Showing preview only (430K chars total). Download the full file or copy to clipboard to get everything.
Repository: zezhishao/DailyArXiv
Branch: master
Commit: 55c8c5e65eae
Files: 6
Total size: 418.6 KB
Directory structure:
gitextract_uotra79q/
├── .github/
│ ├── ISSUE_TEMPLATE.md
│ └── workflows/
│ └── update.yaml
├── .gitignore
├── README.md
├── main.py
└── utils.py
================================================
FILE CONTENTS
================================================
================================================
FILE: .github/ISSUE_TEMPLATE.md
================================================
---
title: Latest 15 Papers - April 20, 2026
labels: documentation
---
**Please check the [Github](https://github.com/zezhishao/MTS_Daily_ArXiv) page for a better reading experience and more papers.**
## Time Series
| **Title** | **Date** | **Comment** |
| --- | --- | --- |
| **[On the robustness of Mann-Kendall tests used to forecast critical transitions](https://arxiv.org/abs/2604.15230v1)** | 2026-04-16 | <details><summary>26 pa...</summary><p>26 pages including appendices, 10 figures, 2 tables</p></details> |
| **[Parameter estimation for land-surface models using Neural Physics](https://arxiv.org/abs/2505.02979v3)** | 2026-04-16 | <details><summary>18 pa...</summary><p>18 pages, 5 figures, 3 tables</p></details> |
| **[TempusBench: An Evaluation Framework for Time-Series Forecasting](https://arxiv.org/abs/2604.11529v2)** | 2026-04-16 | |
| **[Time-RA: Towards Time Series Reasoning for Anomaly Diagnosis with LLM Feedback](https://arxiv.org/abs/2507.15066v5)** | 2026-04-16 | <details><summary>ACL 2...</summary><p>ACL 2026 Findings. 27 pages, 11 figures, 15 tables. Code and dataset are publicly available</p></details> |
| **[MambaSL: Exploring Single-Layer Mamba for Time Series Classification](https://arxiv.org/abs/2604.15174v1)** | 2026-04-16 | <details><summary>accep...</summary><p>accepted at ICLR 2026</p></details> |
| **[Assessing the Potential of Masked Autoencoder Foundation Models in Predicting Downhole Metrics from Surface Drilling Data](https://arxiv.org/abs/2604.15169v1)** | 2026-04-16 | |
| **[Universal hidden monotonic trend estimation with contrastive learning](https://arxiv.org/abs/2210.09817v3)** | 2026-04-16 | |
| **[Logo-LLM: Local and Global Modeling with Large Language Models for Time Series Forecasting](https://arxiv.org/abs/2505.11017v2)** | 2026-04-16 | |
| **[Assessing the Performance-Efficiency Trade-off of Foundation Models in Probabilistic Electricity Price Forecasting](https://arxiv.org/abs/2604.14739v1)** | 2026-04-16 | <details><summary>Submi...</summary><p>Submitted to the 7th International Workshop on Energy Data and Analytics (EDA), held in conjunction with ACM e-Energy 2026</p></details> |
| **[From Time Series to State: Situation-Aware Modeling for Air Traffic Flow Prediction](https://arxiv.org/abs/2604.11198v3)** | 2026-04-16 | <details><summary>There...</summary><p>There are issues with the authors of the paper I submitted, as well as problems with the content of the article, so it needs to be withdrawn. Thank you for your understanding</p></details> |
| **[CSRA: Controlled Spectral Residual Augmentation for Robust Sepsis Prediction](https://arxiv.org/abs/2604.14532v1)** | 2026-04-16 | |
| **[AIBuildAI: An AI Agent for Automatically Building AI Models](https://arxiv.org/abs/2604.14455v1)** | 2026-04-15 | |
| **[Frame forecasting in cine MRI using the PCA respiratory motion model: comparing recurrent neural networks trained online and transformers](https://arxiv.org/abs/2410.05882v3)** | 2026-04-15 | <details><summary>43 pa...</summary><p>43 pages, 19 figures. Revised version with minor corrections and improved figures and language. Accepted for publication in Computerized Medical Imaging and Graphics</p></details> |
| **[Unsupervised Anomaly Detection in Process-Complex Industrial Time Series: A Real-World Case Study](https://arxiv.org/abs/2604.13928v1)** | 2026-04-15 | |
| **[ASTER: Latent Pseudo-Anomaly Generation for Unsupervised Time-Series Anomaly Detection](https://arxiv.org/abs/2604.13924v1)** | 2026-04-15 | |
## Trajectory
| **Title** | **Date** | **Comment** |
| --- | --- | --- |
| **[LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories](https://arxiv.org/abs/2604.15311v1)** | 2026-04-16 | <details><summary>Accep...</summary><p>Accepted by CVPR 2026. Project page: https://rockeycoss.github.io/leapalign/</p></details> |
| **[OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis](https://arxiv.org/abs/2604.15093v1)** | 2026-04-16 | Work in progress |
| **[Trajectory Planning for a Multi-UAV Rigid-Payload Cascaded Transportation System Based on Enhanced Tube-RRT*](https://arxiv.org/abs/2604.15074v1)** | 2026-04-16 | <details><summary>15 pa...</summary><p>15 pages, 7 figures. Under review at IEEE Transactions on Aerospace and Electronic Systems (TAES). This work has been submitted to the IEEE for possible publication</p></details> |
| **[Predicting Power-System Dynamic Trajectories with Foundation Models](https://arxiv.org/abs/2604.14991v1)** | 2026-04-16 | 10 pages |
| **[Momentum-constrained Hybrid Heuristic Trajectory Optimization Framework with Residual-enhanced DRL for Visually Impaired Scenarios](https://arxiv.org/abs/2604.14986v1)** | 2026-04-16 | <details><summary>24 pa...</summary><p>24 pages, 14 figures. arXiv admin note: text overlap with arXiv:2509.15582</p></details> |
| **[Reward-Aware Trajectory Shaping for Few-step Visual Generation](https://arxiv.org/abs/2604.14910v1)** | 2026-04-16 | |
| **[Benchmarks for Trajectory Safety Evaluation and Diagnosis in OpenClaw and Codex: ATBench-Claw and ATBench-CodeX](https://arxiv.org/abs/2604.14858v1)** | 2026-04-16 | 18 pages, 3 figures |
| **[Trajectory-based actuator identification via differentiable simulation](https://arxiv.org/abs/2604.10351v2)** | 2026-04-16 | |
| **[Tora3: Trajectory-Guided Audio-Video Generation with Physical Coherence](https://arxiv.org/abs/2604.09057v2)** | 2026-04-16 | <details><summary>12 pa...</summary><p>12 pages, 5 tables, 5 figures</p></details> |
| **[FinTrace: Holistic Trajectory-Level Evaluation of LLM Tool Calling for Long-Horizon Financial Tasks](https://arxiv.org/abs/2604.10015v2)** | 2026-04-15 | |
| **[Staying on Track: Efficient Trajectory Discovery with Adaptive Batch Sampling](https://arxiv.org/abs/2510.18099v2)** | 2026-04-15 | |
| **[HINTBench: Horizon-agent Intrinsic Non-attack Trajectory Benchmark](https://arxiv.org/abs/2604.13954v1)** | 2026-04-15 | |
| **[Bayesian Joint Modelling of Longitudinal Creatinine Trajectories in Children with Auto-Immune Disorders to Predict Paediatric Kidney Disease Risk in a Single Centre Study](https://arxiv.org/abs/2604.12740v1)** | 2026-04-14 | |
| **[FeaXDrive: Feasibility-aware Trajectory-Centric Diffusion Planning for End-to-End Autonomous Driving](https://arxiv.org/abs/2604.12656v1)** | 2026-04-14 | 21 pages, 6 figures |
| **[SparseWorld-TC: Trajectory-Conditioned Sparse Occupancy World Model](https://arxiv.org/abs/2511.22039v3)** | 2026-04-14 | <details><summary>Accep...</summary><p>Accepted by CVPR2026 as an oral</p></details> |
## Graph Neural Networks
| **Title** | **Date** | **Comment** |
| --- | --- | --- |
| **[How Embeddings Shape Graph Neural Networks: Classical vs Quantum-Oriented Node Representations](https://arxiv.org/abs/2604.15273v1)** | 2026-04-16 | <details><summary>6 pag...</summary><p>6 pages. Accepted at IJCNN 2026</p></details> |
| **[Sampling Transferable Graph Neural Networks with Limited Graph Information](https://arxiv.org/abs/2410.16593v6)** | 2026-04-16 | <details><summary>Submi...</summary><p>Submitted to IEEE TSP</p></details> |
| **[Beyond the Laplacian: Doubly Stochastic Matrices for Graph Neural Networks](https://arxiv.org/abs/2604.15069v1)** | 2026-04-16 | |
| **[Adaptive Canonicalization with Application to Invariant Anisotropic Geometric Networks](https://arxiv.org/abs/2509.24886v3)** | 2026-04-16 | |
| **[Dense Neural Networks are not Universal Approximators](https://arxiv.org/abs/2602.07618v3)** | 2026-04-16 | |
| **[Using deep learning to construct stochastic local search SAT solvers with performance bounds](https://arxiv.org/abs/2309.11452v3)** | 2026-04-16 | <details><summary>24 pa...</summary><p>24 pages, significantly updated version with new datasets and experiments. Code available at https://github.com/porscheofficial/sls_sat_solving_with_deep_learning. Accepted for publication in Machine Learning: Science and Technology 7 (2026) 025057</p></details> |
| **[Leveraging graph neural networks and mobility data for COVID-19 forecasting](https://arxiv.org/abs/2501.11711v2)** | 2026-04-16 | |
| **[PUFFIN: Protein Unit Discovery with Functional Supervision](https://arxiv.org/abs/2604.14796v1)** | 2026-04-16 | <details><summary>21 pa...</summary><p>21 pages, 9 figures, to appear in ISMB 2026 proceedings</p></details> |
| **[Graph-Based Alternatives to LLMs for Human Simulation](https://arxiv.org/abs/2511.02135v2)** | 2026-04-16 | <details><summary>Confe...</summary><p>Conference: ACL 2026 Long Main Code: https://github.com/schang-lab/gems</p></details> |
| **[CPGRec+: A Balance-oriented Framework for Personalized Video Game Recommendations](https://arxiv.org/abs/2604.14586v1)** | 2026-04-16 | <details><summary>Publi...</summary><p>Published in ACM Transactions on Information Systems (TOIS). 43 pages, 9 figures</p></details> |
| **[Behavior-Aware Dual-Channel Preference Learning for Heterogeneous Sequential Recommendation](https://arxiv.org/abs/2604.14581v1)** | 2026-04-16 | |
| **[Unsupervised Learning of Local Updates for Maximum Independent Set in Dynamic Graphs](https://arxiv.org/abs/2505.13754v3)** | 2026-04-15 | <details><summary>10 pa...</summary><p>10 pages, 3 figures, 1 table, 3 algorithms. To appear at IJCNN 2026</p></details> |
| **[ID and Graph View Contrastive Learning with Multi-View Attention Fusion for Sequential Recommendation](https://arxiv.org/abs/2604.14114v1)** | 2026-04-15 | |
| **[Log-based vs Graph-based Approaches to Fault Diagnosis](https://arxiv.org/abs/2604.14019v1)** | 2026-04-15 | <details><summary>8 pag...</summary><p>8 pages, 7 figures, student project</p></details> |
| **[Leveraging LLM-GNN Integration for Open-World Question Answering over Knowledge Graphs](https://arxiv.org/abs/2604.13979v1)** | 2026-04-15 | <details><summary>18 pa...</summary><p>18 pages,6 figures,10 tables. https://aclanthology.org/2026.eacl-long.26/</p></details> |
================================================
FILE: .github/workflows/update.yaml
================================================
name: Update
on:
label:
types:
- created # for test
schedule:
- cron: '30 16 * * 0-4' # 00:30 Beijing time every Monday to Friday
permissions:
contents: write
issues: write
jobs:
update_daily_papers:
runs-on: ubuntu-latest
steps:
- name: Checkout repository
uses: actions/checkout@v3
- name: Set up Python
uses: actions/setup-python@v4
with:
python-version: '3.9'
- name: Install dependencies
run: pip install -r requirements.txt
- name: Update papers
run: |
python main.py
- name: Commit and push changes
uses: github-actions-x/commit@v2.9
with:
github-token: ${{ secrets.GITHUB_TOKEN }}
push-branch: 'master'
commit-message: '✏️ Update papers automatically.'
force-add: 'true'
files: README.md .github/ISSUE_TEMPLATE.md
name: Zezhishao
email: 864453277@qq.com
- name: Create an issue to notify
uses: JasonEtco/create-an-issue@v2
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
================================================
FILE: .gitignore
================================================
# dir
__pycache__/
.vscode/
# file
*.npz
*.npy
*.csv
*.pkl
*.h5
*.pt
core*
*.p
*.pickle
*.pyc
*.txt
*.py[cod]
*$py.class
# C extensions
# *.so
# Distribution / packaging
.Python
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
share/python-wheels/
*.egg-info/
.installed.cfg
*.egg
MANIFEST
# PyInstaller
# Usually these files are written by a python script from a template
# before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec
# Installer logs
pip-log.txt
pip-delete-this-directory.txt
# Unit test / coverage reports
htmlcov/
.tox/
.nox/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*.cover
*.py,cover
.hypothesis/
.pytest_cache/
cover/
# Translations
*.mo
*.pot
# Django stuff:
*.log
local_settings.py
db.sqlite3
db.sqlite3-journal
# Flask stuff:
instance/
.webassets-cache
# Scrapy stuff:
.scrapy
# Sphinx documentation
docs/_build/
# PyBuilder
.pybuilder/
target/
# Jupyter Notebook
.ipynb_checkpoints
# IPython
profile_default/
ipython_config.py
# pyenv
# For a library or package, you might want to ignore these files since the code is
# intended to run in multiple environments; otherwise, check them in:
# .python-version
# pipenv
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
# However, in case of collaboration, if having platform-specific dependencies or dependencies
# having no cross-platform support, pipenv may install dependencies that don't work, or not
# install all needed dependencies.
#Pipfile.lock
# poetry
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
# This is especially recommended for binary packages to ensure reproducibility, and is more
# commonly ignored for libraries.
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
#poetry.lock
# pdm
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
#pdm.lock
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
# in version control.
# https://pdm.fming.dev/#use-with-ide
.pdm.toml
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
__pypackages__/
# Celery stuff
celerybeat-schedule
celerybeat.pid
# SageMath parsed files
*.sage.py
# Environments
.env
.venv
env/
venv/
ENV/
env.bak/
venv.bak/
# Spyder project settings
.spyderproject
.spyproject
# Rope project settings
.ropeproject
# mkdocs documentation
/site
# mypy
.mypy_cache/
.dmypy.json
dmypy.json
# Pyre type checker
.pyre/
# pytype static type analyzer
.pytype/
# Cython debug symbols
cython_debug/
# PyCharm
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
# and can be added to the global gitignore or merged into this file. For a more nuclear
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
================================================
FILE: README.md
================================================
# Daily Papers
The project automatically fetches the latest papers from arXiv based on keywords.
The subheadings in the README file represent the search keywords.
Only the most recent articles for each keyword are retained, up to a maximum of 100 papers.
You can click the 'Watch' button to receive daily email notifications.
