optimal continuous representation into a concrete requirement, such embeddings must be invertible. We tackle this issue by training a Transformer…

ICU-TSB: A Benchmark for Temporal Patient Representation Learning for Unsupervised Stratification into Patient Cohorts
Dimitrios Proios, Alban Bornet, Anthony Yazdani, Jose F Rodrigues Jr, Douglas Teodoro
https://arxiv.org/abs/2506.06192

ICU-TSB: A Benchmark for Temporal Patient Representation Learning for Unsupervised Stratification into Patient Cohorts
Patient stratification identifying clinically meaningful subgroups is essential for advancing personalized medicine through improved diagnostics and treatment strategies. Electronic health records (EHRs), particularly those from intensive care units (ICUs), contain rich temporal clinical data that can be leveraged for this purpose. In this work, we introduce ICU-TSB (Temporal Stratification Benchmark), the first comprehensive benchmark for evaluating patient stratification based on temporal pat…

Change-Points Detection and Support Recovery for Spatially Indexed Functional Data
Fengyi Song, Decai Liang, Changliang Zou
https://arxiv.org/abs/2506.07206

Change-Points Detection and Support Recovery for Spatially Indexed Functional Data
Large volumes of spatiotemporal data, characterized by high spatial and temporal variability, may experience structural changes over time. Unlike traditional change-point problems, each sequence in this context consists of function-valued curves observed at multiple spatial locations, with typically only a small subset of locations affected. This paper addresses two key issues: detecting the global change-point and identifying the spatial support set, within a unified framework tailored to spat…

Revealing the Hidden Temporal Structure of HubertSoft Embeddings based on the Russian Phonetic Corpus
Anastasia Ananeva, Anton Tomilov, Marina Volkova
https://arxiv.org/abs/2507.06794

Revealing the Hidden Temporal Structure of HubertSoft Embeddings based on the Russian Phonetic Corpus
Self-supervised learning (SSL) models such as Wav2Vec 2.0 and HuBERT have shown remarkable success in extracting phonetic information from raw audio without labelled data. While prior work has demonstrated that SSL embeddings encode phonetic features at the frame level, it remains unclear whether these models preserve temporal structure, specifically, whether embeddings at phoneme boundaries reflect the identity and order of adjacent phonemes. This study investigates the extent to which boundar…

Experimental memory control in continuous variable optical quantum reservoir computing
Iris Paparelle, Johan Henaff, Jorge Garcia-Beni, Emilie Gillet, Gian Luca Giorgi, Miguel C. Soriano, Roberta Zambrini, Valentina Parigi
https://arxiv.org/abs/2506.07279

Experimental memory control in continuous variable optical quantum reservoir computing
Quantum reservoir computing (QRC) offers a promising framework for online quantum-enhanced machine learning tailored to temporal tasks, yet practical implementations with native memory capabilities remain limited. Here, we demonstrate an optical QRC platform based on deterministically generated multimode squeezed states, exploiting both spectral and temporal multiplexing in a fully continuous-variable (CV) setting, and enabling controlled fading memory. Data is encoded via programmable phase sh…

This https://arxiv.org/abs/2506.06155 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

A Novel Large-scale Crop Dataset and Dual-stream Transformer Method for Fine-grained Hierarchical Crop Classification from Integrated Hyperspectral EnMAP Data and Multispectral Sentinel-2 Time Series
Fine-grained crop classification is crucial for precision agriculture and food security monitoring. It requires simultaneous capture of both phenological dynamics (obtained from multi-temporal satellite data like Sentinel-2) and subtle spectral variations (demanding nanometer-scale spectral resolution from hyperspectral imagery). Research combining these two modalities remains scarce currently due to challenges in hyperspectral data acquisition and crop types annotation costs. To address these …

sp_high_school: High school temporal contacts (2013)
These data sets correspond to the contacts and friendship relations between students in a high school in Marseilles, France, in December 2013, as measured through several techniques.
This network has 329 nodes and 1437 edges.
Tags: Social, Offline, Unweighted, Weighted, Temporal, Metadata

DTECT: Dynamic Topic Explorer & Context Tracker
Suman Adhya, Debarshi Kumar Sanyal
https://arxiv.org/abs/2507.07910 https://arxiv…

DTECT: Dynamic Topic Explorer & Context Tracker
The explosive growth of textual data over time presents a significant challenge in uncovering evolving themes and trends. Existing dynamic topic modeling techniques, while powerful, often exist in fragmented pipelines that lack robust support for interpretation and user-friendly exploration. We introduce DTECT (Dynamic Topic Explorer & Context Tracker), an end-to-end system that bridges the gap between raw textual data and meaningful temporal insights. DTECT provides a unified workflow that sup…

STI-SNN: A 0.14 GOPS/W/PE Single-Timestep Inference FPGA-based SNN Accelerator with Algorithm and Hardware Co-Design
Kainan Wang, Chengyi Yang, Chengting Yu, Yee Sin Ang, Bo Wang, Aili Wang
https://arxiv.org/abs/2506.08842

STI-SNN: A 0.14 GOPS/W/PE Single-Timestep Inference FPGA-based SNN Accelerator with Algorithm and Hardware Co-Design
Brain-inspired Spiking Neural Networks (SNNs) have attracted attention for their event-driven characteristics and high energy efficiency. However, the temporal dependency and irregularity of spikes present significant challenges for hardware parallel processing and data reuse, leading to some existing accelerators falling short in processing latency and energy efficiency. To overcome these challenges, we introduce the STI-SNN accelerator, designed for resource-constrained applications with high…

Multilayer GNN for Predictive Maintenance and Clustering in Power Grids
Muhammad Kazim, Harun Pirim, Chau Le, Trung Le, Om Prakash Yadav
https://arxiv.org/abs/2507.07298

Multilayer GNN for Predictive Maintenance and Clustering in Power Grids
Unplanned power outages cost the US economy over $150 billion annually, partly due to predictive maintenance (PdM) models that overlook spatial, temporal, and causal dependencies in grid failures. This study introduces a multilayer Graph Neural Network (GNN) framework to enhance PdM and enable resilience-based substation clustering. Using seven years of incident data from Oklahoma Gas & Electric (292,830 records across 347 substations), the framework integrates Graph Attention Networks (spatial…

New Public Neutrino Alerts for Clusters of IceCube Events
Sarah Mancina (for the IceCube Collaboration), Sergio Cuenca (for the IceCube Collaboration), Elisa Bernardini (for the IceCube Collaboration)
https://arxiv.org/abs/2507.07491

New Public Neutrino Alerts for Clusters of IceCube Events
The IceCube Neutrino Observatory searches for the origins of astrophysical neutrinos using various techniques to overcome the significant backgrounds produced by cosmic-ray air showers. One such technique involves combining the neutrino data with other cosmic messengers to identify spatial and temporal correlations. IceCube contributes to multi-messenger astrophysics (MMA) by providing alerts for interesting events observed in the detector. The Gamma-ray Follow-Up (GFU) cluster alert system is …

Time Series Foundation Models for Multivariate Financial Time Series Forecasting
Ben A. Marconi
https://arxiv.org/abs/2507.07296 https://

Time Series Foundation Models for Multivariate Financial Time Series Forecasting
Financial time series forecasting presents significant challenges due to complex nonlinear relationships, temporal dependencies, variable interdependencies and limited data availability, particularly for tasks involving low-frequency data, newly listed instruments, or emerging market assets. Time Series Foundation Models (TSFMs) offer a promising solution through pretraining on diverse time series corpora followed by task-specific adaptation. This study evaluates two TSFMs (Tiny Time Mixers (TT…

Carbon-Aware Temporal Data Transfer Scheduling Across Cloud Datacenters
Elvis Rodrigues, Jacob Goldverg, Tevfik Kosar
https://arxiv.org/abs/2506.04117 http…