Last update: 2026-04-20
## Time Series
| **Title** | **Date** | **Abstract** | **Comment** |
| --- | --- | --- | --- |
| **[On the robustness of Mann-Kendall tests used to forecast critical transitions](https://arxiv.org/abs/2604.15230v1)** | 2026-04-16 | <details><summary>Show</summary><p>Non-parametric approaches to test for trends in time series make use of the Mann-Kendall statistic. Based on asymptotic arguments, these tests assume that its distribution follows a Gaussian distribution, even for autocorrelated time series. Recent results on the lack of validity of this assumption urge a robustness analysis of these approaches. While the issue is relevant across a wide range of applications, we illustrate it here in the context of detecting early warning signals (EWS) of critical transitions, which are used across a variety of research domains, and where commonly applied methods generate autocorrelation. We present a broad analysis, covering all types of critical transitions commonly investigated in EWS studies. We compare empirical distributions of the Mann-Kendall statistic computed from classical EWS indicators preceding critical transitions to the theoretical distributions hypothesized by Mann-Kendall tests. We detect mismatches leading to inflated type I error rates, which would routinely lead to announcing a critical transition while it is not occurring. In contrast to a recent recommendation, we conclude that the use of Mann-Kendall tests for trend detection in the context of forecasting critical transitions should be avoided. We point out several alternative methods available instead.</p></details> | <details><summary>26 pa...</summary><p>26 pages including appendices, 10 figures, 2 tables</p></details> |
| **[Parameter estimation for land-surface models using Neural Physics](https://arxiv.org/abs/2505.02979v3)** | 2026-04-16 | <details><summary>Show</summary><p>We propose a novel inverse-modelling approach which estimates the parameters of a simple land-surface model (LSM) by assimilating data into a differentiable physics-based forward model. The governing equations are expressed within a machine-learning framework using the Neural Physics approach, allowing direct gradient-based optimisation of time-dependent parameters without the need to derive and maintain adjoint formulations. The model parameters are updated by minimising the mismatch between model predictions and synthetic or observational data. Although differentiability is achieved through functionality in machine-learning libraries, the forward model itself remains entirely physics-based and no part of either the forward model or the parameter estimation involves training. In order to test the approach, a synthetic dataset is generated by running the forward model with known parameter values to create a time series of soil temperature that serves as observations for an inverse problem in which the parameters are assumed unknown and subsequently estimated. We show that it is not possible to obtain a reliable estimate of the parameters using a time series of soil temperature observed at a single depth. Using measurements at two depths, reliable parameter estimates can be obtained although it is not possible to differentiate between latent and sensible heat fluxes. We also apply the approach to urban flux tower data from Phoenix, United States, and show that the thermal conductivity, volumetric heat capacity and the combined sensible-latent heat transfer coefficient can be reliably estimated whilst using an observed value for the effective surface albedo.</p></details> | <details><summary>18 pa...</summary><p>18 pages, 5 figures, 3 tables</p></details> |
| **[TempusBench: An Evaluation Framework for Time-Series Forecasting](https://arxiv.org/abs/2604.11529v2)** | 2026-04-16 | <details><summary>Show</summary><p>Foundation models have transformed natural language processing and computer vision, and a rapidly growing literature on time-series foundation models (TSFMs) seeks to replicate this success in forecasting. While recent open-source models demonstrate the promise of TSFMs, the field lacks a comprehensive and community-accepted model evaluation framework. We see at least four major issues impeding progress on the development of such a framework. First, existing evaluation frameworks comprise benchmark forecasting tasks derived from often outdated datasets (e.g., M3), many of which lack clear metadata and overlap with the corpora used to pre-train TSFMs. Second, these frameworks evaluate models along a narrowly defined set of benchmark forecasting tasks, such as forecast horizon length or domain, but overlook core statistical properties such as non-stationarity and seasonality. Third, domain-specific models (e.g., XGBoost) are often compared unfairly, as existing frameworks do not enforce a systematic and consistent hyperparameter tuning convention for all models. Fourth, visualization tools for interpreting comparative performance are lacking. To address these issues, we introduce TempusBench, an open-source evaluation framework for TSFMs. TempusBench consists of 1) new datasets which are not included in existing TSFM pretraining corpora, 2) a set of novel benchmark tasks that go beyond existing ones, 3) a model evaluation pipeline with a standardized hyperparameter tuning protocol, and 4) a tensorboard-based visualization interface. We provide access to our code on GitHub: https://github.com/Smlcrm/TempusBench and maintain a live leaderboard at https://benchmark.smlcrm.com/.</p></details> | |
| **[Time-RA: Towards Time Series Reasoning for Anomaly Diagnosis with LLM Feedback](https://arxiv.org/abs/2507.15066v5)** | 2026-04-16 | <details><summary>Show</summary><p>Time series anomaly detection (TSAD) has traditionally focused on binary classification and often lacks the fine-grained categorization and explanatory reasoning required for transparent decision-making. To address these limitations, we propose Time-series Reasoning for Anomaly (Time-RA), a novel task that reformulates TSAD from a discriminative into a generative, reasoning-intensive paradigm. To facilitate this, we introduce RATs40K, the first real-world large-scale multimodal benchmark with ~40,000 samples across 10 domains, integrating raw time series, textual context, and visual plots with structured reasoning annotations. Extensive benchmarking shows that while supervised fine-tuning and visual representations boost diagnostic accuracy and reasoning consistency, performance varies across complex scenarios. Notably, fine-tuned models demonstrate strong "plug-and-play" transferability, outperforming traditional baselines on unseen real-world datasets. Our work establishes a foundation for interpretable, multimodal time series analysis. All code (https://github.com/yyysjz1997/Time-RA) and the RATs40K dataset (https://huggingface.co/datasets/Time-RA/RATs40K) are fully open-sourced to facilitate future research.</p></details> | <details><summary>ACL 2...</summary><p>ACL 2026 Findings. 27 pages, 11 figures, 15 tables. Code and dataset are publicly available</p></details> |
| **[MambaSL: Exploring Single-Layer Mamba for Time Series Classification](https://arxiv.org/abs/2604.15174v1)** | 2026-04-16 | <details><summary>Show</summary><p>Despite recent advances in state space models (SSMs) such as Mamba across various sequence domains, research on their standalone capacity for time series classification (TSC) has remained limited. We propose MambaSL, a framework that minimally redesigns the selective SSM and projection layers of a single-layer Mamba, guided by four TSC-specific hypotheses. To address benchmarking limitations -- restricted configurations, partial University of East Anglia (UEA) dataset coverage, and insufficiently reproducible setups -- we re-evaluate 20 strong baselines across all 30 UEA datasets under a unified protocol. As a result, MambaSL achieves state-of-the-art performance with statistically significant average improvements, while ensuring reproducibility via public checkpoints for all evaluated models. Together with visualizations, these results demonstrate the potential of Mamba-based architectures as a TSC backbone.</p></details> | <details><summary>accep...</summary><p>accepted at ICLR 2026</p></details> |
| **[Assessing the Potential of Masked Autoencoder Foundation Models in Predicting Downhole Metrics from Surface Drilling Data](https://arxiv.org/abs/2604.15169v1)** | 2026-04-16 | <details><summary>Show</summary><p>Oil and gas drilling operations generate extensive time-series data from surface sensors, yet accurate real-time prediction of critical downhole metrics remains challenging due to the scarcity of labelled downhole measurements. This systematic mapping study reviews thirteen papers published between 2015 and 2025 to assess the potential of Masked Autoencoder Foundation Models (MAEFMs) for predicting downhole metrics from surface drilling data. The review identifies eight commonly collected surface metrics and seven target downhole metrics. Current approaches predominantly employ neural network architectures such as artificial neural networks (ANNs) and long short-term memory (LSTM) networks, yet no studies have explored MAEFMs despite their demonstrated effectiveness in time-series modeling. MAEFMs offer distinct advantages through self-supervised pre-training on abundant unlabeled data, enabling multi-task prediction and improved generalization across wells. This research establishes that MAEFMs represent a technically feasible but unexplored opportunity for drilling analytics, recommending future empirical validation of their performance against existing models and exploration of their broader applicability in oil and gas operations.</p></details> | |
| **[Universal hidden monotonic trend estimation with contrastive learning](https://arxiv.org/abs/2210.09817v3)** | 2026-04-16 | <details><summary>Show</summary><p>In this paper, we describe a universal method for extracting the underlying monotonic trend factor from time series data. We propose an approach related to the Mann-Kendall test, a standard monotonic trend detection method and call it contrastive trend estimation (CTE). We show that the CTE method identifies any hidden trend underlying temporal data while avoiding the standard assumptions used for monotonic trend identification. In particular, CTE can take any type of temporal data (vector, images, graphs, time series, etc.) as input. We finally illustrate the interest of our CTE method through several experiments on different types of data and problems.</p></details> | |
| **[Logo-LLM: Local and Global Modeling with Large Language Models for Time Series Forecasting](https://arxiv.org/abs/2505.11017v2)** | 2026-04-16 | <details><summary>Show</summary><p>Time series forecasting is critical across multiple domains, where time series data exhibit both local patterns and global dependencies. While Transformer-based methods effectively capture global dependencies, they often overlook short-term local variations in time series. Recent methods that adapt large language models (LLMs) into time series forecasting inherit this limitation by treating LLMs as black-box encoders, relying solely on the final-layer output and underutilizing hierarchical representations. To address this limitation, we propose Logo-LLM, a novel LLM-based framework that explicitly extracts and models multi-scale temporal features from different layers of a pre-trained LLM. Through empirical analysis, we show that shallow layers of LLMs capture local dynamics in time series, while deeper layers encode global trends. Moreover, Logo-LLM introduces lightweight Local-Mixer and Global-Mixer modules to align and integrate features with the temporal input across layers. Extensive experiments demonstrate that Logo-LLM achieves superior performance across diverse benchmarks, with strong generalization in few-shot and zero-shot settings while maintaining low computational overhead.</p></details> | |
| **[Assessing the Performance-Efficiency Trade-off of Foundation Models in Probabilistic Electricity Price Forecasting](https://arxiv.org/abs/2604.14739v1)** | 2026-04-16 | <details><summary>Show</summary><p>Large-scale renewable energy deployment introduces pronounced volatility into the electricity system, turning grid operation into a complex stochastic optimization problem. Accurate electricity price forecasting (EPF) is essential not only to support operational decisions, such as optimal bidding strategies and balancing power preparation, but also to reduce economic risk and improve market efficiency. Probabilistic forecasts are particularly valuable because they quantify uncertainty stemming from renewable intermittency, market coupling, and regulatory changes, enabling market participants to make informed decisions that minimize losses and optimize expected revenues. However, it remains an open question which models to employ to produce accurate forecasts. Should these be task-specific machine learning (ML) models or Time Series Foundation Models (TSFMs)? In this work, we compare four models for day-ahead probabilistic EPF (PEPF) in European bidding zones: a deterministic NHITS backbone with Quantile-Regression Averaging (NHITS+QRA) and a conditional Normalizing-Flow forecaster (NF) are compared with two TSFMs, namely Moirai and ChronosX. On the one hand, we find that TSFMs outperform task-specific deep learning models trained from scratch in terms of CRPS, Energy Score, and predictive interval calibration across market conditions. On the other hand, we find that well-configured task-specific models, particularly NHITS combined with QRA, achieve performance very close to TSFMs, and in some scenarios, such as when supplied with additional informative feature groups or adapted via few-shot learning from other European markets, they can even surpass TSFMs. Overall, our findings show that while TSFMs offer expressive modeling capabilities, conventional models remain highly competitive, emphasizing the need to weigh computational expense against marginal performance improvements in PEPF.</p></details> | <details><summary>Submi...</summary><p>Submitted to the 7th International Workshop on Energy Data and Analytics (EDA), held in conjunction with ACM e-Energy 2026</p></details> |
| **[From Time Series to State: Situation-Aware Modeling for Air Traffic Flow Prediction](https://arxiv.org/abs/2604.11198v3)** | 2026-04-16 | <details><summary>Show</summary><p>Accurate air traffic prediction in the terminal airspace (TA) is pivotal for proactive air traffic management (ATM). However, existing data-driven approaches predominantly rely on time series-based forecasting paradigms, which inherently overlook critical aircraft state information, such as real-time kinematics and proximity to airspace boundaries. To address this limitation, we propose \textit{AeroSense}, a direct state-to-flow modeling framework for air traffic prediction. Unlike classical time series-based methods that first aggregate aircraft trajectories into macroscopic flow sequences before modeling, AeroSense explicitly represents the real-time airspace situation as \textit{a dynamic set of aircraft states}, enabling the direct processing of a variable number of aircraft instead of time series as inputs. Specifically, we introduce a situation-aware state representation that enables AeroSense to sense the instantaneous terminal airspace situation directly from microscopic aircraft states. Furthermore, we design a model architecture that incorporates masked self-attention to capture inter-aircraft interactions, together with two decoupled prediction heads to model heterogeneous flow dynamics across two key functional areas of the TA. Extensive experiments on a large-scale real-world airport dataset demonstrate that AeroSense consistently achieves state-of-the-art performance, validating that direct modeling of microscopic aircraft states yields substantially higher predictive fidelity than time series-based baselines. Moreover, the proposed framework exhibits superior robustness during peak traffic periods, achieves Pareto-optimal performance under dayparting multi-object evaluation, and provides meaningful interpretability through attention-based visualizations.</p></details> | <details><summary>There...</summary><p>There are issues with the authors of the paper I submitted, as well as problems with the content of the article, so it needs to be withdrawn. Thank you for your understanding</p></details> |
| **[CSRA: Controlled Spectral Residual Augmentation for Robust Sepsis Prediction](https://arxiv.org/abs/2604.14532v1)** | 2026-04-16 | <details><summary>Show</summary><p>Accurate prediction of future risk and disease progression in sepsis is clinically important for early warning and timely intervention in intensive care. However, short-window sepsis prediction remains challenging, because shorter observation windows provide limited historical evidence, whereas longer prediction horizons reduce the number of patient trajectories with valid future supervision. To address this problem, we propose CSRA, a Controlled Spectral Residual Augmentation framework for short-window multi-system ICU time series. CSRA first groups variables by clinical systems and extracts system-level and global representations. It then performs input-adaptive residual perturbation in the spectral domain to generate structured and clinically plausible trajectory variations. To improve augmentation stability and controllability, CSRA is trained end-to-end with the downstream predictor under a unified objective, together with anchor consistency loss and controller regularization. Experiments on a MIMIC-IV sepsis cohort across multiple downstream models show that CSRA is consistently competitive and often superior, reducing regression error by 10.2\% in MSE and 3.7\% in MAE over the non-augmentation baseline, while also yielding consistent gains on classification. CSRA further maintains more favorable performance under shorter observation windows, longer prediction horizons, and smaller training data scales, while also remaining effective on an external clinical dataset~(ZiGongICUinfection), indicating stronger robustness and generalizability in clinically constrained settings.</p></details> | |
| **[AIBuildAI: An AI Agent for Automatically Building AI Models](https://arxiv.org/abs/2604.14455v1)** | 2026-04-15 | <details><summary>Show</summary><p>AI models underpin modern intelligent systems, driving advances across science, medicine, finance, and technology. Yet developing high-performing AI models remains a labor-intensive process that requires expert practitioners to iteratively design architectures, engineer representations, implement training pipelines and refine approaches through empirical evaluation. Existing AutoML methods partially alleviate this burden but remain limited to narrow aspects such as hyperparameter optimization and model selection within predefined search spaces, leaving the full development lifecycle largely dependent on human expertise. To address this gap, we introduce AIBuildAI, an AI agent that automatically builds AI models from a task description and training data. AIBuildAI adopts a hierarchical agent architecture in which a manager agent coordinates three specialized sub-agents: a designer for modeling strategy, a coder for implementation and debugging, and a tuner for training and performance optimization. Each sub-agent is itself a large language model (LLM) based agent capable of multi-step reasoning and tool use, enabling end-to-end automation of the AI model development process that goes beyond the scope of existing AutoML approaches. We evaluate AIBuildAI on MLE-Bench, a benchmark of realistic Kaggle-style AI development tasks spanning visual, textual, time-series and tabular modalities. AIBuildAI ranks first on MLE-Bench with a medal rate of 63.1%, outperforming all existing baseline methods and matching the capability of highly experienced AI engineers. These results demonstrate that hierarchical agent systems can automate the full AI model development process from task specification to deployable model, suggesting a pathway toward broadly accessible AI development with minimal human intervention.</p></details> | |
| **[Frame forecasting in cine MRI using the PCA respiratory motion model: comparing recurrent neural networks trained online and transformers](https://arxiv.org/abs/2410.05882v3)** | 2026-04-15 | <details><summary>Show</summary><p>Respiratory motion complicates accurate irradiation of thoraco-abdominal tumors during radiotherapy, as treatment-system latency entails target-location uncertainties. This work addresses frame forecasting in chest and liver cine MRI to compensate for such delays. We investigate RNNs trained with online learning algorithms, enabling adaptation to changing respiratory patterns via on-the-fly parameter updates, and transformers, increasingly common in time-series forecasting for their ability to capture long-term dependencies. Experiments used 12 sagittal thoracic and upper-abdominal cine-MRI sequences from ETH Zürich and OvGU; the OvGU data exhibited higher motion variability, noise, and lower contrast. PCA decomposes the Lucas-Kanade optical-flow field into static deformation modes and low-dimensional, time-dependent weights. We compare various methods for forecasting these weights: linear filters, population and sequence-specific transformer encoders, and RNNs trained with real-time recurrent learning (RTRL), unbiased online recurrent optimization, decoupled neural interfaces, and sparse one-step approximation (SnAp-1). Predicted displacements were used to warp the reference frame and generate future images. Prediction accuracy decreased with the horizon h. Linear regression performed best at short horizons (1.3mm geometrical error at h=0.32s, ETH Zürich dataset), while RTRL and SnAp-1 outperformed the other algorithms at medium-to-long horizons, with geometrical errors below 1.4mm and 2.8mm on the sequences from ETH Zürich and OvGU, respectively. The sequence-specific transformer was competitive for low-to-medium horizons, but transformers remained overall limited by data scarcity and domain shift between datasets. Predicted frames visually resembled the ground truth, with notable errors occurring near the diaphragm at end-inspiration and regions affected by out-of-plane motion.</p></details> | <details><summary>43 pa...</summary><p>43 pages, 19 figures. Revised version with minor corrections and improved figures and language. Accepted for publication in Computerized Medical Imaging and Graphics</p></details> |
| **[Unsupervised Anomaly Detection in Process-Complex Industrial Time Series: A Real-World Case Study](https://arxiv.org/abs/2604.13928v1)** | 2026-04-15 | <details><summary>Show</summary><p>Industrial time-series data from real production environments exhibits substantially higher complexity than commonly used benchmark datasets, primarily due to heterogeneous, multi-stage operational processes. As a result, anomaly detection methods validated under simplified conditions often fail to generalize to industrial settings. This work presents an empirical study on a unique dataset collected from fully operational industrial machinery, explicitly capturing pronounced process-induced variability. We evaluate which model classes are capable of capturing this complexity, starting with a classical Isolation Forest baseline and extending to multiple autoencoder architectures. Experimental results show that Isolation Forest is insufficient for modeling the non-periodic, multi-scale dynamics present in the data, whereas autoencoders consistently perform better. Among them, temporal convolutional autoencoders achieve the most robust performance, while recurrent and variational variants require more careful tuning.</p></details> | |
| **[ASTER: Latent Pseudo-Anomaly Generation for Unsupervised Time-Series Anomaly Detection](https://arxiv.org/abs/2604.13924v1)** | 2026-04-15 | <details><summary>Show</summary><p>Time-series anomaly detection (TSAD) is critical in domains such as industrial monitoring, healthcare, and cybersecurity, but it remains challenging due to rare and heterogeneous anomalies and the scarcity of labelled data. This scarcity makes unsupervised approaches predominant, yet existing methods often rely on reconstruction or forecasting, which struggle with complex data, or on embedding-based approaches that require domain-specific anomaly synthesis and fixed distance metrics. We propose ASTER, a framework that generates pseudo-anomalies directly in the latent space, avoiding handcrafted anomaly injections and the need for domain expertise. A latent-space decoder produces tailored pseudo-anomalies to train a Transformer-based anomaly classifier, while a pre-trained LLM enriches the temporal and contextual representations of this space. Experiments on three benchmark datasets show that ASTER achieves state-of-the-art performance and sets a new standard for LLM-based TSAD.</p></details> | |
| **[Forecasting Multivariate Time Series under Predictive Heterogeneity: A Validation-Driven Clustering Framework](https://arxiv.org/abs/2604.13748v1)** | 2026-04-15 | <details><summary>Show</summary><p>We study adaptive pooling under predictive heterogeneity in high-dimensional multivariate time series forecasting, where global models improve statistical efficiency but may fail to capture heterogeneous predictive structure, while naive specialization can induce negative transfer. We formulate adaptive pooling as a statistical decision problem and propose a validation-driven framework that determines when and how specialization should be applied. Rather than grouping series based on representation similarity, we define partitions through out-of-sample predictive performance, thereby aligning data organization with predictive risk, defined as expected out-of-sample loss and approximated via validation error. Cluster assignments are iteratively updated using validation losses for both point (Huber) and probabilistic (pinball) forecasting, improving robustness to heavy-tailed errors and local anomalies. To ensure reliability, we introduce a leakage-free fallback mechanism that reverts to a global model whenever specialization fails to improve validation performance, providing a safeguard against performance degradation under a strict training-validation-test protocol. Experiments on large-scale traffic datasets demonstrate consistent improvements over strong baselines while avoiding degradation when heterogeneity is weak. Overall, the proposed framework provides a principled and practically reliable approach to adaptive pooling in high-dimensional forecasting problems.</p></details> | |
| **[Precision spectral estimation at sub-Hz frequencies: closed-form posteriors and Bayesian noise projection](https://arxiv.org/abs/2507.20846v2)** | 2026-04-15 | <details><summary>Show</summary><p>We consider the problem of estimating cross-spectral quantities in the low-frequency regime, where long observation times limit averaging over large ensembles of periodograms, thereby preventing the use of approximate Gaussian statistics. This case is relevant for precision low-frequency gravitational experiments such as LISA and LISA Pathfinder. We present a Bayesian method for estimating spectral quantities in multivariate Gaussian time series. The approach, based on periodograms and Wishart statistics, yields closed-form expressions at any given frequency for the marginal posterior distributions of the individual power spectral densities, the pairwise coherence, and the multiple coherence, as well as for the joint posterior distribution of the full cross-spectral density matrix. In the context of noise projection -- where one series is modeled as a linear combination of filtered versions of the others, plus a background component -- the method also provides closed-form posteriors for both the susceptibilities, i.e., the filter transfer functions, and the power spectral density of the background. We apply the method to data from the LISA Pathfinder mission, showing effective decorrelation of temperature-induced acceleration noise and reliable estimation of its coupling coefficient.</p></details> | <details><summary>This ...</summary><p>This work has been submitted for possible publication</p></details> |
| **[Fractional lower-order covariance-based measures for cyclostationary time series with heavy-tailed distributions: application to dependence testing and model order identification](https://arxiv.org/abs/2604.13689v1)** | 2026-04-15 | <details><summary>Show</summary><p>This article introduces new methods for the analysis of cyclostationary time series with infinite variance. Traditional cyclostationary analysis, based on periodically correlated (PC) processes, relies on the autocovariance function (ACVF). However, the ACVF is not suitable for data exhibiting a heavy-tailed distribution, particularly with infinite variance. Thus, we propose a novel framework for the analysis of cyclostationary time series with heavy-tailed distribution, utilizing the fractional lower-order covariance (FLOC) as an alternative to covariance. This leads to the introduction of two new autodependence measures: the periodic fractional lower-order autocorrelation function (peFLOACF) and the periodic fractional lower-order partial autocorrelation function (peFLOPACF). These measures generalize the classical periodic autocorrelation function (peACF) and periodic partial autocorrelation function (pePACF), offering robust tools for analyzing infinite-variance processes. Two practical applications of the proposed measures are explored: a portmanteau test for testing dependence in cyclostationary series and a method for order identification in periodic autoregressive (PAR) and periodic moving average (PMA) models with infinite variance. Both applications demonstrate the potential of new tools, with simulations validating their efficiency. The methodology is further illustrated through the analysis of real-world air pollution data, which showcases its practical utility. The results indicate that the proposed measures based on FLOC provide reliable and efficient techniques for analyzing cyclostationary processes with heavy-tailed distributions.</p></details> | 26 pages, 17 figures |
| **[Irregularly Sampled Time Series Interpolation for Binary Evolution Simulations Using Dynamic Time Warping](https://arxiv.org/abs/2604.13604v1)** | 2026-04-15 | <details><summary>Show</summary><p>Binary stellar evolution simulations are computationally expensive. Stellar population synthesis relies on these detailed evolution models at a fundamental level. Producing thousands of such models requires hundreds of CPU hours, but stellar track interpolation provides one approach to significantly reduce this computational cost. Although single-star track interpolation is straightforward, stellar interactions in binary systems introduce significant complexity to binary evolution, making traditional single-track interpolation methods inapplicable. Binary tracks present fundamentally different challenges compared to single stars, which possess relatively straightforward evolutionary phases identifiable through distinct physical properties. Binary systems are complicated by mutual interactions that can dramatically alter evolutionary trajectories and introduce discontinuities difficult to capture through standard interpolation. In this work, we introduce a novel approach for track alignment and iterative track averaging based on Dynamic Time Warping to address misalignments between neighboring tracks. Our method computes a single shared warping path across all physical parameters simultaneously, placing them on a consistent temporal grid that preserves the causal relationships between parameters. We demonstrate that this joint-alignment strategy maintains key physical relationships such as the Stefan-Boltzmann law in the interpolated tracks. Our comprehensive evaluation across multiple binary configurations demonstrates that proper temporal alignment is crucial for track interpolation methods. The proposed method consistently outperforms existing approaches and enables the efficient generation of more accurate binary population samples for astrophysical studies.</p></details> | <details><summary>25 pa...</summary><p>25 pages, 11 figures. Submitted to ApJ</p></details> |
| **[Minimax Optimality and Spectral Routing for Majority-Vote Ensembles under Markov Dependence](https://arxiv.org/abs/2604.13414v1)** | 2026-04-15 | <details><summary>Show</summary><p>Majority-vote ensembles achieve variance reduction by averaging over diverse, approximately independent base learners. When training data exhibits Markov dependence, as in time-series forecasting, reinforcement learning (RL) replay buffers, and spatial grids, this classical guarantee degrades in ways that existing theory does not fully quantify. We provide a minimax characterization of this phenomenon for discrete classification in a fixed-dimensional Markov setting, together with an adaptive algorithm that matches the rate on a graph-regular subclass. We first establish an information-theoretic lower bound for stationary, reversible, geometrically ergodic chains in fixed ambient dimension, showing that no measurable estimator can achieve excess classification risk better than $Ω(\sqrt{\Tmix/n})$. We then prove that, on the AR(1) witness subclass underlying the lower-bound construction, dependence-agnostic uniform bagging is provably suboptimal with excess risk bounded below by $Ω(\Tmix/\sqrt{n})$, exhibiting a $\sqrt{\Tmix}$ algorithmic gap. Finally, we propose \emph{adaptive spectral routing}, which partitions the training data via the empirical Fiedler eigenvector of a dependency graph and achieves the minimax rate $\mathcal{O}(\sqrt{\Tmix/n})$ up to a lower-order geometric cut term on a graph-regular subclass, without knowledge of $\Tmix$. Experiments on synthetic Markov chains, 2D spatial grids, the 128-dataset UCR archive, and Atari DQN ensembles validate the theoretical predictions. Consequences for deep RL target variance, scalability via Nyström approximation, and bounded non-stationarity are developed as supporting material in the appendix.</p></details> | |
| **[Bias-Corrected Adaptive Conformal Inference for Multi-Horizon Time Series Forecasting](https://arxiv.org/abs/2604.13253v1)** | 2026-04-14 | <details><summary>Show</summary><p>Adaptive Conformal Inference (ACI) provides distribution-free prediction intervals with asymptotic coverage guarantees for time series under distribution shift. However, ACI only adapts the quantile threshold -- it cannot shift the interval center. When a base forecaster develops persistent bias after a regime change, ACI compensates by widening intervals symmetrically, producing unnecessarily conservative bands. We propose Bias-Corrected ACI (BC-ACI), which augments standard ACI with an online exponentially weighted moving average (EWM) estimate of forecast bias. BC-ACI corrects nonconformity scores before quantile computation and re-centers prediction intervals, addressing the root cause of miscalibration rather than its symptom. An adaptive dead-zone threshold suppresses corrections when estimated bias is indistinguishable from noise, ensuring no degradation on well-calibrated data. In controlled experiments across 688 runs spanning two base models, four synthetic regimes, and three real datasets, BC-ACI reduces Winkler interval scores by 13--17% under mean and compound distribution shifts (Wilcoxon p < 0.001) while maintaining equivalent performance on stationary data (ratio 1.002x). We provide finite-sample analysis showing that coverage guarantees degrade gracefully with bias estimation error.</p></details> | <details><summary>14 pa...</summary><p>14 pages, 3 figures, 2 tables. Preprint</p></details> |
| **[Predicting Time Pressure of Powered Two-Wheeler Riders for Proactive Safety Interventions](https://arxiv.org/abs/2601.03173v2)** | 2026-04-14 | <details><summary>Show</summary><p>Time pressure critically influences risky maneuvers and crash proneness among powered two-wheeler riders, yet its prediction remains underexplored in intelligent transportation systems. We present a large-scale dataset of 129,000+ labeled multivariate time-series sequences from 153 rides by 51 participants under No, Low, and High Time Pressure conditions. Each sequence captures 63 features spanning vehicle kinematics, control inputs, behavioral violations, and environmental context. Our empirical analysis shows High Time Pressure induces 48% higher speeds, 36.4% greater speed variability, 58% more risky turns at intersections, 36% more sudden braking, and 50% higher rear brake forces versus No Time Pressure. To benchmark this dataset, we propose MotoTimePressure, a deep learning model combining convolutional preprocessing, dual-stage temporal attention, and Squeeze-and-Excitation feature recalibration, achieving 91.53% accuracy and 98.93% ROC AUC, outperforming eight baselines, with only 172K parameters, 2.16 MB model size, and 0.04 ms inference on CPU. Since time pressure cannot be directly measured in real time, we demonstrate its utility in collision prediction and threshold determination. Using MTPS-predicted time pressure as a feature improves collision risk accuracy for both Informer (91.25% to 93.51%) and TimesNet (92.10% to 93.90%), approaching oracle performance (93.72% and 94.06%, respectively). Thresholded time pressure states capture rider cognitive stress and enable proactive ITS interventions, including adaptive alerts, haptic feedback, V2I signaling, and speed guidance, supporting safer two-wheeler mobility under the Safe System Approach.</p></details> | 13 pages |
| **[Invariant Features for Global Crop Type Classification](https://arxiv.org/abs/2509.03497v3)** | 2026-04-14 | <details><summary>Show</summary><p>Accurate global crop type mapping supports agricultural monitoring and food security, yet remains limited by the scarcity of labeled data in many regions. A key challenge is enabling models trained in one geography to generalize reliably to others despite shifts in climate, phenology, and spectral characteristics. In this work, we show that geographic transfer in crop classification is primarily governed by the ability to learn invariant structure in multispectral time series. To systematically study this, we introduce CropGlobe, a globally distributed benchmark dataset of 300,000 samples spanning eight countries and five continents, and define progressively harder transfer settings from cross-country to cross-hemisphere. Across all settings, we find that simple spectral-temporal representations outperform both handcrafted features and modern geospatial foundation model embeddings. We propose CropNet, a lightweight convolutional architecture that jointly convolves across spectral and temporal dimensions to learn invariant crop signatures. Despite its simplicity, CropNet consistently outperforms larger transformer-based and foundation-model approaches under geographic domain shift. To further improve robustness to geographic variation, we introduce augmentations that simulate shifts in crop phenology and reflectance. Combined with CropNet, this yields substantial gains under large domain shifts. Our results demonstrate that inductive bias toward joint spectral-temporal structure is more critical for transfer than model scale or pretraining, pointing toward a scalable and data-efficient paradigm for worldwide agricultural mapping. Data and code are available at https://github.com/x-ytong/CropNet/.</p></details> | |
| **[A Shiny micromapST App](https://arxiv.org/abs/2604.12773v1)** | 2026-04-14 | <details><summary>Show</summary><p>The linked micromaps approach was originally developed as an improvement to choropleth maps for displaying statistical summaries connected with spatial areal units, such as countries, states, and counties. Two R packages to create linked micromaps were published in 2015. These are the micromap and micromapST packages. The latter was originally for data indexed to the 50 US states and DC, but the latest version accommodates arbitrary geographies. The micromapST package handles the formatting needed for linked micromaps and offers several options for statistical displays (scatterplots, boxplots, time series plots, and more). The micromapST package is very useful and takes care of most details of the layouts, but it can be problematic specifying the data frames needed to create the desired graphic. Furthermore, exploring data through visualization is easier, faster, and more intuitive using a graphical user interface. This is the motivation behind the R Shiny micromapST app. This paper will serve as a brief tutorial and introduction to micromapST and the Shiny app using real-world data and applications. In this paper, we provide background information on visualizing geographically indexed data and linked micromaps in Section 1. Section 2 discusses the data sets used in two illustrative examples. Sections 3 and 4 describe the application interface and show how it can create linked micromaps. The paper concludes with comments and future work.</p></details> | |
| **[Automated Batch Distillation Process Simulation for a Large Hybrid Dataset for Deep Anomaly Detection](https://arxiv.org/abs/2604.09166v2)** | 2026-04-14 | <details><summary>Show</summary><p>Anomaly detection (AD) in chemical processes based on deep learning offers significant opportunities but requires large, diverse, and well-annotated training datasets that are rarely available from industrial operations. In a recent work, we introduced a large, fully annotated experimental dataset for batch distillation under normal and anomalous operating conditions. In the present study, we augment this dataset with a corresponding simulation dataset, creating a novel hybrid dataset. The simulation data is generated in an automated workflow with a novel Python-based process simulator that employs a tailored index-reduction strategy for the underlying differential-algebraic equations. Leveraging the rich metadata and structured anomaly annotations of the experimental database, experimental records are automatically translated into simulation scenarios. After calibration to a single reference experiment, the dynamics of the other experiments are well predicted. This enabled the fully automated, consistent generation of time-series data for a large number of experimental runs, covering both normal operation and a wide range of actuator- and control-related anomalies. The resulting hybrid dataset is released openly. From a process simulation perspective, this work demonstrates the automated, consistent simulation of large-scale experimental campaigns, using batch distillation as an example. From a data-driven AD perspective, the hybrid dataset provides a unique basis for simulation-to-experiment style transfer, the generation of pseudo-experimental data, and future research on deep AD methods in chemical process monitoring.</p></details> | |
| **[Do VLMs Truly "Read" Candlesticks? A Multi-Scale Benchmark for Visual Stock Price Forecasting](https://arxiv.org/abs/2604.12659v1)** | 2026-04-14 | <details><summary>Show</summary><p>Vision-language models(VLMs) are increasingly applied to visual stock price forecasting, yet existing benchmarks inadequately evaluate their understanding of stock price in candlestick charts. First, prior studies fail to isolate VLMs' comprehension of visual inputs genuinely improves predictive performance and whether VLMs truly comprehend candlestick patterns. Further, most existing datasets and evaluation setups are designed around single-period or tabular inputs. However, human analysts strongly rely on multi-scale candlestick charts, where longer-term horizons capture trend direction and shorter-term horizons provide cues for inflection points, making it difficult to systematically assess VLMs' ability to integrate short-term and long-term visual market dynamics. To bridge this gap, we construct a multi-scale candlestick charts dataset and a standardized evaluation framework to assess VLMs' ability to utilize multi-scale visual market signals. Evaluation combines confusion-matrix-based diagnostics with information coefficient(IC) time series metrics and includes XGBoost as a feature-based temporal baseline. Using this dataset, we benchmark representative VLMs and analyze their ability to leverage multi-scale stock price data. Experimental results show that most VLMs perform well only under persistent uptrend or downtrend conditions, while exhibiting weak predictive capability in more common market scenarios. We also identify significant prediction biases and limited sensitivity to explicitly specified forecast horizons in prompts, indicating inherent limitations in precise temporal reasoning.</p></details> | <details><summary>We ev...</summary><p>We evaluate whether VLMs can comprehend multi-scale visual stock price data like human analysts with a proposed benchmark, identifying current VLMs' weak predictive power, significant biases, and limited sensitivity to forecast horizons and prompts</p></details> |