Carbon-Aware Temporal Data Transfer Scheduling Across Cloud Datacenters
Inter-datacenter communication is a significant part of cloud operations and produces a substantial amount of carbon emissions for cloud data centers, where the environmental impact has already been a pressing issue. In this paper, we present a novel carbon-aware temporal data transfer scheduling framework, called LinTS, which promises to significantly reduce the carbon emission of data transfers between cloud data centers. LinTS produces a competitive transfer schedule and makes scaling decisi…

Tracking the economy at high frequency
Freddy Garc\'ia-Alb\'an, Juan Jarr\'in
https://arxiv.org/abs/2507.07450 https://ar…

Tracking the economy at high frequency
This paper develops a high-frequency economic indicator using a Bayesian Dynamic Factor Model estimated with mixed-frequency data. The model incorporates weekly, monthly, and quarterly official indicators, and allows for dynamic heterogeneity and stochastic volatility. To ensure temporal consistency and avoid irregular aggregation artifacts, we introduce a pseudo-week structure that harmonizes the timing of observations. Our framework integrates dispersed and asynchronous official statistics in…

This https://arxiv.org/abs/2408.15920 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Nonlinear Filtering and Spatial Asymptotic Consistency for SPDEs Observed via Spatio-Temporal Point Processes
In this paper, we develop the mathematical framework for filtering problems arising from biophysical applications where data is collected from confocal laser scanning microscopy recordings of the space-time evolution of intracellular wave dynamics of biophysical quantities. In these applications, signals are described by stochastic partial differential equations (SPDEs) and observations can be modelled as functionals of marked point processes whose intensities depend on the underlying signal. W…

The TESS Ten Thousand Catalog: 10,001 uniformly-vetted and -validated Eclipsing Binary Stars detected in Full-Frame Image data by machine learning and analyzed by citizen scientists
Veselin B. Kostov, Brian P. Powell, Aline U. Fornear, Marco Z. Di Fraia, Robert Gagliano, Thomas L. Jacobs, Julien S. de Lambilly, Hugo A. Durantini Luca, Steven R. Majewski, Mark Omohundro, Jerome Orosz, Saul A. Rappaport, Ryan Salik, Donald Short, William Welsh, Svetoslav Alexandrov, Cledison Marcos da Si…

The TESS Ten Thousand Catalog: 10,001 uniformly-vetted and -validated Eclipsing Binary Stars detected in Full-Frame Image data by machine learning and analyzed by citizen scientists
The Transiting Exoplanet Survey Satellite (TESS) has surveyed nearly the entire sky in Full-Frame Image mode with a time resolution of 200 seconds to 30 minutes and a temporal baseline of at least 27 days. In addition to the primary goal of discovering new exoplanets, TESS is exceptionally capable at detecting variable stars, and in particular short-period eclipsing binaries which are relatively common, making up a few percent of all stars, and represent powerful astrophysical laboratories for …

This https://arxiv.org/abs/2506.05678 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Numerical Investigation of Sequence Modeling Theory using Controllable Memory Functions
The evolution of sequence modeling architectures, from recurrent neural networks and convolutional models to Transformers and structured state-space models, reflects ongoing efforts to address the diverse temporal dependencies inherent in sequential data. Despite this progress, systematically characterizing the strengths and limitations of these architectures remains a fundamental challenge.In this work, we propose a synthetic benchmarking framework to evaluate how effectively different sequenc…

Scalable Spatiotemporal Modeling for Bicycle Count Prediction
Rishikesh Yadav, Alexandra M. Schmidt, Aurelie Labbe, Pratheepa Jeganathan, Luis F. Miranda-Moreno
https://arxiv.org/abs/2506.07582

Scalable Spatiotemporal Modeling for Bicycle Count Prediction
We propose a novel sparse spatiotemporal dynamic generalized linear model for efficient inference and prediction of bicycle count data. Assuming Poisson distributed counts with spacetime-varying rates, we model the log-rate using spatiotemporal intercepts, dynamic temporal covariates, and site-specific effects additively. Spatiotemporal dependence is modeled using a spacetime-varying intercept that evolves smoothly over time with spatially correlated errors, and coefficients of some temporal co…

sp_high_school: High school temporal contacts (2013)
These data sets correspond to the contacts and friendship relations between students in a high school in Marseilles, France, in December 2013, as measured through several techniques.
This network has 329 nodes and 668 edges.
Tags: Social, Offline, Unweighted, Weighted, Temporal, Metadata

Spatial-Temporal-Spectral Mamba with Sparse Deformable Token Sequence for Enhanced MODIS Time Series Classification
Zack Dewis, Zhengsen Xu, Yimin Zhu, Motasem Alkayid, Mabel Heffring, Lincoln Linlin Xu
https://arxiv.org/abs/2508.02839

Spatial-Temporal-Spectral Mamba with Sparse Deformable Token Sequence for Enhanced MODIS Time Series Classification
Although MODIS time series data are critical for supporting dynamic, large-scale land cover land use classification, it is a challenging task to capture the subtle class signature information due to key MODIS difficulties, e.g., high temporal dimensionality, mixed pixels, and spatial-temporal-spectral coupling effect. This paper presents a novel spatial-temporal-spectral Mamba (STSMamba) with deformable token sequence for enhanced MODIS time series classification, with the following key contrib…

Breaking Anonymity at Scale: Re-identifying the Trajectories of 100K Real Users in Japan
Abhishek Kumar Mishra, Mathieu Cunche, Heber H. Arcolezi
https://arxiv.org/abs/2506.05611 …

Breaking Anonymity at Scale: Re-identifying the Trajectories of 100K Real Users in Japan
Mobility traces represent a critical class of personal data, often subjected to privacy-preserving transformations before public release. In this study, we analyze the anonymized Yjmob100k dataset, which captures the trajectories of 100,000 users in Japan, and demonstrate how existing anonymization techniques fail to protect their sensitive attributes. We leverage population density patterns, structural correlations, and temporal activity profiles to re-identify the dataset's real-world locatio…

Turbulence in the Geomagnetic Field at Earth Surface
Mingshu Zhao, Xiaoping Zeng, Yunfang Lin
https://arxiv.org/abs/2508.06143 https://arxiv.org/pdf/2508.0…

Turbulence in the Geomagnetic Field at Earth Surface
We investigated turbulence-like behavior in the geomagnetic field using ground-based magnetic observatory data across China. Through analysis of spatial and temporal structure functions, we find power-law scaling consistent with Kolmogorov-like turbulence under extended self-similarity. We also identify significant correlations between vertical geomagnetic field variations and large earthquakes. The combination of turbulent characteristics with these correlations suggests a physical mechanism w…

A visual analytics tool for taxonomy-based trajectory data exploration
Ivan A. Hanono Cozzetti, Ahmad Abdou
https://arxiv.org/abs/2507.22899 https://arxiv.…

A visual analytics tool for taxonomy-based trajectory data exploration
The analysis of spatio-temporal data presents significant challenges due to the complexity and heterogeneity of movement patterns. This project proposes a data analytics tool that combines data visualization and statistical computation to facilitate spatio-temporal data analysis through a multi-level approach. The tool categorizes moving objects into distinct taxonomies using Machine Learning models, adding meaningful structure to the analysis. Two case studies demonstrate the methodology's eff…

Data-Driven Discovery of Mobility Periodicity for Understanding Urban Transportation Systems
Xinyu Chen, Qi Wang, Yunhan Zheng, Nina Cao, HanQin Cai, Jinhua Zhao
https://arxiv.org/abs/2508.03747

Data-Driven Discovery of Mobility Periodicity for Understanding Urban Transportation Systems
Uncovering the temporal regularity of human mobility is crucial for discovering urban dynamics and has implications for various decision-making processes and urban system applications. This study formulates the periodicity quantification problem in complex and multidimensional human mobility data as a sparse identification of dominant positive auto-correlations in time series autoregression, allowing one to discover and quantify significant periodic patterns such as weekly periodicity from a da…