| **[TimeSAF: Towards LLM-Guided Semantic Asynchronous Fusion for Time Series Forecasting](https://arxiv.org/abs/2604.12648v1)** | 2026-04-14 | <details><summary>Show</summary><p>Despite the recent success of large language models (LLMs) in time-series forecasting, most existing methods still adopt a Deep Synchronous Fusion strategy, where dense interactions between textual and temporal features are enforced at every layer of the network. This design overlooks the inherent granularity mismatch between modalities and leads to what we term semantic perceptual dissonance: high-level abstract semantics provided by the LLM become inappropriately entangled with the low-level, fine-grained numerical dynamics of time series, making it difficult for semantic priors to effectively guide forecasting. To address this issue, we propose TimeSAF, a new framework based on hierarchical asynchronous fusion. Unlike synchronous approaches, TimeSAF explicitly decouples unimodal feature learning from cross-modal interaction. It introduces an independent cross-modal semantic fusion trunk, which uses learnable queries to aggregate global semantics from the temporal and prompt backbones in a bottom-up manner, and a stage-wise semantic refinement decoder that asynchronously injects these high-level signals back into the temporal backbone. This mechanism provides stable and efficient semantic guidance while avoiding interference with low-level temporal dynamics. Extensive experiments on standard long-term forecasting benchmarks show that TimeSAF significantly outperforms state-of-the-art baselines, and further exhibits strong generalization in both few-shot and zero-shot transfer settings.</p></details> | |
| **[Fun-TSG: A Function-Driven Multivariate Time Series Generator with Variable-Level Anomaly Labeling](https://arxiv.org/abs/2604.14221v1)** | 2026-04-14 | <details><summary>Show</summary><p>Reliable evaluation of anomaly detection methods in multivariate time series remains an open challenge, largely due to the limitations of existing benchmark datasets. Current resources often lack fine-grained anomaly annotations, do not provide explicit intervariable and temporal dependencies, and offer little insight into the underlying generative mechanisms. These shortcomings hinder the development and rigorous comparison of detection models, especially those targeting interpretable and variable-specific outputs. To address this gap, we introduce Fun-TSG, a fully customizable time series generator designed to support high-quality evaluation of anomaly detection systems. Our tool enables both fully automated generation, based on randomly sampled dependency structures and anomaly types, and manual generation through user-defined equations and anomaly configurations. In both cases, it provides full transparency over the data generation process, including access to ground-truth anomaly labels at the variable and timestamp levels. Fun-TSG supports the creation of diverse, interpretable, and reproducible benchmarking scenarios, enabling fine-grained performance analysis for both classical and modern anomaly detection models.</p></details> | |
| **[GTCN-G: A Residual Graph-Temporal Fusion Network for Imbalanced Intrusion Detection](https://arxiv.org/abs/2510.07285v3)** | 2026-04-14 | <details><summary>Show</summary><p>The escalating complexity of network threats and the inherent class imbalance in traffic data present formidable challenges for modern Intrusion Detection Systems (IDS). While Graph Neural Networks (GNNs) excel in modeling topological structures and Temporal Convolutional Networks (TCNs) are proficient in capturing time-series dependencies, a framework that synergistically integrates both while explicitly addressing data imbalance remains an open challenge. This paper introduces a novel deep learning framework, named Gated Temporal Convolutional Network and Graph (GTCN-G), engineered to overcome these limitations. Our model uniquely fuses a Gated TCN (G-TCN) for extracting hierarchical temporal features from network flows with a Graph Convolutional Network (GCN) designed to learn from the underlying graph structure. The core innovation lies in the integration of a residual learning mechanism, implemented via a Graph Attention Network (GAT). This mechanism preserves original feature information through residual connections, which is critical for mitigating the class imbalance problem and enhancing detection sensitivity for rare malicious activities (minority classes). We conducted extensive experiments on two public benchmark datasets, UNSW-NB15 and ToN-IoT, to validate our approach. The empirical results demonstrate that the proposed GTCN-G model achieves state-of-the-art performance, significantly outperforming existing baseline models in both binary and multi-class classification tasks.</p></details> | <details><summary>This ...</summary><p>This preprint was submitted to IEEE TrustCom 2025. The accepted version will be published under copyright 2025 IEEE</p></details> |
| **[Self-Normalization for CUSUM-based Change Detection in Locally Stationary Time Series](https://arxiv.org/abs/2509.07112v3)** | 2026-04-14 | <details><summary>Show</summary><p>A new bivariate partial sum process for locally stationary time series is introduced and its weak convergence to a Brownian sheet is established. This construction enables the development of a novel self-normalized CUSUM test statistic for detecting changes in the mean of a locally stationary time series. For stationary data, self-normalization relies on the factorization of a constant long-run variance and a stochastic factor. In this case, the CUSUM statistic can be divided by another statistic proportional to the long-run variance, so that the latter cancels, avoiding estimation of the long-run variance. Under local stationarity, the partial sum process converges to $\int_0^t σ(x) d B_x$ and no such factorization is possible. To overcome this obstacle, a bivariate partial-sum process is introduced, allowing the construction of self-normalized test statistics under local stationarity. Weak convergence of the process is proven, and it is shown that the resulting self-normalized tests attain asymptotic level $α$ under the null hypothesis of no change, while being consistent against abrupt, gradual, and multiple changes under mild assumptions. Simulation studies show that the proposed tests have accurate size and substantially improved finite-sample power relative to existing approaches. Two data examples illustrate practical performance.</p></details> | <details><summary>Keywo...</summary><p>Keywords: Change point analysis, gradual changes, local stationarity, self-normalization, CUSUM test</p></details> |
| **[Predicting Energy Demand with Tensor Factor Models](https://arxiv.org/abs/2502.06213v2)** | 2026-04-14 | <details><summary>Show</summary><p>Hourly consumption from multiple providers displays pronounced intra-day, intra-week, and annual seasonalities, as well as strong cross-sectional correlations. We introduce a novel approach for forecasting high-dimensional U.S. electricity demand data by accounting for multiple seasonal patterns via tensor factor models. To this end, we restructure the hourly electricity demand data into a sequence of weekly tensors. Each weekly tensor is a three-mode array whose dimensions correspond to the hours of the day, the days of the week, and the number of providers. This multi-dimensional representation enables a factor decomposition that distinguishes among the various seasonal patterns along each mode: factor loadings over the hour dimension highlight intra-day cycles, factor loadings over the day dimension capture differences across weekdays and weekends, and factor loadings over the provider dimension reveal commonalities and shared dynamics among the different entities. We rigorously compare the predictive performance of our tensor factor model against several benchmarks, including traditional vector factor models and cutting-edge functional time series methods. The results consistently demonstrate that the tensor-based approach delivers superior forecasting accuracy at different horizons and provides interpretable factors that align with domain knowledge. Beyond its empirical advantages, our framework offers a systematic way to gain insight into the underlying processes that shape electricity demand patterns. In doing so, it paves the way for more nuanced, data-driven decision-making and can be adapted to address similar challenges in other high-dimensional time series applications.</p></details> | |
| **[Mortality Forecasting as a Flow Field in Tucker Decomposition Space](https://arxiv.org/abs/2603.24299v2)** | 2026-04-13 | <details><summary>Show</summary><p>Mortality forecasting methods in the Lee-Carter tradition extrapolate temporal components via time-series models, often producing forecasts that systematically underpredict life expectancy at long horizons. This bias is consequential for planning pension funding, healthcare capacity, and social security solvency. The dominant alternative - the Bayesian double-logistic model underlying the UN World Population Prospects - forecasts scalar life expectancy and requires a separate model life table system to recover age-specific rates. We reframe forecasting as integrating a flow field through the low-dimensional score space of a Tucker tensor decomposition of the Human Mortality Database. PCA reduction reveals that the mortality transition is essentially a one-dimensional flow: a scalar speed function advances the level, trajectory functions supply the structural scores, and the Tucker reconstruction produces complete sex-specific, single-year-of-age mortality schedules at each horizon. In leave-country-out cross-validation (9,507 test points, 50-year horizon), the flow-field achieves bias of +1.058 years - substantially smaller than Lee-Carter (-3.2), Hyndman-Ullah (-3.5), and pyBayesLife (+3.3) - because it navigates a score space parameterised by mortality level rather than extrapolating temporal trends into unobserved territory. On 1.66 million sex-age-specific test points, it achieves 2.7x lower error than our de novo Python reimplementation of the UN pipeline trained on the same data - with lower error at every age, every forecast horizon, and for both sexes.</p></details> | |
| **[A unified data format for managing diabetes time-series data: DIAbetes eXchange (DIAX)](https://arxiv.org/abs/2604.11944v1)** | 2026-04-13 | <details><summary>Show</summary><p>Diabetes devices, including Continuous Glucose Monitoring (CGM), Smart Insulin Pens, and Automated Insulin Delivery systems, generate rich time-series data widely used in research and machine learning. However, inconsistent data formats across sources hinder sharing, integration, and analysis. We present DIAX (DIAbetes eXchange), a standardized JSON-based format for unifying diabetes time-series data, including CGM, insulin, and meal signals. DIAX promotes interoperability, reproducibility, and extensibility, particularly for machine learning applications. An open-source repository provides tools for dataset conversion, cross-format compatibility, visualization, and community contributions. DIAX is a translational resource, not a data host, ensuring flexibility without imposing data-sharing constraints. Currently, DIAX is compatible with other standardization efforts and supports major datasets (DCLP3, DCLP5, IOBP2, PEDAP, T1Dexi, Loop), totaling over 10 million patient-hours of data. https://github.com/Center-for-Diabetes-Technology/DIAX</p></details> | 7 pages, 2 figures |
| **[INTARG: Informed Real-Time Adversarial Attack Generation for Time-Series Regression](https://arxiv.org/abs/2604.11928v1)** | 2026-04-13 | <details><summary>Show</summary><p>Time-series forecasting aims to predict future values by modeling temporal dependencies in historical observations. It is a critical component of many real-world systems, where accurate forecasts improve operational efficiency and help mitigate uncertainty and risk. More recently, machine learning (ML), and especially deep learning (DL)-based models, have gained widespread adoption for time-series forecasting, but they remain vulnerable to adversarial attacks. However, many state-of-the-art attack methods are not directly applicable in time-series settings, where storing complete historical data or performing attacks at every time step is often impractical. This paper proposes an adversarial attack framework for time-series forecasting under an online bounded-buffer setting, leveraging an informed and selective attack strategy. By selectively targeting time steps where the model exhibits high confidence and the expected prediction error is maximal, our framework produces fewer but substantially more effective attacks. Experiments show that our framework can increase the prediction error up to 2.42x, while performing attacks in fewer than 10% of time steps.</p></details> | |
| **[SmellNet: A Large-scale Dataset for Real-world Smell Recognition](https://arxiv.org/abs/2506.00239v5)** | 2026-04-13 | <details><summary>Show</summary><p>The ability of AI to sense and identify various substances based on their smell alone can have profound impacts on allergen detection (e.g. smelling gluten or peanuts in a cake), monitoring the manufacturing process, and sensing hormones that indicate emotional states, stress levels, and diseases. Despite these broad impacts, there are few standardized datasets, and therefore little progress, for training and evaluating AI systems' ability to `smell' in the real-world. In this paper, we use small gas and chemical sensors to create SmellNet, a comparatively large dataset for sensor-based machine olfaction that digitizes a diverse range of smells in the natural world. SmellNet contains about 828,000 time-series data points across 50 substances, spanning nuts, spices, herbs, fruits, and vegetables, and 43 mixtures among them with fixed ingredient volumetric ratios, with 68 hours of data collected. Using SmellNet, we developed ScentFormer, a Transformer-based architecture combining temporal differencing and sliding-window augmentation for smell data. For the SmellNet-Base classification tasks, ScentFormer achieves 63.3% Top-1 accuracy with GC-MS supervision, and for the SmellNet-Mixture distribution prediction tasks, ScentFormer achieves 50.2% Top-1@0.1 on the test-seen split. ScentFormer's ability to generalize across conditions and capture transient chemical dynamics demonstrates the promise of temporal modeling in sensor-based olfactory AI. SmellNet and ScentFormer lay the groundwork for sensor-based olfactory applications across healthcare, food and beverage, environmental monitoring, manufacturing, and entertainment.</p></details> | <details><summary>Accep...</summary><p>Accepted to ICLR 2026; published as a conference paper at ICLR 2026. 32 pages; 21 figures</p></details> |
| **[MSTN: A Lightweight and Fast Model for General TimeSeries Analysis](https://arxiv.org/abs/2511.20577v3)** | 2026-04-13 | <details><summary>Show</summary><p>Real-world time series often exhibit strong non-stationarity, complex nonlinear dynamics, and behavior expressed across multiple temporal scales, from rapid local fluctuations to slow-evolving long-range trends. However, many contemporary architectures impose rigid, fixed-scale structural priors -- such as patch-based tokenization, predefined receptive fields, or frozen backbone encoders -- which can over-regularize temporal dynamics and limit adaptability to abrupt high-magnitude events. To handle this, we introduce the Multi-scale Temporal Network (MSTN), a hybrid neural architecture grounded in an Early Temporal Aggregation principle. MSTN integrates three complementary components: (i) a multi-scale convolutional encoder that captures fine-grained local structure; (ii) a sequence modeling module that learns long-range dependencies through either recurrent or attention-based mechanisms; and (iii) a self-gated fusion stage incorporating squeeze-excitation and a single dense layer to dynamically reweight and fuse multi-scale representations. This design enables MSTN to flexibly model temporal patterns spanning milliseconds to extended horizons, while avoiding the computational burden typically associated with long-context models. Across extensive benchmarks covering imputation, long term forecasting, short term forecasting, classification, and cross-dataset generalization, MSTN achieves state-of-the-art performance, establishing new best results on 33 of 40 datasets, while remaining lightweight ($\sim$278,520 params for MSTN-BiLSTM and $\sim$950,776 $\approx$ 1M for MSTN-Transformer) and suitable for low-latency inference ($<$1 sec, often in milliseconds), resource-constrained deployment.</p></details> | 34 pages |
| **[SLALOM: Simulation Lifecycle Analysis via Longitudinal Observation Metrics for Social Simulation](https://arxiv.org/abs/2604.11466v1)** | 2026-04-13 | <details><summary>Show</summary><p>Large Language Model (LLM) agents offer a potentially-transformative path forward for generative social science but face a critical crisis of validity. Current simulation evaluation methodologies suffer from the "stopped clock" problem: they confirm that a simulation reached the correct final outcome while ignoring whether the trajectory leading to it was sociologically plausible. Because the internal reasoning of LLMs is opaque, verifying the "black box" of social mechanisms remains a persistent challenge. In this paper, we introduce SLALOM (Simulation Lifecycle Analysis via Longitudinal Observation Metrics), a framework that shifts validation from outcome verification to process fidelity. Drawing on Pattern-Oriented Modeling (POM), SLALOM treats social phenomena as multivariate time series that must traverse specific SLALOM gates, or intermediate waypoint constraints representing distinct phases. By utilizing Dynamic Time Warping (DTW) to align simulated trajectories with empirical ground truth, SLALOM offers a quantitative metric to assess structural realism, helping to differentiate plausible social dynamics from stochastic noise and contributing to more robust policy simulation standards.</p></details> | <details><summary>CHI 2...</summary><p>CHI 2026 PoliSim@CHI 2026: LLM Agent Simulation for Policy Workshop</p></details> |
| **[Detection and Mode-Identification of Multiple Change Points in Tensor Factor Models](https://arxiv.org/abs/2604.11300v1)** | 2026-04-13 | <details><summary>Show</summary><p>We study the problems arising from modeling high-dimensional tensor-valued time series under a Tucker decomposition-based factor model with multiple structural change points. First, we propose an algorithm for detecting the multiple change points, which utilizes the low-rank structure of the data for statistical and computational efficiency. Also, the multi-dimensional array setting poses unique challenges, as some changes are associated with a subset of the modes, and the changes in different modes may interact with one another. Recognizing these, we investigate the problem of identifying each change with the tensor modes post-segmentation. To this end, we formalize the mode-identifiability of each change and propose an algorithm for detecting the modes at which the data are undergoing a mode-identifiable shift. We establish the consistency of both change point detection and mode-identification methods under a weak moment condition, and demonstrate their good performance on simulated datasets where, in particular, it is shown that the mode-identification step can improve the post-segmentation estimation of the mode-wise loading space. Additionally we analyze the datasets on New York City taxi usage and Fama--French portfolio returns using the proposed suite of methods.</p></details> | 165 pages |
| **[Detection of Anomalous Network Nodes via Hierarchical Prediction and Extreme Value Theory](https://arxiv.org/abs/2304.13941v2)** | 2026-04-13 | <details><summary>Show</summary><p>Continuously evolving cyber-attacks against industrial networks reduce the effectiveness of signature-based detection methods. Once malware has infiltrated a network (for example, entering via an unsecured device), it can infect further network nodes and carry out malicious activity. Infected nodes can exhibit unusual behaviour in their use of Address Resolution Protocol (ARP) calls within the network. In order to detect such anomalous nodes, we propose a two-stage method: (i) modelling of ARP call behaviour via hierarchical time series prediction methods, and (ii) exploiting Extreme Value Theory (EVT) to robustly detect whether deviations from expected behaviour are anomalous. EVT is able to handle heavy-tailed distributions which are exhibited by internet traffic. Empirical evaluations on a real-life dataset containing over 10M ARP calls from 362 nodes show that the proposed method results in considerably reduced number of false positives, addressing the problem of alert fatigue commonly reported by security professionals.</p></details> | |
| **[TESSERA: Temporal Embeddings of Surface Spectra for Earth Representation and Analysis](https://arxiv.org/abs/2506.20380v7)** | 2026-04-12 | <details><summary>Show</summary><p>Satellite Earth-observation (EO) time series in the optical and microwave ranges of the electromagnetic spectrum are often irregular due to orbital patterns and cloud obstruction. Compositing addresses these issues but loses information with respect to vegetation phenology, which is critical for many downstream tasks. Instead, we present TESSERA, a pixel-wise foundation model for multi-modal (Sentinel-1/2) EO time series that learns robust, label-efficient embeddings. During model training, TESSERA uses Barlow Twins and sparse random temporal sampling to enforce invariance to the selection of valid observations. We employ two key regularizers: global shuffling to decorrelate spatial neighborhoods and mix-based regulation to improve invariance under extreme sparsity. We find that for diverse classification, segmentation, and regression tasks, TESSERA embeddings deliver state-of-the-art accuracy with high label efficiency, often requiring only a small task head and minimal computation. To democratize access, adhere to FAIR - principles, and simplify use, we release global, annual, 10m, pixel-wise int8 embeddings together with open weights/code and lightweight adaptation heads, thus providing practical tooling for large-scale retrieval and inference at planetary scale. All code and data are available at: https://github.com/ucam-eo/tessera.</p></details> | |