Future Deployment and Flexibility of Distributed Energy Resources in the Distribution Grids of Switzerland
Lorenzo Zapparoli, Alfredo Oneto, Mar\'ia Parajeles Herrera, Blazhe Gjorgiev, Gabriela Hug, Giovanni Sansavini
https://arxiv.org/abs/2506.08724

Future Deployment and Flexibility of Distributed Energy Resources in the Distribution Grids of Switzerland
The decarbonization goals worldwide drive the energy transition of power distribution grids, which operate under increasingly volatile conditions and closer to their technical limits. In this context, localized operational data with high temporal and spatial resolution is essential for their effective planning and regulation. Nevertheless, information on grid-connected distributed energy resources, such as electric vehicles, photovoltaic systems, and heat pumps, is often fragmented, inconsisten…

Integrating Complexity and Biological Realism: High-Performance Spiking Neural Networks for Breast Cancer Detection
Zofia Rudnicka, Januszcz Szczepanski, Agnieszka Pregowska
https://arxiv.org/abs/2506.06265

Integrating Complexity and Biological Realism: High-Performance Spiking Neural Networks for Breast Cancer Detection
Spiking Neural Networks (SNNs) event-driven nature enables efficient encoding of spatial and temporal features, making them suitable for dynamic time-dependent data processing. Despite their biological relevance, SNNs have seen limited application in medical image recognition due to difficulties in matching the performance of conventional deep learning models. To address this, we propose a novel breast cancer classification approach that combines SNNs with Lempel-Ziv Complexity (LZC) a computat…

Interband Lag Variability in Active Galactic Nuclei across ZTF Data from Multiple Years
Zhen-Bo Su, Zhen-Yi Cai, Hengxiao Guo, Mouyuan Sun, Jun-Xian Wang
https://arxiv.org/abs/2507.04359

Interband Lag Variability in Active Galactic Nuclei across ZTF Data from Multiple Years
Interband lags in the optical continua of active galactic nuclei (AGN) have been observed over years of monitoring, yet their physical origins remain unclear. While variable interband lags have been found in a few individual AGN potentially, the temporal behavior of interband lags of an AGN sample has not been explored systematically. Here, we analyze the interband lags of 94 bright AGN at $z<0.8$, using both seasonal one-year and full six-year $gri$-band light curves from Zwicky Transient Faci…

A Generative Adaptive Replay Continual Learning Model for Temporal Knowledge Graph Reasoning
Zhiyu Zhang, Wei Chen, Youfang Lin, Huaiyu Wan
https://arxiv.org/abs/2506.04083

A Generative Adaptive Replay Continual Learning Model for Temporal Knowledge Graph Reasoning
Recent Continual Learning (CL)-based Temporal Knowledge Graph Reasoning (TKGR) methods focus on significantly reducing computational cost and mitigating catastrophic forgetting caused by fine-tuning models with new data. However, existing CL-based TKGR methods still face two key limitations: (1) They usually one-sidedly reorganize individual historical facts, while overlooking the historical context essential for accurately understanding the historical semantics of these facts; (2) They preserv…

Boosting Temporal Sentence Grounding via Causal Inference
Kefan Tang, Lihuo He, Jisheng Dang, Xinbo Gao
https://arxiv.org/abs/2507.04958 https://

Boosting Temporal Sentence Grounding via Causal Inference
Temporal Sentence Grounding (TSG) aims to identify relevant moments in an untrimmed video that semantically correspond to a given textual query. Despite existing studies having made substantial progress, they often overlook the issue of spurious correlations between video and textual queries. These spurious correlations arise from two primary factors: (1) inherent biases in the textual data, such as frequent co-occurrences of specific verbs or phrases, and (2) the model's tendency to overfit to…

Reinforcement Learning with Action Chunking
Qiyang Li, Zhiyuan Zhou, Sergey Levine
https://arxiv.org/abs/2507.07969 https://arxiv.org/pdf/2507.07969 https://arxiv.org/html/2507.07969
arXiv:2507.07969v1 Announce Type: new
Abstract: We present Q-chunking, a simple yet effective recipe for improving reinforcement learning (RL) algorithms for long-horizon, sparse-reward tasks. Our recipe is designed for the offline-to-online RL setting, where the goal is to leverage an offline prior dataset to maximize the sample-efficiency of online learning. Effective exploration and sample-efficient learning remain central challenges in this setting, as it is not obvious how the offline data should be utilized to acquire a good exploratory policy. Our key insight is that action chunking, a technique popularized in imitation learning where sequences of future actions are predicted rather than a single action at each timestep, can be applied to temporal difference (TD)-based RL methods to mitigate the exploration challenge. Q-chunking adopts action chunking by directly running RL in a 'chunked' action space, enabling the agent to (1) leverage temporally consistent behaviors from offline data for more effective online exploration and (2) use unbiased $n$-step backups for more stable and efficient TD learning. Our experimental results demonstrate that Q-chunking exhibits strong offline performance and online sample efficiency, outperforming prior best offline-to-online methods on a range of long-horizon, sparse-reward manipulation tasks.
toXiv_bot_toot

This https://arxiv.org/abs/2506.02576 has been replaced.
link: https://scholar.google.com/scholar?q=a

ADFormer: Aggregation Differential Transformer for Passenger Demand Forecasting
Passenger demand forecasting helps optimize vehicle scheduling, thereby improving urban efficiency. Recently, attention-based methods have been used to adequately capture the dynamic nature of spatio-temporal data. However, existing methods that rely on heuristic masking strategies cannot fully adapt to the complex spatio-temporal correlations, hindering the model from focusing on the right context. These works also overlook the high-level correlations that exist in the real world. Effectively …

sp_high_school: High school temporal contacts (2013)
These data sets correspond to the contacts and friendship relations between students in a high school in Marseilles, France, in December 2013, as measured through several techniques.
This network has 329 nodes and 668 edges.
Tags: Social, Offline, Unweighted, Weighted, Temporal, Metadata

Graph Estimation Based on Neighborhood Selection for Matrix-variate Data
Minsub Shin, Johan Lim, Seongoh Park
https://arxiv.org/abs/2507.04711 https://

Graph Estimation Based on Neighborhood Selection for Matrix-variate Data
Undirected graphical models are powerful tools for uncovering complex relationships among high-dimensional variables. This paper aims to fully recover the structure of an undirected graphical model when the data naturally take matrix form, such as temporal multivariate data. As conventional vector-variate analyses have clear limitations in handling such matrix-structured data, several approaches have been proposed, mostly relying on the likelihood of the Gaussian distribution with a separable…

SCOUT: An in-vivo Methane Sensing System for Real-time Monitoring of Enteric Emissions in Cattle with ex-vivo Validation
Yuelin Deng, Hinayah Rojas de Oliveira, Richard M. Voyles, Upinder Kaur
https://arxiv.org/abs/2508.04056

SCOUT: An in-vivo Methane Sensing System for Real-time Monitoring of Enteric Emissions in Cattle with ex-vivo Validation
Accurate measurement of enteric methane emissions remains a critical bottleneck for advancing livestock sustainability through genetic selection and precision management. Existing ambient sampling approaches suffer from low data retention rates, environmental interference, and limited temporal resolution. We developed SCOUT (Smart Cannula-mounted Optical Unit for Trace-methane), the first robust in-vivo sensing system enabling continuous, high-resolution monitoring of ruminal methane concentrat…

This https://arxiv.org/abs/2503.22103 has been replaced.
link: https://scholar.google.com/scholar?q=a

Hierarchical models for small area estimation using zero-inflated forest inventory variables: comparison and implementation
National Forest Inventory (NFI) data are typically limited to sparse networks of sample locations due to cost constraints. While traditional design-based estimators provide reliable forest parameter estimates for large areas, there is increasing interest in model-based small area estimation (SAE) methods to improve precision for smaller spatial, temporal, or biophysical domains. SAE methods can be broadly categorized into area- and unit-level models, with unit-level models offering greater flex…