| **[TS-Haystack: A Multi-Scale Retrieval Benchmark for Time Series Language Models](https://arxiv.org/abs/2602.14200v4)** | 2026-04-12 | <details><summary>Show</summary><p>Time Series Language Models (TSLMs) are emerging as unified models for reasoning over continuous signals in natural language. However, long-context retrieval remains a major limitation: existing models are typically trained and evaluated on short sequences, while real-world time-series sensor streams can span millions of datapoints. This mismatch requires precise temporal localization under strict computational constraints, a regime that is not captured by current benchmarks. We introduce TS-Haystack, a long-context temporal retrieval benchmark comprising ten task types across four categories: direct retrieval, temporal reasoning, multi-step reasoning and contextual anomaly. The benchmark uses controlled needle insertion by embedding short activity bouts into longer longitudinal accelerometer recordings, enabling systematic evaluation across context lengths ranging from seconds to 2 hours per sample. We hypothesize that existing TSLM time series encoders overlook temporal granularity as context length increases, creating a task-dependent effect: compression aids classification but impairs retrieval of localized events. Across multiple model and encoding strategies, we observe a consistent divergence between classification and retrieval behavior. Learned latent compression preserves or improves classification accuracy at compression ratios up to 176$\times$, but retrieval performance degrades with context length, incurring in the loss of temporally localized information. These results highlight the importance of architectural designs that decouple sequence length from computational complexity while preserving temporal fidelity.</p></details> | <details><summary>ICLR ...</summary><p>ICLR TSALM 2026. Benchmark generation code and datasets: https://github.com/AI-X-Labs/TS-Haystack</p></details> |
| **[DBGL: Decay-aware Bipartite Graph Learning for Irregular Medical Time Series Classification](https://arxiv.org/abs/2604.11842v1)** | 2026-04-12 | <details><summary>Show</summary><p>Irregular Medical Time Series play a critical role in the clinical domain to better understand the patient's condition. However, inherent irregularity arising from heterogeneous sampling rates, asynchronous observations, and variable gaps poses key challenges for reliable modeling. Existing methods often distort temporal sampling irregularity and missingness patterns while failing to capture variable decay irregularity, resulting in suboptimal representations. To address these limitations, we introduce DBGL, Decay-Aware Bipartite Graph Learning for Irregular Medical Time Series. DBGL first introduces a patient-variable bipartite graph that simultaneously captures irregular sampling patterns without artificial alignment and adaptively models variable relationships for temporal sampling irregularity modeling, enhancing representation learning. To model variable decay irregularity, DBGL designs a novel node-specific temporal decay encoding mechanism that captures each variable's decay rates based on sampling interval, yielding a more accurate and faithful representation of irregular temporal dynamics. We evaluate the performance of DBGL on four publicly available datasets, and the results show that DBGL outperforms all baselines.</p></details> | |
| **[Non-stationary Diffusion For Probabilistic Time Series Forecasting](https://arxiv.org/abs/2505.04278v3)** | 2026-04-12 | <details><summary>Show</summary><p>Due to the dynamics of underlying physics and external influences, the uncertainty of time series often varies over time. However, existing Denoising Diffusion Probabilistic Models (DDPMs) often fail to capture this non-stationary nature, constrained by their constant variance assumption from the additive noise model (ANM). In this paper, we innovatively utilize the Location-Scale Noise Model (LSNM) to relax the fixed uncertainty assumption of ANM. A diffusion-based probabilistic forecasting framework, termed Non-stationary Diffusion (NsDiff), is designed based on LSNM that is capable of modeling the changing pattern of uncertainty. Specifically, NsDiff combines a denoising diffusion-based conditional generative model with a pre-trained conditional mean and variance estimator, enabling adaptive endpoint distribution modeling. Furthermore, we propose an uncertainty-aware noise schedule, which dynamically adjusts the noise levels to accurately reflect the data uncertainty at each step and integrates the time-varying variances into the diffusion process. Extensive experiments conducted on nine real-world and synthetic datasets demonstrate the superior performance of NsDiff compared to existing approaches. Code is available at https://github.com/wwy155/NsDiff.</p></details> | <details><summary>Accep...</summary><p>Accepted as spotlight poster at ICML</p></details> |
| **[WaveMoE: A Wavelet-Enhanced Mixture-of-Experts Foundation Model for Time Series Forecasting](https://arxiv.org/abs/2604.10544v1)** | 2026-04-12 | <details><summary>Show</summary><p>Time series foundation models (TSFMs) have recently achieved remarkable success in universal forecasting by leveraging large-scale pretraining on diverse time series data. Complementing this progress, incorporating frequency-domain information yields promising performance in enhancing the modeling of complex temporal patterns, such as periodicity and localized high-frequency dynamics, which are prevalent in real-world time series. To advance this direction, we propose a new perspective that integrates explicit frequency-domain representations into scalable foundation models, and introduce WaveMoE, a wavelet-enhanced mixture-of-experts foundation model for time series forecasting. WaveMoE adopts a dual-path architecture that jointly processes time series tokens and wavelet tokens aligned along a unified temporal axis, and coordinates them through a shared expert routing mechanism that enables consistent expert specialization while efficiently scaling model capacity. Preliminary experimental results on 16 diverse benchmark datasets indicate that WaveMoE has the potential to further improve forecasting performance by incorporating wavelet-domain corpora.</p></details> | <details><summary>Prese...</summary><p>Presented at ICLR 2026 TSALM Workshop (1st Workshop on Time Series in the Age of Large Models)</p></details> |
| **[Semantic-Enhanced Time-Series Forecasting via Large Language Models](https://arxiv.org/abs/2508.07697v7)** | 2026-04-12 | <details><summary>Show</summary><p>Time series forecasting plays a significant role in finance, energy, meteorology, and IoT applications. Recent studies have leveraged the generalization capabilities of large language models (LLMs) to adapt to time series forecasting, achieving promising performance. However, existing studies focus on token-level modal alignment, instead of bridging the intrinsic modality gap between linguistic knowledge structures and time series data patterns, greatly limiting the semantic representation. To address this issue, we propose a novel Semantic-Enhanced LLM (SE-LLM) that explores the inherent periodicity and anomalous characteristics of time series to embed into the semantic space to enhance the token embedding. This process enhances the interpretability of tokens for LLMs, thereby activating the potential of LLMs for temporal sequence analysis. Moreover, existing Transformer-based LLMs excel at capturing long-range dependencies but are weak at modeling short-term anomalies in time-series data. Hence, we propose a plugin module embedded within self-attention that models long-term and short-term dependencies to effectively adapt LLMs to time-series analysis. Our approach freezes the LLM and reduces the sequence dimensionality of tokens, greatly reducing computational consumption. Experiments demonstrate the superiority performance of our SE-LLM against the state-of-the-art (SOTA) methods.</p></details> | 23 pages,6 figures |
| **[Transformers for dynamical systems learn transfer operators in-context](https://arxiv.org/abs/2602.18679v2)** | 2026-04-12 | <details><summary>Show</summary><p>Large-scale foundation models for scientific machine learning adapt to physical settings unseen during training, such as zero-shot transfer between turbulent scales. This phenomenon, in-context learning, challenges conventional understanding of learning and adaptation in physical systems. Here, we study in-context learning of dynamical systems in a minimal setting: we train a small two-layer, single-head transformer to forecast one dynamical system, and then evaluate its ability to forecast a different dynamical system without retraining. We discover an early tradeoff in training between in-distribution and out-of-distribution performance, which manifests as a secondary double descent phenomenon. We discover that attention-based models apply a transfer-operator forecasting strategy in-context. They (1) lift low-dimensional time series using delay embedding, to detect the system's higher-dimensional dynamical manifold, and (2) identify and forecast long-lived invariant sets that characterize the global flow on this manifold. Our results clarify the mechanism enabling large pretrained models to forecast unseen physical systems at test time without retraining, and they illustrate the unique ability of attention-based models to leverage global attractor information in service of short-term forecasts.</p></details> | 5 pages, 4 figures |
| **[Fourier-KAN-Mamba: A Novel State-Space Equation Approach for Time-Series Anomaly Detection](https://arxiv.org/abs/2511.15083v2)** | 2026-04-12 | <details><summary>Show</summary><p>Time-series anomaly detection plays a critical role in numerous real-world applications, including industrial monitoring and fault diagnosis. Recently, Mamba-based state-space models have shown remarkable efficiency in long-sequence modeling. However, directly applying Mamba to anomaly detection tasks still faces challenges in capturing complex temporal patterns and nonlinear dynamics. In this paper, we propose Fourier-KAN-Mamba, a novel hybrid architecture that integrates Fourier layer, Kolmogorov-Arnold Networks (KAN), and Mamba selective state-space model. The Fourier layer extracts multi-scale frequency features, KAN enhances nonlinear representation capability, and a temporal gating control mechanism further improves the model's ability to distinguish normal and anomalous patterns. Extensive experiments on MSL, SMAP, and SWaT datasets demonstrate that our method significantly outperforms existing state-of-the-art approaches. Keywords: time-series anomaly detection, state-space model, Mamba, Fourier transform, Kolmogorov-Arnold Network</p></details> | <details><summary>We re...</summary><p>We request withdrawal because we identified a flaw in the theoretical analysis of the anomaly-score identification mechanism. This part was supported mainly by metric observations without sufficient visual or empirical verification, which may affect the reliability of the related conclusions</p></details> |
| **[ZARA: Training-Free Motion Time-Series Reasoning via Evidence-Grounded LLM Agents](https://arxiv.org/abs/2508.04038v2)** | 2026-04-12 | <details><summary>Show</summary><p>Motion sensor time-series are central to Human Activity Recognition (HAR), yet conventional approaches are constrained to fixed activity sets and typically require costly parameter retraining to adapt to new behaviors. While Large Language Models (LLMs) offer promising open-set reasoning capabilities, applying them directly to numerical time-series often leads to hallucinations and weak grounding. To address this challenge, we propose ZARA (Zero-training Activity Reasoning Agents), a knowledge- and retrieval-augmented agentic framework for motion time-series reasoning in a training-free inference setting. Rather than relying on black-box projections, ZARA distills reference data into a statistically grounded textual knowledge base that transforms implicit signal patterns into verifiable natural-language priors. Guided by retrieved evidence, ZARA iteratively selects discriminative cues and performs grounded reasoning over candidate activities. Extensive experiments on eight benchmarks show that ZARA generalizes robustly to unseen subjects and across datasets, demonstrating strong transferability across heterogeneous sensor domains. These results mark a step toward trustworthy, plug-and-play motion understanding beyond dataset-specific artifacts. Our code is available at https://github.com/zechenli03/ZARA.</p></details> | <details><summary>Accep...</summary><p>Accepted by ACL 2026 Main Conference</p></details> |
| **[On the Structure of Risk Contribution: A Leave-One-Out Decomposition into Inherent and Correlation Risk](https://arxiv.org/abs/2604.10375v1)** | 2026-04-11 | <details><summary>Show</summary><p>This paper develops a decomposition of standard Risk Contribution (RC) into two economically interpretable components: inherent risk and correlation risk. Using a leave-one-out representation, each position's RC separates into a term reflecting its own volatility contribution independent of the portfolio and a term capturing its covariance with the remainder of the portfolio. The inherent component is always positive, arising from the intrinsic volatility of the position, while the correlation component may amplify or mitigate total portfolio risk depending on how the position moves relative to other holdings. Because the decomposition operates within standard RC, it preserves the property of strict additivity. This separation provides diagnostic insight not visible from aggregate risk contributions alone. It distinguishes whether a position contributes risk because it is volatile in isolation or because it is highly correlated with the rest of the portfolio, and it clarifies when a negatively correlated position functions as an effective hedge. Two approaches to time-series analysis are presented to track how inherent and correlation risk evolve across market regimes, revealing whether changes in portfolio risk during stress periods are driven by volatility shocks, correlation shifts, or both. Empirical illustrations suggest that the decomposition provides stable, transparent, and easily implementable risk diagnostics that can support portfolio risk reporting, stress testing, and performance attribution.</p></details> | <details><summary>Code:...</summary><p>Code: https://github.com/nolanalexander/inherent-correlation-decomposition</p></details> |
| **[Structural Gating and Effect-aligned Lag-resolved Temporal Causal Discovery Framework with Application to Heat-Pollution Extremes](https://arxiv.org/abs/2604.10371v1)** | 2026-04-11 | <details><summary>Show</summary><p>This study proposes Structural Gating and Effect-aligned Discovery for Temporal Causal Discovery (SGED-TCD), a novel and general framework for lag-resolved causal discovery in complex multivariate time series. SGED-TCD combines explicit structural gating, stability-oriented learning, perturbation-effect alignment, and unified graph extraction to improve the interpretability, robustness, and functional consistency of inferred causal graphs. To evaluate its effectiveness in a representative real-world setting, we apply SGED-TCD to teleconnection-driven compound heatwave--air-pollution extremes in eastern and northern China. Using large-scale climate indices, regional circulation and boundary-layer variables, and compound extreme indicators, the framework reconstructs weighted causal networks with explicit dominant lags and relative causal importance. The inferred networks reveal clear regional and seasonal heterogeneity: warm-season extremes in Eastern China are mainly linked to low-latitude oceanic variability through circulation, radiation, and ventilation pathways, whereas cold-season extremes in Northern China are more strongly governed by high-latitude circulation variability associated with boundary-layer suppression and persistent stagnation. These results show that SGED-TCD can recover physically interpretable, hierarchical, and lag-resolved causal pathways in a challenging climate--environment system. More broadly, the proposed framework is not restricted to the present application and provides a general basis for temporal causal discovery in other complex domains.</p></details> | |
| **[On testing for independence between generalized error models of several time series](https://arxiv.org/abs/2410.24003v5)** | 2026-04-11 | <details><summary>Show</summary><p>We define generalized innovations associated with generalized error models having arbitrary distributions, that is, distributions that can be mixtures of continuous and discrete distributions. These models include stochastic volatility models and regime-switching models. We also propose statistics for testing independence between the generalized errors of these models, extending previous results of Duchesne, Ghoudi and Remillard (2012) obtained for stochastic volatility models. We define families of empirical processes constructed from lagged generalized errors, and we show that their joint asymptotic distributions are Gaussian and independent of the estimated parameters of the individual time series. Moebius transformations of the empirical processes are used to obtain tractable covariances. Several tests statistics are then proposed, based on Cramer-von Mises statistics and dependence measures, as well as graphical methods to visualize the dependence. In addition, numerical experiments are performed to assess the power of the proposed tests. Finally, to show the usefulness of our methodologies, examples of applications for financial data and crime data are given to cover both discrete and continuous cases. ll developed methodologies are implemented in the CRAN package IndGenErrors.</p></details> | |
| **[Detecting Invariant Manifolds in ReLU-Based RNNs](https://arxiv.org/abs/2510.03814v4)** | 2026-04-11 | <details><summary>Show</summary><p>Recurrent Neural Networks (RNNs) have found widespread applications in machine learning for time series prediction and dynamical systems reconstruction, and experienced a recent renaissance with improved training algorithms and architectural designs. Understanding why and how trained RNNs produce their behavior is important for scientific and medical applications, and explainable AI more generally. An RNN's dynamical repertoire depends on the topological and geometrical properties of its state space. Stable and unstable manifolds of periodic points play a particularly important role: They dissect a dynamical system's state space into different basins of attraction, and their intersections lead to chaotic dynamics with fractal geometry. Here we introduce a novel algorithm for detecting these manifolds, with a focus on piecewise-linear RNNs (PLRNNs) employing rectified linear units (ReLUs) as their activation function. We demonstrate how the algorithm can be used to trace the boundaries between different basins of attraction, and hence to characterize multistability, a computationally important property. We further show its utility in finding so-called homoclinic points, the intersections between stable and unstable manifolds, and thus establish the existence of chaos in PLRNNs. Finally we show for an empirical example, electrophysiological recordings from a cortical neuron, how insights into the underlying dynamics could be gained through our method.</p></details> | |
| **[TimeSeriesExamAgent: Creating Time Series Reasoning Benchmarks at Scale](https://arxiv.org/abs/2604.10291v1)** | 2026-04-11 | <details><summary>Show</summary><p>Large Language Models (LLMs) have shown promising performance in time series modeling tasks, but do they truly understand time series data? While multiple benchmarks have been proposed to answer this fundamental question, most are manually curated and focus on narrow domains or specific skill sets. To address this limitation, we propose scalable methods for creating comprehensive time series reasoning benchmarks that combine the flexibility of templates with the creativity of LLM agents. We first develop TimeSeriesExam, a multiple-choice benchmark using synthetic time series to evaluate LLMs across five core reasoning categories: pattern recognitionnoise understandingsimilarity analysisanomaly detection, and causality. Then, with TimeSeriesExamAgent, we scale our approach by automatically generating benchmarks from real-world datasets spanning healthcare, finance and weather domains. Through multi-dimensional quality evaluation, we demonstrate that our automatically generated benchmarks achieve diversity comparable to manually curated alternatives. However, our experiments reveal that LLM performance remains limited in both abstract time series reasoning and domain-specific applications, highlighting ongoing challenges in enabling effective time series understanding in these models. TimeSeriesExamAgent is available at https://github.com/magwiazda/TimeSeriesExamAgent.</p></details> | |
| **[A Heavy-Load-Enhanced and Changeable-Periodicity-Perceived Workload Prediction Network](https://arxiv.org/abs/2308.01917v3)** | 2026-04-11 | <details><summary>Show</summary><p>Cloud providers can greatly benefit from accurate workload prediction. However, the workload of cloud servers is highly variable, with occasional workload bursts, which makes workload prediction challenging. The time series forecasting methods relying on periodicity information, often assume fixed and known periodicity length, which does not align with the periodicity-changeable nature of cloud service workloads. Although many state-of-the-art time-series forecasting methods do not rely on periodicity information and achieve high overall accuracy, they are vulnerable to data imbalance between heavy workloads and regular workloads. As a result, their prediction accuracy on rare heavy workloads is limited. Unfortunately, heavyload-prediction accuracy is more important than overall one, as errors in heavyload prediction are more likely to cause Service Level Agreement violations than errors in normal-load prediction. Thus, we propose a changeable-periodicity-perceived workload prediction network (PePNet) to fuse periodic information adaptively for periodicity-changeable time series and improve rare heavy workload prediction accuracy. It has two distinctive characteristics: (i) A Periodicity-Perceived Mechanism to detect the periodicity length automatically and fuses periodic information adaptively, which is suitable for periodicity-changeable time series, and (ii) An Achilles' Heel Loss Function that is used to iteratively optimize the most under-fitting part in predicting sequence for each step, thus evidently improving the prediction accuracy of heavy load. Extensive experiments conducted on real-world datasets demonstrate that PePNet improves accuracy for overall workload by 11.8% averagely, compared with state-of-the-art methods. Especially, PePNet improves accuracy for heavy workload by 21.0% averagely.</p></details> | <details><summary>Submi...</summary><p>Submitted to TII 2026</p></details> |
| **[DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignment](https://arxiv.org/abs/2510.24574v2)** | 2026-04-11 | <details><summary>Show</summary><p>Training time-series forecasting models requires aligning the conditional distribution of model forecasts with that of the label sequence. The standard direct forecast (DF) approach resorts to minimizing the conditional negative log-likelihood, typically estimated by the mean squared error. However, this estimation proves biased when the label sequence exhibits autocorrelation. In this paper, we propose DistDF, which achieves alignment by minimizing a distributional discrepancy between the conditional distributions of forecast and label sequences. Since such conditional discrepancies are difficult to estimate from finite time-series observations, we introduce a joint-distribution Wasserstein discrepancy for time-series forecasting, which provably upper bounds the conditional discrepancy of interest. The proposed discrepancy is tractable, differentiable, and readily compatible with gradient-based optimization. Extensive experiments show that DistDF improves diverse forecasting models and achieves leading performance. Code is available at https://anonymous.4open.science/r/DistDF-F66B.</p></details> | |
| **[Predicting Associations between Solar Flares and Coronal Mass Ejections Using SDO/HMI Magnetograms and a Hybrid Neural Network](https://arxiv.org/abs/2604.10016v1)** | 2026-04-11 | <details><summary>Show</summary><p>Solar eruptions, including flares and coronal mass ejections (CMEs), have a significant impact on Earth. Some flares are associated with CMEs, and some flares are not. The association between flares and CMEs is not always obvious. In this study, we propose a new deep learning method, specifically a hybrid neural network (HNN) that combines a vision transformer with long short-term memory, to predict associations between flares and CMEs. HNN finds spatio-temporal patterns in the time series of line-of-sight magnetograms of solar active regions (ARs) collected by the Helioseismic and Magnetic Imager on board the Solar Dynamics Observatory and uses the patterns to predict whether a flare projected to occur within the next 24 hours will be eruptive (i.e., CME-associated) or confined (i.e., not CME-associated). Our experimental results demonstrate the good performance of the HNN method. Furthermore, the results show that magnetic flux cancellation in polarity inversion line regions may well play a role in triggering flare-associated CMEs, a finding consistent with literature.</p></details> | 14 pages, 8 figures |
| **[A Weak Penalty Neural ODE for Learning Chaotic Dynamics from Noisy Time Series](https://arxiv.org/abs/2511.06609v3)** | 2026-04-10 | <details><summary>Show</summary><p>The accurate forecasting of complex, high-dimensional dynamical systems from observational data is a fundamental task across numerous scientific and engineering disciplines. A significant challenge arises from noise-corrupted measurements, which severely degrade the performance of data-driven models. In chaotic dynamical systems, where small initial errors amplify exponentially, it is particularly difficult to develop a model from noisy data that achieves short-term accuracy while preserving long-term invariant properties. To overcome this, we consider the weak formulation as a complementary approach to the classical $L2$-loss function for training models of dynamical systems. We empirically verify that the weak formulation, with a proper choice of test function and integration domain, effectively filters noisy data. This insight explains why a weak form loss function is analogous to fitting a model to filtered data and provides a practical way to parameterize the weak form. Subsequently, we demonstrate how this approach overcomes the instability and inaccuracy of standard Neural ODE (NODE) in modeling chaotic systems. Through numerical examples, we show that our proposed training strategy, the Weak Penalty NODE, is computationally efficient, solver-agnostic, and yields accurate and robust forecasts across benchmark chaotic systems and a real-world climate dataset.</p></details> | |
| **[LLM4Delay: Flight Delay Prediction via Cross-Modality Adaptation of Large Language Models and Aircraft Trajectory Representation](https://arxiv.org/abs/2510.23636v3)** | 2026-04-10 | <details><summary>Show</summary><p>Flight delay prediction has become a key focus in air traffic management (ATM), as delays reflect inefficiencies in the system. This paper proposes LLM4Delay, a large language model (LLM)-based framework for predicting flight delays from the perspective of air traffic controllers monitoring aircraft after they enter the terminal maneuvering area (TMA). LLM4Delay is designed to integrate textual aeronautical information, including flight data, weather reports, and aerodrome notices, together with multiple trajectories that model airspace conditions, forming a comprehensive delay-relevant context. By jointly leveraging comprehensive textual and trajectory contexts via instance-level projection, an effective cross-modality adaptation strategy that maps multiple instance-level trajectory representations into the language modality, the framework improves delay prediction accuracy. LLM4Delay demonstrates superior performance compared to existing ATM frameworks and prior time-series-to-language adaptation methods. This highlights the complementary roles of textual and trajectory data while leveraging knowledge from both the pretrained trajectory encoder and the pretrained LLM. The proposed framework enables continuous updates to predictions as new information becomes available, indicating potential operational relevance.</p></details> | <details><summary>Prepr...</summary><p>Preprint submitted to IEEE Transactions on Intelligent Transportation Systems (T-ITS) for possible publication</p></details> |
| **[A scalable estimator of higher-order information in complex dynamical systems](https://arxiv.org/abs/2506.18498v2)** | 2026-04-10 | <details><summary>Show</summary><p>Our understanding of complex systems rests on our ability to characterise how they perform distributed computation and integrate information. Advances in information theory have introduced several quantities to describe complex information structures, where collective patterns of coordination emerge from higher-order (i.e. beyond-pairwise) interdependencies. Unfortunately, the use of these approaches to study large complex systems is severely hindered by the poor scalability of existing techniques. Moreover, there are relatively few measures specifically designed for multivariate time series data. Here we introduce a novel measure of information about macroscopic structures, termed M-information, which quantifies the higher-order integration of information in complex dynamical systems. We show that M-information can be calculated via a convex optimisation problem, and we derive a robust and efficient algorithm that scales gracefully with system size. Our analyses show that M-information is resilient to noise, indexes critical behaviour in artificial neuronal populations, and reflects states of consciousness and task performance in real-world macaque and mouse neuroimaging data. Furthermore, M-information can be incorporated into existing information decomposition frameworks to reveal a comprehensive taxonomy of information dynamics. Taken together, these results help us unravel collective computation in large complex systems.</p></details> | <details><summary>12 pa...</summary><p>12 pages, 5 figures + appendix</p></details> |
| **[Drift-Aware Online Dynamic Learning for Nonstationary Multivariate Time Series: Application to Sintering Quality Prediction](https://arxiv.org/abs/2604.09358v1)** | 2026-04-10 | <details><summary>Show</summary><p>Accurate prediction of nonstationary multivariate time series remains a critical challenge in complex industrial systems such as iron ore sintering. In practice, pronounced concept drift compounded by significant label verification latency rapidly degrades the performance of offline-trained models. Existing methods based on static architectures or passive update strategies struggle to simultaneously extract multi-scale spatiotemporal features and overcome the stability-plasticity dilemma without immediate supervision. To address these limitations, a Drift-Aware Multi-Scale Dynamic Learning (DA-MSDL) framework is proposed to maintain robust multi-output predictive performance via online adaptive mechanisms on nonstationary data streams. The framework employs a multi-scale bi-branch convolutional network as its backbone to disentangle local fluctuations from long-term trends, thereby enhancing representational capacity for complex dynamic patterns. To circumvent the label latency bottleneck, DA-MSDL leverages Maximum Mean Discrepancy (MMD) for unsupervised drift detection. By quantifying online statistical deviations in feature distributions, DA-MSDL proactively triggers model adaptation prior to inference. Furthermore, a drift-severity-guided hierarchical fine-tuning strategy is developed. Supported by prioritized experience replay from a dynamic memory queue, this approach achieves rapid distribution alignment while effectively mitigating catastrophic forgetting. Long-horizon experiments on real-world industrial sintering data and a public benchmark dataset demonstrate that DA-MSDL consistently outperforms representative baselines under severe concept drift. Exhibiting strong cross-domain generalization and predictive stability, the proposed framework provides an effective online dynamic learning paradigm for quality monitoring in nonstationary environments.</p></details> | |
| **[QARIMA: A Quantum Approach To Classical Time Series Analysis](https://arxiv.org/abs/2604.08277v2)** | 2026-04-10 | <details><summary>Show</summary><p>We present a quantum-inspired ARIMA methodology that integrates quantum-assisted lag discovery with fixed-configuration variational quantum circuits (VQCs) for parameter estimation and weak-lag refinement. Differencing and candidate lags are identified via swap-test-driven quantum autocorrelation (QACF) and quantum partial autocorrelation (QPACF), with a delayed-matrix construction that aligns quantum projections to time-domain regressors, followed by standard information-criterion parsimony. Given the screened orders (p,d,q), we retain a fixed VQC ansatz, optimizer, and training budget, preventing hyperparameter leakage, and deploy the circuit in two estimation roles: VQC-AR for autoregressive coefficients and VQC-MA for moving-average coefficients. Between screening and estimation, a lightweight VQC weak-lag refinement re-weights or prunes screened AR lags without altering (p,d,q). Across environmental and industrial datasets, we perform rolling-origin evaluations against automated classical ARIMA, reporting out-of-sample mean squared error (MSE), mean absolute percentage error (MAPE), and Diebold-Mariano tests on MSE and MAE. Empirically, the seven quantum contributions (1) differencing selection, (2) QACF, (3) QPACF, (4) swap-test primitives with delayed-matrix construction, (5) VQC-AR, (6) VQC weak-lag refinement, and (7) VQC-MA collectively reduce meta-optimization overhead and make explicit where quantum effects enter order discovery, lag refinement, and AR/MA parameter estimation.</p></details> | <details><summary>17 Al...</summary><p>17 Algorithms, 19 Figures , 26 Tables</p></details> |
| **[BEDTime: A Unified Benchmark for Automatically Describing Time Series](https://arxiv.org/abs/2509.05215v3)** | 2026-04-10 | <details><summary>Show</summary><p>Recent works propose complex multi-modal models that handle both time series and language, ultimately claiming high performance on complex tasks like time series reasoning and cross-modal question answering. However, they skip foundational evaluations that such complex models should have mastered. So we ask a simple question: \textit{How well can recent models describe structural properties of time series?} To answer this, we propose that successful models should be able to \textit{recognize}, \textit{differentiate}, and \textit{generate} descriptions of univariate time series. We then create \textbf{\benchmark}, a benchmark to assess these novel tasks, that comprises \textbf{five datasets} reformatted across \textbf{three modalities}. In evaluating \textbf{17 state-of-the-art models}, we find that (1) surprisingly, dedicated time series-language models fall short, despite being designed for similar tasks, (2) vision language models are quite capable, (3) language only methods perform worst, despite many lauding their potential, and (4) all approaches are clearly fragile to a range of real world robustness tests, indicating directions for future work. Together, our findings critique prior works' claims and provide avenues for advancing multi-modal time series modeling.</p></details> | |
| **[Batch Distillation Data for Developing Machine Learning Anomaly Detection Methods](https://arxiv.org/abs/2510.18075v2)** | 2026-04-10 | <details><summary>Show</summary><p>Machine learning (ML) holds great potential to advance anomaly detection (AD) in chemical processes. However, the development of ML-based methods is hindered by the lack of openly available experimental data. To address this gap, we have set up a laboratory-scale batch distillation plant and operated it to generate an extensive experimental database, covering fault-free experiments and experiments in which anomalies were intentionally induced, for training advanced ML-based AD methods. In total, 119 experiments were conducted across a wide range of operating conditions and mixtures. Most experiments containing anomalies were paired with a corresponding fault-free one. The database that we provide here includes time-series data from numerous sensors and actuators, along with estimates of measurement uncertainty. In addition, unconventional data sources -- such as concentration profiles obtained via online benchtop NMR spectroscopy and video and audio recordings -- are provided. Extensive metadata and expert annotations of all experiments are included. The anomaly annotations are based on an ontology developed in this work. The data are organized in a structured database and made freely available via doi.org/10.5281/zenodo.17395543. This new database paves the way for the development of advanced ML-based AD methods. As it includes information on the causes of anomalies, it further enables the development of interpretable and explainable ML approaches, as well as methods for anomaly mitigation.</p></details> | |
| **[AR-KAN: Autoregressive-Weight-Enhanced Kolmogorov-Arnold Network for Time Series Forecasting](https://arxiv.org/abs/2509.02967v3)** | 2026-04-10 | <details><summary>Show</summary><p>Traditional neural networks struggle to capture the spectral structure of complex signals. Fourier neural networks (FNNs) attempt to address this by embedding Fourier series components, yet many real-world signals are almost-periodic with non-commensurate frequencies, posing additional challenges. Building on prior work showing that ARIMA outperforms large language models (LLMs) for time series forecasting, we extend the comparison to neural predictors and find that ARIMA still maintains a clear advantage. Inspired by this finding, we propose the Autoregressive-Weight-Enhanced Kolmogorov-Arnold Network (AR-KAN). Based in the Universal Myopic Mapping Theorem, it integrates a pre-trained AR module for temporal memory with a KAN for nonlinear representation. We prove that the AR module preserves essential temporal features while reducing redundancy, and that the upper bound of the approximation error for AR-KAN is smaller than that for KAN in a probabilistic sense. Experimental results also demonstrate that AR-KAN delivers exceptional performance compared to existing models, both on synthetic almost-periodic functions and real-world datasets. These results highlight AR-KAN as a robust and effective framework for time series forecasting. Our code is available at https://github.com/ChenZeng001/AR-KAN.</p></details> | |
| **[Temporal Patch Shuffle (TPS): Leveraging Patch-Level Shuffling to Boost Generalization and Robustness in Time Series Forecasting](https://arxiv.org/abs/2604.09067v1)** | 2026-04-10 | <details><summary>Show</summary><p>Data augmentation is a crucial technique for improving model generalization and robustness, particularly in deep learning models where training data is limited. Although many augmentation methods have been developed for time series classification, most are not directly applicable to time series forecasting due to the need to preserve temporal coherence. In this work, we propose Temporal Patch Shuffle (TPS), a simple and model-agnostic data augmentation method for forecasting that extracts overlapping temporal patches, selectively shuffles a subset of patches using variance-based ordering as a conservative heuristic, and reconstructs the sequence by averaging overlapping regions. This design increases sample diversity while preserving forecast-consistent local temporal structure. We extensively evaluate TPS across nine long-term forecasting datasets using five recent model families (TSMixer, DLinear, PatchTST, TiDE, and LightTS), and across four short-term forecasting datasets using PatchTST, observing consistent performance improvements. Comprehensive ablation studies further demonstrate the effectiveness, robustness, and design rationale of the proposed method.</p></details> | <details><summary>25 pa...</summary><p>25 pages, 7 figures, 17 tables</p></details> |
| **[TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis](https://arxiv.org/abs/2410.04047v6)** | 2026-04-10 | <details><summary>Show</summary><p>Time series analysis is crucial in real-world applications, yet traditional methods focus on isolated tasks only, and recent studies on time series reasoning remain limited to either single-step inference or are constrained to natural language answers. In this work, we introduce TS-Reasoner, a domain-specialized agent designed for multi-step time series inference. By integrating large language model (LLM) reasoning with domain-specific computational tools and an error feedback loop, TS-Reasoner enables domain-informed, constraint-aware analytical workflows that combine symbolic reasoning with precise numerical analysis. We assess the system's capabilities along two axes: (1) fundamental time series understanding assessed by TimeSeriesExam and (2) complex, multi-step inference evaluated by a newly proposed dataset designed to test both compositional reasoning and computational precision in time series analysis. Experiments show that our approach outperforms standalone general-purpose LLMs in both basic time series concept understanding as well as the multi-step time series inference task, highlighting the promise of domain-specialized agents for automating real-world time series reasoning and analysis.</p></details> | |
| **[Lightweight and Generalizable Multi-Sensor Human Activity Recognition via Cascaded Fusion and Style-Augmented Decomposition](https://arxiv.org/abs/2604.08910v1)** | 2026-04-10 | <details><summary>Show</summary><p>Wearable Human Activity Recognition (WHAR) is a prominent research area within ubiquitous computing, whose core lies in effectively modeling intra- and inter-sensor spatio-temporal relationships from multi-modal time series data. Existing methods either suffer from high computational complexity due to attention-based fusion or lack robustness to data variations during feature extraction. To address these issues, we propose a lightweight and generalizable framework that retains the core "decomposition-extraction-fusion" paradigm while introducing two key innovations. First, we replace the computationally expensive Attention and Cross-Variable Fusion (CVF) modules with a Cascaded Fusion Block (CFB), which achieves efficient feature interaction without explicit attention weights through the operational process of "compression-recursion-concatenation-fusion". Second, we integrate a MixStyle-based data augmentation module before the Local Temporal Feature Extraction (LTFE) and Global Temporal Aggregation (GTA) stages. By mixing the mean and variance of different samples within a batch and introducing random coefficients to perturb the data distribution, the model's generalization ability is enhanced without altering the core information of the data. The proposed framework maintains sensor-level, variable-level, and channel-level independence during the decomposition phase, and achieves efficient feature fusion and robust feature extraction in subsequent processes. Experiments on two benchmark datasets (Realdisp, Skoda) demonstrate that our model outperforms state-of-the-art methods in both accuracy and macro-F1 score, while reducing computational overhead by more than 30\% compared to attention-based baselines. This work provides a practical solution for WHAR applications on resource-constrained wearable devices.</p></details> | <details><summary>8 pag...</summary><p>8 pages. arXiv admin note: text overlap with arXiv:2501.10917 by other authors</p></details> |
| **[AlphaCast: A Human Wisdom-LLM Intelligence Co-Reasoning Framework for Interactive Time Series Forecasting](https://arxiv.org/abs/2511.08947v5)** | 2026-04-10 | <details><summary>Show</summary><p>Time series forecasting plays a crucial role in decision-making across many real-world applications. Despite substantial progress, most existing methods still treat forecasting as a static, single-pass regression problem. In contrast, human experts form predictions through iterative reasoning that integrates temporal features, domain knowledge, case-based references, and supplementary context, with continuous refinement. In this work, we propose Alphacast, an interaction-driven agentic reasoning framework that enables accurate time series forecasting with training-free large language models. Alphacast reformulates forecasting as an expert-like process and organizes it into a multi-stage workflow involving context preparation, reasoning-based generation, and reflective evaluation, transforming forecasting from a single-pass output into a multi-turn, autonomous interaction process. To support diverse perspectives commonly considered by human experts, we develop a lightweight toolkit comprising a feature set, a knowledge base, a case library, and a contextual pool that provides external support for LLM-based reasoning. Extensive experiments across multiple benchmarks show that Alphacast generally outperforms representative baselines. Code is available at this repository: https://github.com/echo01-ai/AlphaCast.</p></details> | |