Fast Algorithm for Moving Sound Source
Dong Yang
https://arxiv.org/abs/2508.03065 https://arxiv.org/pdf/2508.03065

Fast Algorithm for Moving Sound Source
Modern neural network-based speech processing systems need reverberation resistance, relying on large amounts of reverberation data for training. Existing methods simulate dynamic scenarios by sampling static systems or supplement with measured data, but struggle to simulate motion data conforming to physical laws. To address insufficient training data for speech enhancement models in moving scenarios, this paper proposes Yang's motion spatio-temporal sampling reconstruction theory, enabling ef…

Alzheimers Disease Classification in Functional MRI With 4D Joint Temporal-Spatial Kernels in Novel 4D CNN Model
Javier Salazar Cavazos, Scott Peltier
https://arxiv.org/abs/2506.02060

Alzheimers Disease Classification in Functional MRI With 4D Joint Temporal-Spatial Kernels in Novel 4D CNN Model
Previous works in the literature apply 3D spatial-only models on 4D functional MRI data leading to possible sub-par feature extraction to be used for downstream tasks like classification. In this work, we aim to develop a novel 4D convolution network to extract 4D joint temporal-spatial kernels that not only learn spatial information but in addition also capture temporal dynamics. Experimental results show promising performance in capturing spatial-temporal data in functional MRI compared to 3D…

Dynamic Campus Origin-Destination Mobility Prediction using Graph Convolutional Neural Network on WiFi Logs
Godwin Badu-Marfo, Bilal Farooq
https://arxiv.org/abs/2507.05507

Dynamic Campus Origin-Destination Mobility Prediction using Graph Convolutional Neural Network on WiFi Logs
We present an integrated graph-based neural networks architecture for predicting campus buildings occupancy and inter-buildings movement at dynamic temporal resolution that learns traffic flow patterns from Wi-Fi logs combined with the usage schedules within the buildings. The relative traffic flows are directly estimated from the WiFi data without assuming the occupant behaviour or preferences while maintaining individual privacy. We formulate the problem as a data-driven graph structure repre…

Temporal Evolution of the Third Interstellar Comet 3I/ATLAS: Spin, Color, Spectra and Dust Activity
T. Santana-Ros, O. Ivanova, S. Mykhailova, N. Erasmus, K. Kami\'nski, D. Oszkiewicz, T. Kwiatkowski, M. Hus\'arik, T. S. Ngwane, A. Penttil\"a
https://arxiv.org/abs/2508.00808

Temporal Evolution of the Third Interstellar Comet 3I/ATLAS: Spin, Color, Spectra and Dust Activity
We aim to characterize the physical and activity properties of the interstellar comet 3I/ATLAS through spectroscopic and photometric observations during the first month after its discovery. We performed time-series photometry and long-slit spectroscopy between 2 and 29 July 2025 using multiple ground-based telescopes. Photometric data were calibrated against field stars from the ATLAS and APASS catalogs, and Fourier analysis was applied to derive the comet's rotational period. Spectral data wer…

F-Hash: Feature-Based Hash Design for Time-Varying Volume Visualization via Multi-Resolution Tesseract Encoding
Jianxin Sun, David Lenz, Hongfeng Yu, Tom Peterka
https://arxiv.org/abs/2507.03836

F-Hash: Feature-Based Hash Design for Time-Varying Volume Visualization via Multi-Resolution Tesseract Encoding
Interactive time-varying volume visualization is challenging due to its complex spatiotemporal features and sheer size of the dataset. Recent works transform the original discrete time-varying volumetric data into continuous Implicit Neural Representations (INR) to address the issues of compression, rendering, and super-resolution in both spatial and temporal domains. However, training the INR takes a long time to converge, especially when handling large-scale time-varying volumetric datasets. …

The Observations of Magnetic Reconnection During the Interaction Process of Two Active Region Filaments
Zongyin Wu, Zhike Xue, Xiaoli Yan, Jincheng Wang, Liheng Yang, Zhe Xu, Qiaoling Li, Yang Peng, Liping Yang, Yian Zhou, Xinsheng Zhang, Liufan Gong, Qifan Dong, Guotang Wu
https://arxiv.org/abs/2506.05659

The Observations of Magnetic Reconnection During the Interaction Process of Two Active Region Filaments
We investigate the interaction between two filaments (F1 and F2) and their subsequent magnetic reconnection in active region (AR) NOAA 13296 and AR NOAA 13293 on May 9, 2023, utilizing high spatial and temporal resolution and multi-wavelength observational data from the Solar Dynamics Observatory, the New Vacuum Solar Telescope, and the Chinese Hα Solar Explorer. The movement of F1 from the southeast toward the northwest, driven by the motion of the positive magnetic polarity (P1), leads to a …

Forecasting Geopolitical Events with a Sparse Temporal Fusion Transformer and Gaussian Process Hybrid: A Case Study in Middle Eastern and U.S. Conflict Dynamics
Hsin-Hsiung Huang, Hayden Hampton
https://arxiv.org/abs/2506.20935

Forecasting Geopolitical Events with a Sparse Temporal Fusion Transformer and Gaussian Process Hybrid: A Case Study in Middle Eastern and U.S. Conflict Dynamics
Forecasting geopolitical conflict from data sources like the Global Database of Events, Language, and Tone (GDELT) is a critical challenge for national security. The inherent sparsity, burstiness, and overdispersion of such data cause standard deep learning models, including the Temporal Fusion Transformer (TFT), to produce unreliable long-horizon predictions. We introduce STFT-VNNGP, a hybrid architecture that won the 2023 Algorithms for Threat Detection (ATD) competition by overcoming these l…

Robust Spatio-Temporal Distributional Regression
Tomotaka Momozaki, Shonosuke Sugasawa, Tomoyuki Nakagawa, Hiroko Kato Solvang, Sam Subbey
https://arxiv.org/abs/2508.05041 https…

Robust Spatio-Temporal Distributional Regression
Motivated by investigating spatio-temporal patterns of the distribution of continuous variables, we consider describing the conditional distribution function of the response variable incorporating spatio-temporal components given predictors. In many applications, continuous variables are observed only as threshold-categorized data due to measurement constraints. For instance, ecological measurements often categorize sizes into intervals rather than recording exact values due to practical limita…

Packet-Level DDoS Data Augmentation Using Dual-Stream Temporal-Field Diffusion
Gongli Xi, Ye Tian, Yannan Hu, Yuchao Zhang, Yapeng Niu, Xiangyang Gong
https://arxiv.org/abs/2507.20115

Packet-Level DDoS Data Augmentation Using Dual-Stream Temporal-Field Diffusion
In response to Distributed Denial of Service (DDoS) attacks, recent research efforts increasingly rely on Machine Learning (ML)-based solutions, whose effectiveness largely depends on the quality of labeled training datasets. To address the scarcity of such datasets, data augmentation with synthetic traces is often employed. However, current synthetic trace generation methods struggle to capture the complex temporal patterns and spatial distributions exhibited in emerging DDoS attacks. This res…

sp_high_school: High school temporal contacts (2013)
These data sets correspond to the contacts and friendship relations between students in a high school in Marseilles, France, in December 2013, as measured through several techniques.
This network has 329 nodes and 1437 edges.
Tags: Social, Offline, Unweighted, Weighted, Temporal, Metadata