| **[Forecasting the Evolving Composition of Inbound Tourism Demand: A Bayesian Compositional Time Series Approach Using Platform Booking Data](https://arxiv.org/abs/2602.18358v3)** | 2026-04-09 | <details><summary>Show</summary><p>Understanding how the composition of guest origin markets evolves over time is critical for destination marketing organizations, hospitality businesses, and tourism planners. We develop and apply Bayesian Dirichlet autoregressive moving average (BDARMA) models to forecast the compositional dynamics of guest origin market shares using proprietary Airbnb booking data spanning 2017--2025 across four major destination regions. Our analysis reveals substantial pandemic-induced structural breaks in origin composition, with heterogeneous recovery patterns across markets. In our analysis, the BDARMA framework achieves the lowest forecast error for EMEA and competitive performance across destination regions, outperforming standard benchmarks including naïve forecasts, exponential smoothing, and SARIMA on log-ratio transformed data in compositionally complex markets. For EMEA destinations, BDARMA achieves 27% lower forecast error than naïve methods ($p < 0.001$), with the greatest gains where multiple origin markets compete in the 5-25% share range. By modeling compositions directly on the simplex with a Dirichlet likelihood and incorporating seasonal variation in both mean and precision parameters, our approach produces coherent forecasts that respect the unit-sum constraint while capturing complex temporal dependencies. The methodology provides destination stakeholders with probabilistic forecasts of source market shares, enabling more informed strategic planning for marketing resource allocation, infrastructure investment, and crisis response.</p></details> | |
| **[StationarityToolkit: Comprehensive Time Series Stationarity Analysis in Python](https://arxiv.org/abs/2604.08676v1)** | 2026-04-09 | <details><summary>Show</summary><p>Time-series stationarity is a property that statistical characteristics such as trend, variance, seasonality remain constant over time. It is considered fundamental to many forecasting and analysis methods. Different tests detect different types of non-stationarity: structural breaks or deterministic trends, clustered or time-dependent variance, stochastic or deterministic seasonality. A series might pass one test while failing another; single-test approaches seldom distinguish between conceptually different types of non-stationarity that require different types of tests and transformations. `StationarityToolkit` addresses this by providing a comprehensive Python library that runs 10 statistical tests across three categories: trend (4 tests), variance (4 tests), and seasonality (2 tests). Rather than a binary stationary/non-stationary verdict, users receive detailed diagnostics with actionable notes for each detection. The toolkit automatically infers the frequency of the data provided (requires datetime index), provides clear interpretations with test statistics and p-values, and supports an iterative test-transform-retest workflow essential for real-world data sets.</p></details> | <details><summary>Submi...</summary><p>Submitted to Journal of Open Source Software</p></details> |
| **[Zero-shot Multivariate Time Series Forecasting Using Tabular Prior Fitted Networks](https://arxiv.org/abs/2604.08400v1)** | 2026-04-09 | <details><summary>Show</summary><p>Tabular foundation models, particularly Prior-data Fitted Networks like TabPFN have emerged as the leading contender in a myriad of tasks ranging from data imputation to label prediction on the tabular data format surpassing the historical successes of tree-based models. This has led to investigations on their applicability to forecasting time series data which can be formulated as a tabular problem. While recent work to this end has displayed positive results, most works have limited their treatment of multivariate time series problems to several independent univariate time series forecasting subproblems, thus ignoring any inter-channel interactions. Overcoming this limitation, we introduce a generally applicable framework for multivariate time series forecasting using tabular foundation models. We achieve this by recasting the multivariate time series forecasting problem as a series of scalar regression problems which can then be solved zero-shot by any tabular foundation model with regression capabilities. We present results of our method using the TabPFN-TS backbone and compare performance with the current state of the art tabular methods.</p></details> | |
| **[ADAPTive Input Training for Many-to-One Pre-Training on Time-Series Classification](https://arxiv.org/abs/2604.08398v1)** | 2026-04-09 | <details><summary>Show</summary><p>Recent work on time-series models has leveraged self-supervised training to learn meaningful features and patterns in order to improve performance on downstream tasks and generalize to unseen modalities. While these pretraining methods have shown great promise in one-to-many scenarios, where a model is pre-trained on one dataset and fine-tuned on a downstream dataset, they have struggled to generalize to new datasets when more datasets are added during pre-training. This is a fundamental challenge in building foundation models for time-series data, as it limits the ability to develop models that can learn from a large variety of diverse datasets available. To address this challenge, we present a new pre-training paradigm for time-series data called ADAPT, which can efficiently align the physical properties of data in the time-series domain, enabling mixed-batch pre-training despite the extreme discrepancies in the input sizes and channel dimensions of pre-training data. We trained on 162 time-series classification datasets and set new state-of-the-art performance for classification benchmarks. We successfully train a model within the time-series domain on a wide range of datasets simultaneously, which is a major building block for building generalist foundation models in time-series domains.</p></details> | |
## Trajectory
| **Title** | **Date** | **Abstract** | **Comment** |
| --- | --- | --- | --- |
| **[LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories](https://arxiv.org/abs/2604.15311v1)** | 2026-04-16 | <details><summary>Show</summary><p>This paper focuses on the alignment of flow matching models with human preferences. A promising way is fine-tuning by directly backpropagating reward gradients through the differentiable generation process of flow matching. However, backpropagating through long trajectories results in prohibitive memory costs and gradient explosion. Therefore, direct-gradient methods struggle to update early generation steps, which are crucial for determining the global structure of the final image. To address this issue, we introduce LeapAlign, a fine-tuning method that reduces computational cost and enables direct gradient propagation from reward to early generation steps. Specifically, we shorten the long trajectory into only two steps by designing two consecutive leaps, each skipping multiple ODE sampling steps and predicting future latents in a single step. By randomizing the start and end timesteps of the leaps, LeapAlign leads to efficient and stable model updates at any generation step. To better use such shortened trajectories, we assign higher training weights to those that are more consistent with the long generation path. To further enhance gradient stability, we reduce the weights of gradient terms with large magnitude, instead of completely removing them as done in previous works. When fine-tuning the Flux model, LeapAlign consistently outperforms state-of-the-art GRPO-based and direct-gradient methods across various metrics, achieving superior image quality and image-text alignment.</p></details> | <details><summary>Accep...</summary><p>Accepted by CVPR 2026. Project page: https://rockeycoss.github.io/leapalign/</p></details> |
| **[OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis](https://arxiv.org/abs/2604.15093v1)** | 2026-04-16 | <details><summary>Show</summary><p>Mobile agents powered by vision-language models have demonstrated impressive capabilities in automating mobile tasks, with recent leading models achieving a marked performance leap, e.g., nearly 70% success on AndroidWorld. However, these systems keep their training data closed and remain opaque about their task and trajectory synthesis recipes. We present OpenMobile, an open-source framework that synthesizes high-quality task instructions and agent trajectories, with two key components: (1) The first is a scalable task synthesis pipeline that constructs a global environment memory from exploration, then leverages it to generate diverse and grounded instructions. and (2) a policy-switching strategy for trajectory rollout. By alternating between learner and expert models, it captures essential error-recovery data often missing in standard imitation learning. Agents trained on our data achieve competitive results across three dynamic mobile agent benchmarks: notably, our fine-tuned Qwen2.5-VL and Qwen3-VL reach 51.7% and 64.7% on AndroidWorld, far surpassing existing open-data approaches. Furthermore, we conduct transparent analyses on the overlap between our synthetic instructions and benchmark test sets, and verify that performance gains stem from broad functionality coverage rather than benchmark overfitting. We release data and code at https://njucckevin.github.io/openmobile/ to bridge the data gap and facilitate broader mobile agent research.</p></details> | Work in progress |
| **[Trajectory Planning for a Multi-UAV Rigid-Payload Cascaded Transportation System Based on Enhanced Tube-RRT*](https://arxiv.org/abs/2604.15074v1)** | 2026-04-16 | <details><summary>Show</summary><p>This paper presents a two-stage trajectory planning framework for a multi-UAV rigid-payload cascaded transportation system, aiming to address planning challenges in densely cluttered environments. In Stage I, an Enhanced Tube-RRT* algorithm is developed by integrating active hybrid sampling and an adaptive expansion strategy, enabling rapid generation of a safe and feasible virtual tube in environments with dense obstacles. Moreover, a trajectory smoothness cost is explicitly incorporated into the edge cost to reduce excessive turns and thereby mitigate cable-induced oscillations. Simulation results demonstrate that the proposed Enhanced Tube-RRT* achieves a higher success rate and effective sampling rate than mixed-sampling Tube-RRT* (STube-RRT*) and adaptive-extension Tube-RRT* (AETube-RRT*), while producing a shorter optimal path with a smaller cumulative turning angle. In Stage II, a convex quadratic program is formulated by considering payload translational and rotational dynamics, cable tension constraints, and collision-safety constraints, yielding a smooth, collision-free desired payload trajectory. Finally, a centralized geometric control scheme is applied to the cascaded system to validate the effectiveness and feasibility of the proposed planning framework, offering a practical solution for payload attitude maneuvering in densely cluttered environments.</p></details> | <details><summary>15 pa...</summary><p>15 pages, 7 figures. Under review at IEEE Transactions on Aerospace and Electronic Systems (TAES). This work has been submitted to the IEEE for possible publication</p></details> |
| **[Predicting Power-System Dynamic Trajectories with Foundation Models](https://arxiv.org/abs/2604.14991v1)** | 2026-04-16 | <details><summary>Show</summary><p>As power systems transition toward renewable-rich and inverter-dominated operations, accurate time-domain dynamic analysis becomes increasingly critical. Such analysis supports key operational tasks, including transient stability assessment, dynamic security analysis, contingency screening, and post-fault trajectory evaluation. In practice, these tasks may operate under several challenges, including unknown and time-varying system parameters, privacy constraints on data sharing, and the need for fast online inference. Existing learning-based approaches are typically trained for individual systems and therefore lack generalization across operating conditions and physical parameters. Hence, this paper proposes LArge Scale Small ODE (LASS)-ODE-Power, a learning framework for general-purpose time-domain prediction. The proposed approach leverages large-scale pretraining on more than 40 GB of DAE or ordinary differential-equation (ODE) trajectories to learn transferable representations. The resulting model supports trajectory prediction from short measurement prefixes across diverse dynamic regimes, including electromechanical and inverter-driven systems. Hence, the model can be directly used without data sharing in a zero-shot setting. In addition, the proposed architecture incorporates parallel and linearized computation to achieve fast inference. Moreover, to enhance task-specific performance in power systems, a specialized fine-tuning strategy is developed based on approximately 1 GB of heterogeneous power-system dynamic data. Extensive experiments over diverse power-system simulation scenarios demonstrate that LASS-ODE-Power consistently outperforms existing learning-based models in trajectory prediction accuracy with efficient inference.</p></details> | 10 pages |
| **[Momentum-constrained Hybrid Heuristic Trajectory Optimization Framework with Residual-enhanced DRL for Visually Impaired Scenarios](https://arxiv.org/abs/2604.14986v1)** | 2026-04-16 | <details><summary>Show</summary><p>Safe and efficient assistive planning for visually impaired scenarios remains challenging, since existing methods struggle with multi-objective optimization, generalization, and interpretability. In response, this paper proposes a Momentum-Constrained Hybrid Heuristic Trajectory Optimization Framework (MHHTOF). To balance multiple objectives of comfort and safety, the framework designs a Heuristic Trajectory Sampling Cluster (HTSC) with a Momentum-Constrained Trajectory Optimization (MTO), which suppresses abrupt velocity and acceleration changes. In addition, a novel residual-enhanced deep reinforcement learning (DRL) module refines candidate trajectories, advancing temporal modeling and policy generalization. Finally, a dual-stage cost modeling mechanism (DCMM) is introduced to regulate optimization, where costs in the Frenet space ensure consistency, and reward-driven adaptive weights in the Cartesian space integrate user preferences for interpretability and user-centric decision-making. Experimental results show that the proposed framework converges in nearly half the iterations of baselines and achieves lower and more stable costs. In complex dynamic scenarios, MHHTOF further demonstrates stable velocity and acceleration curves with reduced risk, confirming its advantages in robustness, safety, and efficiency.</p></details> | <details><summary>24 pa...</summary><p>24 pages, 14 figures. arXiv admin note: text overlap with arXiv:2509.15582</p></details> |
| **[Reward-Aware Trajectory Shaping for Few-step Visual Generation](https://arxiv.org/abs/2604.14910v1)** | 2026-04-16 | <details><summary>Show</summary><p>Achieving high-fidelity generation in extremely few sampling steps has long been a central goal of generative modeling. Existing approaches largely rely on distillation-based frameworks to compress the original multi-step denoising process into a few-step generator. However, such methods inherently constrain the student to imitate a stronger multi-step teacher, imposing the teacher as an upper bound on student performance. We argue that introducing \textbf{preference alignment awareness} enables the student to optimize toward reward-preferred generation quality, potentially surpassing the teacher instead of being restricted to rigid teacher imitation. To this end, we propose \textbf{Reward-Aware Trajectory Shaping (RATS)}, a lightweight framework for preference-aligned few-step generation. Specifically, teacher and student latent trajectories are aligned at key denoising stages through horizon matching, while a \textbf{reward-aware gate} is introduced to adaptively regulate teacher guidance based on their relative reward performance. Trajectory shaping is strengthened when the teacher achieves higher rewards, and relaxed when the student matches or surpasses the teacher, thereby enabling continued reward-driven improvement. By seamlessly integrating trajectory distillation, reward-aware gating, and preference alignment, RATS effectively transfers preference-relevant knowledge from high-step generators without incurring additional test-time computational overhead. Experimental results demonstrate that RATS substantially improves the efficiency--quality trade-off in few-step visual generation, significantly narrowing the gap between few-step students and stronger multi-step generators.</p></details> | |
| **[Benchmarks for Trajectory Safety Evaluation and Diagnosis in OpenClaw and Codex: ATBench-Claw and ATBench-CodeX](https://arxiv.org/abs/2604.14858v1)** | 2026-04-16 | <details><summary>Show</summary><p>As agent systems move into increasingly diverse execution settings, trajectory-level safety evaluation and diagnosis require benchmarks that evolve with them. ATBench is a diverse and realistic agent trajectory benchmark for safety evaluation and diagnosis. This report presents ATBench-Claw and ATBench-CodeX, two domain-customized extensions that carry ATBench into the OpenClaw and OpenAI Codex / Codex-runtime settings. The key adaptation mechanism is to analyze each new setting, customize the three-dimensional Safety Taxonomy over risk source, failure mode, and real-world harm, and then use that customized taxonomy to define the benchmark specification consumed by the shared ATBench construction pipeline. This extensibility matters because agent frameworks remain relatively stable at the architectural level even as their concrete execution settings, tool ecosystems, and product capabilities evolve quickly. Concretely, ATBench-Claw targets OpenClaw-sensitive execution chains over tools, skills, sessions, and external actions, while ATBench-CodeX targets trajectories in the OpenAI Codex / Codex-runtime setting over repositories, shells, patches, dependencies, approvals, and runtime policy boundaries. Our emphasis therefore falls on taxonomy customization, domain-specific risk coverage, and benchmark design under a shared ATBench generation framework.</p></details> | 18 pages, 3 figures |
| **[Trajectory-based actuator identification via differentiable simulation](https://arxiv.org/abs/2604.10351v2)** | 2026-04-16 | <details><summary>Show</summary><p>Accurate actuation models are critical for bridging the gap between simulation and real robot behavior, yet obtaining high-fidelity actuator dynamics typically requires dedicated test stands and torque sensing. We present a trajectory-based actuator identification method that uses differentiable simulation to fit system-level actuator models from encoder motion alone. Identification is posed as a trajectory-matching problem: given commanded joint positions and measured joint angles and velocities, we optimize actuator and simulator parameters by backpropagating through the simulator, without torque sensors, current/voltage measurements, or access to embedded motor-control internals. The framework supports multiple model classes, ranging from compact structured parameterizations to neural actuator mappings, within a unified optimization pipeline. On held-out real-robot trajectories for a high-gear-ratio actuator with an embedded PD controller, the proposed torque-sensor-free identification achieves much tighter trajectory alignment than a supervised stand-trained baseline dominated by steady-state data, reducing mean absolute position error from 14.20 mrad to as low as 7.54 mrad (1.88 times). Finally, we demonstrate downstream impact for the same actuator class in a real-robot locomotion study: training policies with the refined actuator model increases travel distance by 46% and reduces rotational deviation by 75% relative to the baseline.</p></details> | |
| **[Tora3: Trajectory-Guided Audio-Video Generation with Physical Coherence](https://arxiv.org/abs/2604.09057v2)** | 2026-04-16 | <details><summary>Show</summary><p>Audio-video (AV) generation has recently made strong progress in perceptual quality and multimodal coherence, yet generating content with plausible motion-sound relations remains challenging. Existing methods often produce object motions that are visually unstable and sounds that are only loosely aligned with salient motion or contact events, largely because they lack an explicit motion-aware structure shared by video and audio generation. We present Tora3, a trajectory-guided AV generation framework that improves physical coherence by using object trajectories as a shared kinematic prior. Rather than treating trajectories as a video-only control signal, Tora3 uses them to jointly guide visual motion and acoustic events. Specifically, we design a trajectory-aligned motion representation for video, a kinematic-audio alignment module driven by trajectory-derived second-order kinematic states, and a hybrid flow matching scheme that preserves trajectory fidelity in trajectory-conditioned regions while maintaining local coherence elsewhere. We further curate PAV, a large-scale AV dataset emphasizing motion-relevant patterns with automatically extracted motion annotations. Extensive experiments show that Tora3 improves motion realism, motion-sound synchronization, and overall AV generation quality over strong open-source baselines.</p></details> | <details><summary>12 pa...</summary><p>12 pages, 5 tables, 5 figures</p></details> |