EXPO: Stable Reinforcement Learning with Expressive Policies
Perry Dong, Qiyang Li, Dorsa Sadigh, Chelsea Finn
https://arxiv.org/abs/2507.07986 https://arxiv.org/pdf/2507.07986 https://arxiv.org/html/2507.07986
arXiv:2507.07986v1 Announce Type: new
Abstract: We study the problem of training and fine-tuning expressive policies with online reinforcement learning (RL) given an offline dataset. Training expressive policy classes with online RL present a unique challenge of stable value maximization. Unlike simpler Gaussian policies commonly used in online RL, expressive policies like diffusion and flow-matching policies are parameterized by a long denoising chain, which hinders stable gradient propagation from actions to policy parameters when optimizing against some value function. Our key insight is that we can address stable value maximization by avoiding direct optimization over value with the expressive policy and instead construct an on-the-fly RL policy to maximize Q-value. We propose Expressive Policy Optimization (EXPO), a sample-efficient online RL algorithm that utilizes an on-the-fly policy to maximize value with two parameterized policies -- a larger expressive base policy trained with a stable imitation learning objective and a light-weight Gaussian edit policy that edits the actions sampled from the base policy toward a higher value distribution. The on-the-fly policy optimizes the actions from the base policy with the learned edit policy and chooses the value maximizing action from the base and edited actions for both sampling and temporal-difference (TD) backup. Our approach yields up to 2-3x improvement in sample efficiency on average over prior methods both in the setting of fine-tuning a pretrained policy given offline data and in leveraging offline data to train online.
toXiv_bot_toot

Signals as a First-Class Citizen When Querying Knowledge Graphs
Tobias Schwarzinger, Gernot Steindl, Thomas Fr\"uhwirth, Thomas Preindl, Konrad Diwold, Katrin Ehrenm\"uller, Fajar J. Ekaputra
https://arxiv.org/abs/2506.03826

Signals as a First-Class Citizen When Querying Knowledge Graphs
Cyber-Physical Systems (CPSs) tightly integrate computation with physical entities, often generating vast amounts of time series data from thousands of sensors. Although knowledge graphs offer a powerful means to contextualize these data, existing approaches to integrating knowledge graphs with time series data lack a concept to model the continuous temporal values inherent in CPSs. This gap can make expressing computations on the sensor data cumbersome. In this work, we propose the integration…

Parameterized Infinite-State Reactive Synthesis
Benedikt Maderbacher, Roderick Bloem
https://arxiv.org/abs/2508.00613 https://arxiv.org/pdf/2508.00613

Parameterized Infinite-State Reactive Synthesis
We propose a method to synthesize a parameterized infinite-state systems that can be instantiated for different parameter values. The specification is given in a parameterized temporal logic that allows for data variables as well as parameter variables that encode properties of the environment. Our synthesis method runs in a counterexample-guided loop consisting of four main steps: First, we use existing techniques to synthesize concrete systems for some small parameter instantiations. Second, …

Detailed Time Resolved Spectral and Temporal Investigations of SGR J1550-5418 Bursts Detected with Fermi/Gamma-ray Burst Monitor
Mustafa Demirer, Ersin G\"o\u{g}\"u\c{s}, Yuki Kaneko, \"Ozge Keskin, Sinem \c{S}a\c{s}maz, Shotaro Yamasaki
https://arxiv.org/abs/2506.04414

Detailed Time Resolved Spectral and Temporal Investigations of SGR J1550-5418 Bursts Detected with Fermi/Gamma-ray Burst Monitor
We have conducted a time-resolved spectral analysis of magnetar bursts originating from SGR J1550-5418. Our analysis utilizes a two-step methodology for temporal segmentation of the data. We first generated and fitted overlapping time segments. Subsequently, we obtained non-overlapping time segments with varying lengths based on their spectral evolution patterns, employing a machine learning algorithm called k-means clustering. For the fitting process, we employed three distinct models, namely …

An MLIR-based Compilation Framework for Control Flow Management on CGRAs
Yuxuan Wang, Cristian Tirelli, Giovanni Ansaloni, Laura Pozzi, David Atienza
https://arxiv.org/abs/2508.02167

An MLIR-based Compilation Framework for Control Flow Management on CGRAs
Coarse Grained Reconfigurable Arrays (CGRAs) present both high flexibility and efficiency, making them well-suited for the acceleration of intensive workloads. Nevertheless, a key barrier towards their widespread adoption is posed by CGRA compilation, which must cope with a multi-dimensional space spanning both the spatial and the temporal domains. Indeed, state-of-the-art compilers are limited in scope as they mostly deal with the data flow of applications, while having little or no support fo…

Holovibes: real-time ultrahigh-speed digital hologram rendering and short-time analysis
Marius Dubosc, Maxime Boy-Arnould, Jules Guillou, Titouan Gragnic, Arthur Courselle, Gustave Herv\'e, Alexis Pinson, Etienne Senigout, Bastien Gaulier, Simon Riou, Chlo\'e Magnier, No\'e Topeza, Oscar Morand, Thomas Xu, Samuel Goncalves, Edgar Delaporte, Adrien Langou, Paul Duhot, Julien Nicolle, Sacha Bellier, David Chemaly, Damien Didier, Philippe Bernet, Eliott Bouhana, Fabien Colmagr…

Holovibes: real-time ultrahigh-speed digital hologram rendering and short-time analysis
Real-time ultrahigh-speed rendering of digital holograms from high-bitrate interferogram streams demands robust parallel computing and efficient data handling with minimal latency. We present Holovibes, a high-performance software engine that enables real-time holographic image reconstruction and short-time analysis at unprecedented throughput. Holovibes integrates spatial demodulation techniques, such as Fresnel transformations and angular spectrum propagation, with temporal analysis methods i…

FindRec: Stein-Guided Entropic Flow for Multi-Modal Sequential Recommendation
Maolin Wang, Yutian Xiao, Binhao Wang, Sheng Zhang, Shanshan Ye, Wanyu Wang, Hongzhi Yin, Ruocheng Guo, Zenglin Xu
https://arxiv.org/abs/2507.04651

FindRec: Stein-Guided Entropic Flow for Multi-Modal Sequential Recommendation
Modern recommendation systems face significant challenges in processing multimodal sequential data, particularly in temporal dynamics modeling and information flow coordination. Traditional approaches struggle with distribution discrepancies between heterogeneous features and noise interference in multimodal signals. We propose \textbf{FindRec}~ (\textbf{F}lexible unified \textbf{in}formation \textbf{d}isentanglement for multi-modal sequential \textbf{Rec}ommendation), introducing a novel "info…

Investigating Timing-Based Information Leakage in Data Flow-Driven Real-Time Systems
Mohammad Fakhruddin Babar, Zain A. H. Hammadeh, Mohammad Hamad, Monowar Hasan
https://arxiv.org/abs/2506.01991

Investigating Timing-Based Information Leakage in Data Flow-Driven Real-Time Systems
Leaking information about the execution behavior of critical real-time tasks may lead to serious consequences, including violations of temporal constraints and even severe failures. We study information leakage for a special class of real-time tasks that have two execution modes, namely, typical execution (which invokes the majority of times) and critical execution (to tackle exceptional conditions). The data flow-driven applications inherit such a multimode execution model. In this paper, we i…

Practical considerations for Gaussian Process modeling for causal inference quasi-experimental studies with panel data
Sofia L. Vega, Rachel C. Nethery
https://arxiv.org/abs/2507.05128

Practical considerations for Gaussian Process modeling for causal inference quasi-experimental studies with panel data
Estimating causal effects in quasi-experiments with spatio-temporal panel data often requires adjusting for unmeasured confounding that varies across space and time. Gaussian Processes (GPs) offer a flexible, nonparametric modeling approach that can account for such complex dependencies through carefully chosen covariance kernels. In this paper, we provide a practical and interpretable framework for applying GPs to causal inference in panel data settings. We demonstrate how GPs generalize popul…

Chameleon: A MatMul-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data
Douwe den Blanken, Charlotte Frenkel
https://arxiv.org/abs/2505.24852

Chameleon: A MatMul-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data
On-device learning at the edge enables low-latency, private personalization with improved long-term robustness and reduced maintenance costs. Yet, achieving scalable, low-power end-to-end on-chip learning, especially from real-world sequential data with a limited number of examples, is an open challenge. Indeed, accelerators supporting error backpropagation optimize for learning performance at the expense of inference efficiency, while simplified learning algorithms often fail to reach acceptab…

USAD: An Unsupervised Data Augmentation Spatio-Temporal Attention Diffusion Network
Ying Yu, Hang Xiao, Siyao Li, Jiarui Li, Haotian Tang, Hanyu Liu, Chao Li
https://arxiv.org/abs/2507.02827

USAD: An Unsupervised Data Augmentation Spatio-Temporal Attention Diffusion Network
The primary objective of human activity recognition (HAR) is to infer ongoing human actions from sensor data, a task that finds broad applications in health monitoring, safety protection, and sports analysis. Despite proliferating research, HAR still faces key challenges, including the scarcity of labeled samples for rare activities, insufficient extraction of high-level features, and suboptimal model performance on lightweight devices. To address these issues, this paper proposes a comprehensi…

Interpretable Spatio-Temporal Features Extraction based Industrial Process Modeling and Monitoring by Soft Sensor
Qianchao Wang, Peng Sha, Leena Heistrene, Yuxuan Ding, Yaping Du
https://arxiv.org/abs/2506.00858

Interpretable Spatio-Temporal Features Extraction based Industrial Process Modeling and Monitoring by Soft Sensor
Data-driven soft sensors have been widely applied in complex industrial processes. However, the interpretable spatio-temporal features extraction by soft sensors remains a challenge. In this light, this work introduces a novel method termed spatio-temporal consistent and interpretable model (STCIM). First, temporal and spatial features are captured and aligned by a far topological spatio-temporal consistency extraction block. Then, the features are mapped into an interpretable latent space for …

Quantum generative modeling for financial time series with temporal correlations
David Dechant, Eliot Schwander, Lucas van Drooge, Charles Moussa, Diego Garlaschelli, Vedran Dunjko, Jordi Tura
https://arxiv.org/abs/2507.22035

Quantum generative modeling for financial time series with temporal correlations
Quantum generative adversarial networks (QGANs) have been investigated as a method for generating synthetic data with the goal of augmenting training data sets for neural networks. This is especially relevant for financial time series, since we only ever observe one realization of the process, namely the historical evolution of the market, which is further limited by data availability and the age of the market. However, for classical generative adversarial networks it has been shown that genera…

ZK-SERIES: Privacy-Preserving Authentication using Temporal Biometric Data
Daniel Reijsbergen, Eyasu Getahun Chekole, Howard Halim, Jianying Zhou
https://arxiv.org/abs/2506.19393 …

ZK-SERIES: Privacy-Preserving Authentication using Temporal Biometric Data
Biometric authentication relies on physiological or behavioral traits that are inherent to a user, making them difficult to lose, forge or forget. Biometric data with a temporal component enable the following authentication protocol: recent readings of the underlying biometrics are encoded as time series and compared to a set of base readings. If the distance between the new readings and the base readings falls within an acceptable threshold, then the user is successfully authenticated. Various…

Yule-Walker Estimation for Functional Time Series in Hilbert Space
Ying Niu, Yuwei Zhao, Zhao Chen, Christina Dan Wang
https://arxiv.org/abs/2506.05922 htt…

Yule-Walker Estimation for Functional Time Series in Hilbert Space
Recent advances in data collection technologies have led to the widespread availability of functional data observed over time, often exhibiting strong temporal dependence. However, existing methodologies typically assume independence across functions or impose restrictive low-order dependence structures, limiting their ability to capture the full dynamics of functional time series. To address this gap, we investigate higher-order functional autoregressive (FAR) models in Hilbert spaces, focusin…

ENMA: Tokenwise Autoregression for Generative Neural PDE Operators
Armand Kassa\"i Koupa\"i, Lise Le Boudec, Louis Serrano, Patrick Gallinari
https://arxiv.org/abs/2506.06158

ENMA: Tokenwise Autoregression for Generative Neural PDE Operators
Solving time-dependent parametric partial differential equations (PDEs) remains a fundamental challenge for neural solvers, particularly when generalizing across a wide range of physical parameters and dynamics. When data is uncertain or incomplete-as is often the case-a natural approach is to turn to generative models. We introduce ENMA, a generative neural operator designed to model spatio-temporal dynamics arising from physical phenomena. ENMA predicts future dynamics in a compressed latent …

sp_high_school: High school temporal contacts (2013)
These data sets correspond to the contacts and friendship relations between students in a high school in Marseilles, France, in December 2013, as measured through several techniques.
This network has 329 nodes and 188508 edges.
Tags: Social, Offline, Unweighted, Weighted, Temporal, Metadata

This https://arxiv.org/abs/2506.01991 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDC_…

Investigating Timing-Based Information Leakage in Data Flow-Driven Real-Time Systems
Leaking information about the execution behavior of critical real-time tasks may lead to serious consequences, including violations of temporal constraints and even severe failures. We study information leakage for a special class of real-time tasks that have two execution modes, namely, typical execution (which invokes the majority of times) and critical execution (to tackle exceptional conditions). The data flow-driven applications inherit such a multimode execution model. In this paper, we i…

Towards Explainable Sequential Learning
Giacomo Bergami, Emma Packer, Kirsty Scott, Silvia Del Din
https://arxiv.org/abs/2505.23624 https://

Towards Explainable Sequential Learning
This paper offers a hybrid explainable temporal data processing pipeline, DataFul Explainable MultivariatE coRrelatIonal Temporal Artificial inTElligence (EMeriTAte+DF), bridging numerical-driven temporal data classification with an event-based one through verified artificial intelligence principles, enabling human-explainable results. This was possible through a preliminary a posteriori explainable phase describing the numerical input data in terms of concurrent constituents with numerical pay…

Dynamic mapping from static labels: remote sensing dynamic sample generation with temporal-spectral embedding
Shuai Yuan, Shuang Chen, Tianwu Lin, Jie Wang, Peng Gong
https://arxiv.org/abs/2506.02574

Dynamic mapping from static labels: remote sensing dynamic sample generation with temporal-spectral embedding
Accurate remote sensing geographic mapping depends heavily on representative and timely sample data. However, rapid changes in land surface dynamics necessitate frequent updates, quickly rendering previously collected samples obsolete and imposing significant labor demands for continuous manual updates. In this study, we aim to address this problem by dynamic sample generation using existing single-date static labeled samples. We introduce TasGen, a two-stage automated framework to automaticall…

sp_high_school: High school temporal contacts (2013)
These data sets correspond to the contacts and friendship relations between students in a high school in Marseilles, France, in December 2013, as measured through several techniques.
This network has 329 nodes and 502 edges.
Tags: Social, Offline, Unweighted, Weighted, Temporal, Metadata

DP-RTFL: Differentially Private Resilient Temporal Federated Learning for Trustworthy AI in Regulated Industries
Abhijit Talluri
https://arxiv.org/abs/2505.23813

DP-RTFL: Differentially Private Resilient Temporal Federated Learning for Trustworthy AI in Regulated Industries
Federated Learning (FL) has emerged as a critical paradigm for enabling privacy-preserving machine learning, particularly in regulated sectors such as finance and healthcare. However, standard FL strategies often encounter significant operational challenges related to fault tolerance, system resilience against concurrent client and server failures, and the provision of robust, verifiable privacy guarantees essential for handling sensitive data. These deficiencies can lead to training disruption…

Integrating Expert Knowledge and Recursive Bayesian Inference: A Framework for Spatial and Spatio-Temporal Data Challenges
Mario Figueira, David Conesa, Antonio L\'opez-Qu\'ilez, H{\aa}vard Rue
https://arxiv.org/abs/2506.00221

Integrating Expert Knowledge and Recursive Bayesian Inference: A Framework for Spatial and Spatio-Temporal Data Challenges
Expert elicitation is a critical approach for addressing data scarcity across various disciplines. But moreover, it can also complement big data analytics by mitigating the limitations of observational data, such as incompleteness and reliability issues, thereby enhancing model estimates through the integration of disparate or conflicting data sources. The paper also outlines various strategies for integrating prior information within the Integrated Nested Laplace Approximation method and propo…

Continued Photometric Monitoring Supports Long-Term Dynamical Evolution in the Young Binary Star-Disk System KH 15D
Luke Lamitina (California Institute of Technology), Lynne Hillenbrand (California Institute of Technology), Michael Poon (University of Toronto)
https://arxiv.org/abs/2506.04914

Continued Photometric Monitoring Supports Long-Term Dynamical Evolution in the Young Binary Star-Disk System KH 15D
We present photometric time series data spanning 2018-2024 that show the effects of temporal dynamics in the binary system KH 15D, a member of the NGC 2264 star forming region. This source exhibits complex eclipsing behavior due to a precessing circumbinary disk or ring that is slightly inclined relative to the orbital plane of the binary. Using g-band and r-band observations from the Zwicky Transient Facility (ZTF) over seven observing seasons, we follow the evolution of the KH 15D lightcurve …

A Modular Multitask Reasoning Framework Integrating Spatio-temporal Models and LLMs
Kethmi Hirushini Hettige, Jiahao Ji, Cheng Long, Shili Xiang, Gao Cong, Jingyuan Wang
https://arxiv.org/abs/2506.20073

A Modular Multitask Reasoning Framework Integrating Spatio-temporal Models and LLMs
Spatio-temporal data mining plays a pivotal role in informed decision making across diverse domains. However, existing models are often restricted to narrow tasks, lacking the capacity for multi-task inference and complex long-form reasoning that require generation of in-depth, explanatory outputs. These limitations restrict their applicability to real-world, multi-faceted decision scenarios. In this work, we introduce STReason, a novel framework that integrates the reasoning strengths of large…

Improved Prefetching Techniques for Linked Data Structures
Nikola Vuk Maruszewski
https://arxiv.org/abs/2505.21669 https://arxiv.org/…

Improved Prefetching Techniques for Linked Data Structures
With ever-increasing main memory stall times, we need novel techniques to reduce effective memory access latencies. Prefetching has been shown to be an effective solution, especially with contiguous data structures that follow the traditional principles of spatial and temporal locality. However, on linked data structures$-$made up of many nodes linked together with pointers$-$typical prefetchers struggle, failing to predict accesses as elements are arbitrarily scattered throughout memory and ac…

Data-Driven Stochastic Control via Non-i.i.d. Trajectories: Foundations and Guarantees
Abolfazl Lavaei
https://arxiv.org/abs/2507.23280 https://arxiv.org/p…

Data-Driven Stochastic Control via Non-i.i.d. Trajectories: Foundations and Guarantees
This work establishes a crucial step toward advancing data-driven trajectory-based methods for stochastic systems with unknown mathematical dynamics. In contrast to scenario-based approaches that rely on independent and identically distributed (i.i.d.) trajectories, this work develops a data-driven framework where each trajectory is gathered over a finite horizon and exhibits temporal dependence-referred to as a non-i.i.d. trajectory. To ensure safety of dynamical systems using such trajectorie…

sp_colocation: Social co-locations (2018)
Network of colocations between peoople, based on the information on which RFID readers received information from the RFID tags. Namely, we define two individuals to be in co-presence if the same exact set of readers have received signals from both individuals during a 20s time window.
This network has 100 nodes and 394247 edges.
Tags: Social, Offline, Unweighted, Weighted, Temporal, Metadata

LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences
Ao Liang, Youquan Liu, Yu Yang, Dongyue Lu, Linfeng Li, Lingdong Kong, Huaici Zhao, Wei Tsang Ooi
https://arxiv.org/abs/2508.03692

LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences
Generative world models have become essential data engines for autonomous driving, yet most existing efforts focus on videos or occupancy grids, overlooking the unique LiDAR properties. Extending LiDAR generation to dynamic 4D world modeling presents challenges in controllability, temporal coherence, and evaluation standardization. To this end, we present LiDARCrafter, a unified framework for 4D LiDAR generation and editing. Given free-form natural language inputs, we parse instructions into eg…

Two-stage MCMC for Fast Bayesian Inference of Large Spatio-temporal Ordinal Data, with Application to US Drought
Staci Hepler, Rob Erhardt
https://arxiv.org/abs/2505.24594

Two-stage MCMC for Fast Bayesian Inference of Large Spatio-temporal Ordinal Data, with Application to US Drought
High dimensional space-time data pose known computational challenges when fitting spatio-temporal models. Such data show dependence across several dimensions of space as well as in time, and can easily involve hundreds of thousands of observations. Many spatio-temporal models result in a dependence structure across all observations and can be fit only at a substantial computational cost, arising from dense matrix inversion, high dimensional parameter spaces, poor mixing in Markov Chain Monte Ca…

route_views: Route Views AS graphs (1997-1998)
733 daily network snapshots denoting BGP traffic among autonomous systems (ASs) on the Internet, from the Oregon Route Views Project, spanning 8 November 1997 to 2 January 2000. Data collected by NLANR/MOAT.
This network has 3677 nodes and 7280 edges.
Tags: Technological, Communication, Unweighted, Temporal

This https://arxiv.org/abs/2505.19193 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Interpretable Graph Learning Over Sets of Temporally-Sparse Data
Real-world medical data often includes measurements from multiple signals that are collected at irregular and asynchronous time intervals. For example, different types of blood tests can be measured at different times and frequencies, resulting in fragmented and unevenly scattered temporal data. Similar issues of irregular sampling of different attributes occur in other domains, such as monitoring of large systems using event log files or the spread of fake news on social networks. Effectively …

KGMark: A Diffusion Watermark for Knowledge Graphs
Hongrui Peng, Haolang Lu, Yuanlong Yu, Weiye Fu, Kun Wang, Guoshun Nan
https://arxiv.org/abs/2505.23873 …

KGMark: A Diffusion Watermark for Knowledge Graphs
Knowledge graphs (KGs) are ubiquitous in numerous real-world applications, and watermarking facilitates protecting intellectual property and preventing potential harm from AI-generated content. Existing watermarking methods mainly focus on static plain text or image data, while they can hardly be applied to dynamic graphs due to spatial and temporal variations of structured data. This motivates us to propose KGMARK, the first graph watermarking framework that aims to generate robust, detectable…

Bayesian nonparametric clustering for spatio-temporal data, with an application to air pollution
Luca Aiello, Raffaele Argiento, Sirio Legramanti, Lucia Paci
https://arxiv.org/abs/2505.24694

Bayesian nonparametric clustering for spatio-temporal data, with an application to air pollution
Air pollution is a major global health hazard, with fine particulate matter (PM10) linked to severe respiratory and cardiovascular diseases. Hence, analyzing and clustering spatio-temporal air quality data is crucial for understanding pollution dynamics and guiding policy interventions. This work provides a review of Bayesian nonparametric clustering methods, with a particular focus on their application to spatio-temporal data, which are ubiquitous in environmental sciences. We first introduce …

An Intermittent Model for the $1/f$ Spectrum in the Pristine Solar Wind
Maia Brodiano, Fouad Sahraoui, Davide Manzini, Lina Z. Hadid, Facundo Pugliese, Pablo Dmitruk, Nahuel Andr\'es
https://arxiv.org/abs/2506.04366

An Intermittent Model for the $1/f$ Spectrum in the Pristine Solar Wind
We present a statistical, observational study of the $1/f$ range of solar wind turbulence, where $f$ denotes frequency, using in situ data from the Parker Solar Probe (PSP). We compute the energy cascade rate using the third order law of incompressible magnetohydrodynamic (MHD) turbulence, incorporating expansion terms to account for solar wind dynamics. Our results reveal a $1/τ$ dependence of the energy cascade rate, where $τ$ is the temporal lag, within the $1/f$ range, in contrast to the …

sp_high_school: High school temporal contacts (2013)
These data sets correspond to the contacts and friendship relations between students in a high school in Marseilles, France, in December 2013, as measured through several techniques.
This network has 329 nodes and 1437 edges.
Tags: Social, Offline, Unweighted, Weighted, Temporal, Metadata

Profile-Guided Temporal Prefetching
Mengming Li, Qijun Zhang, Yichuan Gao, Wenji Fang, Yao Lu, Yongqing Ren, Zhiyao Xie
https://arxiv.org/abs/2506.15985 ht…

Profile-Guided Temporal Prefetching
Temporal prefetching shows promise for handling irregular memory access patterns, which are common in data-dependent and pointer-based data structures. Recent studies introduced on-chip metadata storage to reduce the memory traffic caused by accessing metadata from off-chip DRAM. However, existing prefetching schemes struggle to efficiently utilize the limited on-chip storage. An alternative solution, software indirect access prefetching, remains ineffective for optimizing temporal prefetching.…

G-SEED: A Spatio-temporal Encoding Framework for Forest and Grassland Data Based on GeoSOT
Xuan Ouyang, Xinwen Yu, Yan Chen, Guang Deng, Xuanxin Liu
https://arxiv.org/abs/2506.18094

G-SEED: A Spatio-temporal Encoding Framework for Forest and Grassland Data Based on GeoSOT
In recent years, the rapid development of remote sensing, Unmanned Aerial Vehicles, and IoT technologies has led to an explosive growth in spatio-temporal forest and grassland data, which are increasingly multimodal, heterogeneous, and subject to continuous updates. However, existing Geographic Information Systems (GIS)-based systems struggle to integrate and manage of such large-scale and diverse data sources. To address these challenges, this paper proposes G-SEED (GeoSOT-based Scalable Encod…

This https://arxiv.org/abs/2505.10930 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models
Auto-regressive partial differential equation (PDE) foundation models have shown great potential in handling time-dependent data. However, these models suffer from the shortcut problem deeply rooted in auto-regressive prediction, causing error accumulation. The challenge becomes particularly evident for out-of-distribution data, as the pretraining performance may approach random model initialization for downstream tasks with long-term dynamics. To deal with this problem, we propose physics-info…

sp_colocation: Social co-locations (2018)
Network of colocations between peoople, based on the information on which RFID readers received information from the RFID tags. Namely, we define two individuals to be in co-presence if the same exact set of readers have received signals from both individuals during a 20s time window.
This network has 100 nodes and 394247 edges.
Tags: Social, Offline, Unweighted, Weighted, Temporal, Metadata

route_views: Route Views AS graphs (1997-1998)
733 daily network snapshots denoting BGP traffic among autonomous systems (ASs) on the Internet, from the Oregon Route Views Project, spanning 8 November 1997 to 2 January 2000. Data collected by NLANR/MOAT.
This network has 3210 nodes and 6157 edges.
Tags: Technological, Communication, Unweighted, Temporal

Clustering-based accelerometer measures to model relationships between physical activity and key outcomes
Hyatt Moore IV, Thomas N. Robinson, Alexandria Jensen, Fatma Gunturkun, K. Farish Haydel, Kristopher I Kapphahn, Manisha Desai
https://arxiv.org/abs/2507.00484

Clustering-based accelerometer measures to model relationships between physical activity and key outcomes
Accelerometers produce enormous amounts of data. Research that incorporates such data often involves a derived summary metric to describe physical activity. Traditional metrics have often ignored the temporal nature of the data. We build on previous work that applies unsupervised machine learning techniques to describe physical activity patterns over time. Specifically, we evaluate a summary measure of accelerometer data derived from unsupervised clustering in a regression framework through com…

sp_baboons: Baboons' interactions (2020)
Network of interactions between a group of 20 Guinea baboons living in an enclosure of a Primate Center in France, between June 13th 2019 and July 10th 2019. The data set contains observational and wearable sensors data.
This network has 13 nodes and 63095 edges.
Tags: Social, Animal, Offline, Unweighted, Weighted, Temporal, Metadata

This https://arxiv.org/abs/2406.04655 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

Bayesian Inference for Spatial-Temporal Non-Gaussian Data Using Predictive Stacking
Analysing non-Gaussian spatial-temporal data requires introducing spatial dependence in generalised linear models through the link function of an exponential family distribution. Unlike in Gaussian likelihoods, inference is considerably encumbered by the inability to analytically integrate out the random effects and reduce the dimension of the parameter space. Iterative estimation algorithms struggle to converge due to the presence of weakly identified parameters. We devise Bayesian inference u…

sp_baboons: Baboons' interactions (2020)
Network of interactions between a group of 20 Guinea baboons living in an enclosure of a Primate Center in France, between June 13th 2019 and July 10th 2019. The data set contains observational and wearable sensors data.
This network has 13 nodes and 63095 edges.
Tags: Social, Animal, Offline, Unweighted, Weighted, Temporal, Metadata

sp_baboons: Baboons' interactions (2020)
Network of interactions between a group of 20 Guinea baboons living in an enclosure of a Primate Center in France, between June 13th 2019 and July 10th 2019. The data set contains observational and wearable sensors data.
This network has 13 nodes and 63095 edges.
Tags: Social, Animal, Offline, Unweighted, Weighted, Temporal, Metadata

sp_baboons: Baboons' interactions (2020)
Network of interactions between a group of 20 Guinea baboons living in an enclosure of a Primate Center in France, between June 13th 2019 and July 10th 2019. The data set contains observational and wearable sensors data.
This network has 13 nodes and 63095 edges.
Tags: Social, Animal, Offline, Unweighted, Weighted, Temporal, Metadata

Bayesian Inference for Spatially-Temporally Misaligned Data Using Predictive Stacking
Soumyakanti Pan, Sudipto Banerjee
https://arxiv.org/abs/2505.24397 ht…

Bayesian Inference for Spatially-Temporally Misaligned Data Using Predictive Stacking
Air pollution remains a major environmental risk factor that is often associated with adverse health outcomes. However, quantifying and evaluating its effects on human health is challenging due to the complex nature of exposure data. Recent technological advances have led to the collection of various indicators of air pollution at increasingly high spatial-temporal resolutions (e.g., daily averages of pollutant levels at spatial locations referenced by latitude-longitude). However, health outco…

eu_procurements_alt: EU national procurement networks (2008-2016)
These 234 networks represent the annual national public procurement markets of 26 European countries from 2008-2016, inclusive. Data is sourced from Tenders Electronic Daily (TED), the official procurement portal of the European Union.
This network has 4447 nodes and 6713 edges.
Tags: Economic, Commerce, Weighted, Temporal

Distributed lag non-linear models with Laplacian-P-splines for analysis of spatially structured time series
Sara Rutten, Bryan Sumalinab, Oswaldo Gressani, Thomas Neyens, Elisa Duarte, Niel Hens, Christel Faes
https://arxiv.org/abs/2506.04814

Distributed lag non-linear models with Laplacian-P-splines for analysis of spatially structured time series
Distributed lag non-linear models (DLNM) have gained popularity for modeling nonlinear lagged relationships between exposures and outcomes. When applied to spatially referenced data, these models must account for spatial dependence, a challenge that has yet to be thoroughly explored within the penalized DLNM framework. This gap is mainly due to the complex model structure and high computational demands, particularly when dealing with large spatio-temporal datasets. To address this, we propose a…

eu_procurements_alt: EU national procurement networks (2008-2016)
These 234 networks represent the annual national public procurement markets of 26 European countries from 2008-2016, inclusive. Data is sourced from Tenders Electronic Daily (TED), the official procurement portal of the European Union.
This network has 2817 nodes and 2817 edges.
Tags: Economic, Commerce, Weighted, Temporal

eu_procurements_alt: EU national procurement networks (2008-2016)
These 234 networks represent the annual national public procurement markets of 26 European countries from 2008-2016, inclusive. Data is sourced from Tenders Electronic Daily (TED), the official procurement portal of the European Union.
This network has 1770 nodes and 3997 edges.
Tags: Economic, Commerce, Weighted, Temporal