| **[FinTrace: Holistic Trajectory-Level Evaluation of LLM Tool Calling for Long-Horizon Financial Tasks](https://arxiv.org/abs/2604.10015v2)** | 2026-04-15 | <details><summary>Show</summary><p>Recent studies demonstrate that tool-calling capability enables large language models (LLMs) to interact with external environments for long-horizon financial tasks. While existing benchmarks have begun evaluating financial tool calling, they focus on limited scenarios and rely on call-level metrics that fail to capture trajectory-level reasoning quality. To address this gap, we introduce FinTrace, a benchmark comprising 800 expert-annotated trajectories spanning 34 real-world financial task categories across multiple difficulty levels. FinTrace employs a rubric-based evaluation protocol with nine metrics organized along four axes -- action correctness, execution efficiency, process quality, and output quality -- enabling fine-grained assessment of LLM tool-calling behavior. Our evaluation of 13 LLMs reveals that while frontier models achieve strong tool selection, all models struggle with information utilization and final answer quality, exposing a critical gap between invoking the right tools and reasoning effectively over their outputs. To move beyond diagnosis, we construct FinTrace-Training, the first trajectory-level preference dataset for financial tool-calling, containing 8,196 curated trajectories with tool-augmented contexts and preference pairs. We fine-tune Qwen-3.5-9B using supervised fine-tuning followed by direct preference optimization (DPO) and show that training on FinTrace-Training consistently improves intermediate reasoning metrics, with DPO more effectively suppressing failure modes. However, end-to-end answer quality remains a bottleneck, indicating that trajectory-level improvements do not yet fully propagate to final output quality.</p></details> | |
| **[Staying on Track: Efficient Trajectory Discovery with Adaptive Batch Sampling](https://arxiv.org/abs/2510.18099v2)** | 2026-04-15 | <details><summary>Show</summary><p>Bayesian optimization (BO) is a powerful framework for estimating parameters of expensive simulation models, particularly in settings where the likelihood is intractable and evaluations are costly. In stochastic models every simulation is run with a specific parameter set and an implicit or explicit random seed, where each parameter set and random seed combination generates an individual realization, or trajectory, sampled from an underlying random process. Existing BO approaches typically rely on summary statistics over the realizations, such as means, medians, or quantiles, potentially limiting their effectiveness when trajectory-level information is desired. We propose a trajectory-oriented BO method that incorporates a Gaussian process surrogate using both input parameters and random seeds as inputs, enabling direct inference at the trajectory level. Using a common random number approach, we define a surrogate-based likelihood over trajectories and introduce an adaptive Thompson Sampling algorithm that refines a fixed-size input grid through likelihood-based filtering and Metropolis-Hastings-based densification. This approach concentrates computation on statistically promising regions of the input space while balancing exploration and exploitation. We apply the method to stochastic epidemic models, a simple compartmental and a more computationally demanding agent-based model, demonstrating improved sampling efficiency and faster identification of data-consistent trajectories relative to parameter-only inference.</p></details> | |
| **[HINTBench: Horizon-agent Intrinsic Non-attack Trajectory Benchmark](https://arxiv.org/abs/2604.13954v1)** | 2026-04-15 | <details><summary>Show</summary><p>Existing agent-safety evaluation has focused mainly on externally induced risks. Yet agents may still enter unsafe trajectories under benign conditions. We study this complementary but underexplored setting through the lens of \emph{intrinsic} risk, where intrinsic failures remain latent, propagate across long-horizon execution, and eventually lead to high-consequence outcomes. To evaluate this setting, we introduce \emph{non-attack intrinsic risk auditing} and present \textbf{HINTBench}, a benchmark of 629 agent trajectories (523 risky, 106 safe; 33 steps on average) supporting three tasks: risk detection, risk-step localization, and intrinsic failure-type identification. Its annotations are organized under a unified five-constraint taxonomy. Experiments reveal a substantial capability gap: strong LLMs perform well on trajectory-level risk detection, but their performance drops to below 35 Strict-F1 on risk-step localization, while fine-grained failure diagnosis proves even harder. Existing guard models transfer poorly to this setting. These findings establish intrinsic risk auditing as an open challenge for agent safety.</p></details> | |
| **[Bayesian Joint Modelling of Longitudinal Creatinine Trajectories in Children with Auto-Immune Disorders to Predict Paediatric Kidney Disease Risk in a Single Centre Study](https://arxiv.org/abs/2604.12740v1)** | 2026-04-14 | <details><summary>Show</summary><p>This study investigates the relationship between longitudinal serum creatinine measurements and the risk of adverse kidney outcomes in paediatric patients with auto-immune disorders at Great Ormond Street Hospital for Children NHS Foundation Trust, London. To jointly analyse repeated biomarker measurements and time-to-event outcomes, we employed a joint modelling framework that combines the creatinine trajectories with the time to death or diagnosis of acute kidney injury or chronic kidney disease. Covariates considered in analysis included demographic and clinical characteristics. The results demonstrate a strong association between evolving creatinine profiles and the risk of the composite event. Specifically, treatment with corticosteroids and calcium channel blockers was associated with an increased event risk, whereas immunosuppressive therapy was associated with a reduced risk. The longitudinal component showed that creatinine trajectories were significantly influenced by age and BMI z-score. To demonstrate the practical utility of the proposed framework, dynamic risk predictions were generated using patients' observed creatinine trajectories. Model performance was compared using model selection criteria, alongside area under the curve and Brier score to evaluate the accuracy of dynamic risk predictions. These predictions illustrate the potential of joint models to support personalised medicine and clinical decision making in paediatric nephrology through real-time risk assessment.</p></details> | |
| **[FeaXDrive: Feasibility-aware Trajectory-Centric Diffusion Planning for End-to-End Autonomous Driving](https://arxiv.org/abs/2604.12656v1)** | 2026-04-14 | <details><summary>Show</summary><p>End-to-end diffusion planning has shown strong potential for autonomous driving, but the physical feasibility of generated trajectories remains insufficiently addressed. In particular, generated trajectories may exhibit local geometric irregularities, violate trajectory-level kinematic constraints, or deviate from the drivable area, indicating that the commonly used noise-centric formulation in diffusion planning is not yet well aligned with the trajectory space where feasibility is more naturally characterized. To address this issue, we propose FeaXDrive, a feasibility-aware trajectory-centric diffusion planning method for end-to-end autonomous driving. The core idea is to treat the clean trajectory as the unified object for feasibility-aware modeling throughout the diffusion process. Built on this trajectory-centric formulation, FeaXDrive integrates adaptive curvature-constrained training to improve intrinsic geometric and kinematic feasibility, drivable-area guidance within reverse diffusion sampling to enhance consistency with the drivable area, and feasibility-aware GRPO post-training to further improve planning performance while balancing trajectory-space feasibility. Experiments on the NAVSIM benchmark show that FeaXDrive achieves strong closed-loop planning performance while substantially improving trajectory-space feasibility. These findings highlight the importance of explicitly modeling trajectory-space feasibility in end-to-end diffusion planning and provide a step toward more reliable and physically grounded autonomous driving planners.</p></details> | 21 pages, 6 figures |
| **[SparseWorld-TC: Trajectory-Conditioned Sparse Occupancy World Model](https://arxiv.org/abs/2511.22039v3)** | 2026-04-14 | <details><summary>Show</summary><p>This paper introduces a novel architecture for trajectory-conditioned forecasting of future 3D scene occupancy. In contrast to methods that rely on variational autoencoders (VAEs) to generate discrete occupancy tokens, which inherently limit representational capacity, our approach predicts multi-frame future occupancy in an end-to-end manner directly from raw image features. Inspired by the success of attention-based transformer architectures in foundational vision and language models such as GPT and VGGT, we employ a sparse occupancy representation that bypasses the intermediate bird's eye view (BEV) projection and its explicit geometric priors. This design allows the transformer to capture spatiotemporal dependencies more effectively. By avoiding both the finite-capacity constraint of discrete tokenization and the structural limitations of BEV representations, our method achieves state-of-the-art performance on the nuScenes benchmark for 1-3 second occupancy forecasting, outperforming existing approaches by a significant margin. Furthermore, it demonstrates robust scene dynamics understanding, consistently delivering high accuracy under arbitrary future trajectory conditioning.</p></details> | <details><summary>Accep...</summary><p>Accepted by CVPR2026 as an oral</p></details> |
| **[Scalable Trajectory Generation for Whole-Body Mobile Manipulation](https://arxiv.org/abs/2604.12565v1)** | 2026-04-14 | <details><summary>Show</summary><p>Robots deployed in unstructured environments must coordinate whole-body motion -- simultaneously moving a mobile base and arm -- to interact with the physical world. This coupled mobility and dexterity yields a state space that grows combinatorially with scene and object diversity, demanding datasets far larger than those sufficient for fixed-base manipulation. Yet existing acquisition methods, including teleoperation and planning, are either labor-intensive or computationally prohibitive at scale. The core bottleneck is the lack of a scalable pipeline for generating large-scale, physically valid, coordinated trajectory data across diverse embodiments and environments. Here we introduce AutoMoMa, a GPU-accelerated framework that unifies AKR modeling, which consolidates base, arm, and object kinematics into a single chain, with parallelized trajectory optimization. AutoMoMa achieves 5,000 episodes per GPU-hour (over $80\times$ faster than CPU-based baselines), producing a dataset of over 500k physically valid trajectories spanning 330 scenes, diverse articulated objects, and multiple robot embodiments. Prior datasets were forced to compromise on scale, diversity, or kinematic fidelity; AutoMoMa addresses all three simultaneously. Training downstream IL policies further reveals that even a single articulated-object task requires tens of thousands of demonstrations for SOTA methods to reach $\approx 80\%$ success, confirming that data scarcity -- not algorithmic limitations -- has been the binding constraint. AutoMoMa thus bridges high-performance planning and reliable IL-based control, providing the infrastructure previously missing for coordinated mobile manipulation research. By making large-scale, kinematically valid training data practical, AutoMoMa showcases generalizable whole-body robot policies capable of operating in the diverse, unstructured settings of the real world.</p></details> | |
| **[Forecasting the Past: Gradient-Based Distribution Shift Detection in Trajectory Prediction](https://arxiv.org/abs/2604.12425v1)** | 2026-04-14 | <details><summary>Show</summary><p>Trajectory prediction models often fail in real-world automated driving due to distributional shifts between training and test conditions. Such distributional shifts, whether behavioural or environmental, pose a critical risk by causing the model to make incorrect forecasts in unfamiliar situations. We propose a self-supervised method that trains a decoder in a post-hoc fashion on the self-supervised task of forecasting the second half of observed trajectories from the first half. The L2 norm of the gradient of this forecasting loss with respect to the decoder's final layer defines a score to identify distribution shifts. Our approach, first, does not affect the trajectory prediction model, ensuring no interference with original prediction performance and second, demonstrates substantial improvements on distribution shift detection for trajectory prediction on the Shifts and Argoverse datasets. Moreover, we show that this method can also be used to early detect collisions of a deep Q-Network motion planner in the Highway simulator. Source code is available at https://github.com/Michedev/forecasting-the-past.</p></details> | <details><summary>Accep...</summary><p>Accepted at CVPRW SAIAD 2026</p></details> |
| **[Resident fitness computation in linear time and other algorithmic aspects of interacting trajectories](https://arxiv.org/abs/2502.11561v3)** | 2026-04-14 | <details><summary>Show</summary><p>Systems of interacting trajectories were recently studied in~\cite{HGSTW24}. Such a system of $[0,1]$-valued piecewise linear trajectories arises as a scaling limit of the system of logarithmic subpopulation sizes in a population-genetic model (more precisely, a Moran model) with mutation and selection. By definition, the resident fitness is initially 0 and afterwards it increases by the ultimate slope of each trajectory that reaches height 1. We show that although the interaction of $n$ trajectories may yield $Ω(n^2)$ slope changes in total, the resident fitness function can be computed algorithmically in $O(n)$ time. Our algorithm uses the so-called continued lines representation of the system of interacting trajectories. In the special case of Poissonian interacting trajectories where the birth times of the trajectories form a Poisson process and the initial slopes are random and i.i.d., we provide a linear bound on the expected total number of slope changes.</p></details> | 17 pages, 4 figures |
| **[PILOT: Planning via Internalized Latent Optimization Trajectories for Large Language Models](https://arxiv.org/abs/2601.19917v2)** | 2026-04-14 | <details><summary>Show</summary><p>Strategic planning is critical for multi-step reasoning, yet compact Large Language Models (LLMs) often lack the capacity to formulate global strategies, leading to error propagation in long-horizon tasks. Our analysis reveals that LLMs possess latent reasoning capabilities that can be unlocked when conditioned on explicit plans from a teacher model; however, runtime reliance on external guidance is often impractical due to latency and availability constraints. To bridge this gap, we propose PILOT (Planning via Internalized Latent Optimization Trajectories), a non-invasive framework designed to internalize the strategic oversight of large models into intrinsic Latent Guidance. Instead of altering backbone weights, PILOT employs a lightweight Hyper-Network to synthesize a query-conditioned Latent Guidance vector. This vector acts as an internal steering mechanism, guiding the model's representations toward optimal reasoning paths. Extensive experiments on mathematical and coding benchmarks demonstrate that PILOT effectively stabilizes reasoning trajectories, consistently outperforming strong baselines (e.g., +8.9% on MATH500) with negligible inference latency.</p></details> | |
| **[Improved particle swarm optimization algorithm: multi-target trajectory optimization for swarm drones](https://arxiv.org/abs/2507.13647v2)** | 2026-04-14 | <details><summary>Show</summary><p>Real-time trajectory planning for unmanned aerial vehicles (UAVs) in dynamic environments remains a key challenge due to high computational demands and the need for fast, adaptive responses. Traditional Particle Swarm Optimization (PSO) methods, while effective for offline planning, often struggle with premature convergence and latency in real-time scenarios. To overcome these limitations, we propose PE-PSO, an enhanced PSO-based online trajectory planner. The method introduces a persistent exploration mechanism to preserve swarm diversity and an entropy-based parameter adjustment strategy to dynamically adapt optimization behavior. UAV trajectories are modeled using B-spline curves, which ensure path smoothness while reducing optimization complexity. To extend this capability to UAV swarms, we develop a multi-agent framework that combines genetic algorithm (GA)-based task allocation with distributed PE-PSO, supporting scalable and coordinated trajectory generation. The distributed architecture allows for parallel computation and decentralized control, enabling effective cooperation among agents while maintaining real-time performance. Comprehensive simulations demonstrate that the proposed framework outperforms conventional PSO and other swarm-based planners across several metrics, including trajectory quality, energy efficiency, obstacle avoidance, and computation time. These results confirm the effectiveness and applicability of PE-PSO in real-time multi-UAV operations under complex environmental conditions.</p></details> | <details><summary>New e...</summary><p>New experiments have revealed systematic errors in the original data</p></details> |
| **[Joint Trajectory and Resource Optimization for Aerial RIS-assisted Integrated TNT Networks](https://arxiv.org/abs/2604.12283v1)** | 2026-04-14 | <details><summary>Show</summary><p>Integrated terrestrial and non-terrestrial networks (ITNTNs) are regarded as a key architectural paradigm for sixth-generation (6G) wireless systems. This paper investigates a dual-aerial reconfigurable intelligent surface (RIS)-assisted ITNTN, where a terrestrial base station (TBS) and a satellite (SAT) jointly serve terrestrial and satellite users with the aid of an unmanned aerial vehicle (UAV)-mounted RIS and a high-altitude platform (HAP)-mounted RIS. We formulate an average sum-rate maximization problem by jointly optimizing the TBS and SAT precoders, the RIS phase shift matrices, and the three-dimensional trajectories of the UAV and the HAP, subject to transmit power, unit-modulus, and mobility constraints. The resulting optimization problem is highly non-convex due to the strong coupling among the transmit precoders, RIS phase shifts, and aerial platform mobility. To efficiently address this challenge, we propose a block coordinate descent (BCD) framework that integrates weighted minimum mean square error (WMMSE) optimization for precoder design, a manifold-based Riemannian conjugate gradient (RCG) method for RIS phase-shift optimization, and successive convex approximation (SCA) for trajectory optimization. The proposed algorithm is shown to converge to a stationary point. The simulation results show that the proposed joint design achieves an approximately $7.05 \%$ higher average sum-rate compared to the random RIS scheme, highlighting the effectiveness of dual-aerial RIS deployment and joint communication-mobility optimization in ITNTNs.</p></details> | <details><summary>This ...</summary><p>This work has been submitted to IEEE Transactions on Wireless Communications for possible publication</p></details> |
| **[Joint Trajectory and Resource Optimization for Dual-aerial ARIS-assisted NOMA-TNT Networks](https://arxiv.org/abs/2604.12266v1)** | 2026-04-14 | <details><summary>Show</summary><p>Integrated terrestrial and non-terrestrial networks (ITNTNs) are envisioned as a key paradigm for sixth-generation (6G) wireless systems, enabling seamless global connectivity. In this paper, we investigate a dual-aerial active reconfigurable intelligent surface (ARIS)-assisted non-orthogonal multiple access (NOMA)-based ITNTN, where a terrestrial base station (TBS) and a satellite (SAT) simultaneously serve terrestrial and satellite users with the aid of a UAV-mounted ARIS and a HAP-mounted ARIS. Users are multiplexed via power-domain NOMA with a predefined SIC decoding order. We formulate an average sum-rate maximization problem by jointly optimizing transmit beamforming, ARIS coefficients, and the 3D trajectories of the UAV and HAP, subject to power, unit-modulus, ARIS power, and mobility constraints. The problem is highly non-convex due to coupled variables, nonlinear SINR expressions, ARIS amplification, and trajectory-dependent channels. To address this, a block coordinate descent (BCD)-based framework is proposed. Specifically, beamforming is optimized via WMMSE, ARIS phase shifts via a manifold-based RCG method, amplification factors via SCA, and trajectories via first-order approximations. The proposed algorithm is guaranteed to converge to a stationary point. Simulation results demonstrate that the proposed design achieves significant performance gains over benchmark schemes. In particular, it provides an average sum-rate improvement of approximately $8.44\%$ over passive RIS under given power constraints, highlighting the benefits of dual-aerial ARIS and joint communication-mobility optimization.</p></details> | <details><summary>This ...</summary><p>This work has been submitted to IEEE Transactions on Communications for possible publication</p></details> |
| **[Characterizing Human Semantic Navigation in Concept Production as Trajectories in Embedding Space](https://arxiv.org/abs/2602.05971v2)** | 2026-04-14 | <details><summary>Show</summary><p>Semantic representations can be framed as a structured, dynamic knowledge space through which humans navigate to retrieve and manipulate meaning. To investigate how humans traverse this geometry, we introduce a framework that represents concept production as navigation through embedding space. Using different transformer text embedding models, we construct participant-specific semantic trajectories based on cumulative embeddings and extract geometric and dynamical metrics, including distance to next, distance to centroid, entropy, velocity, and acceleration. These measures capture both scalar and directional aspects of semantic navigation, providing a computationally grounded view of semantic representation search as movement in a geometric space. We evaluate the framework on four datasets across different languages, spanning different property generation tasks: Neurodegenerative, Swear verbal fluency, Property listing task in Italian, and in German. Across these contexts, our approach distinguishes between clinical groups and concept types, offering a mathematical framework that requires minimal human intervention compared to typical labor-intensive linguistic pre-processing methods. Comparison with a non-cumulative approach reveals that cumulative embeddings work best for longer trajectories, whereas shorter ones may provide too little context, favoring the non-cumulative alternative. Critically, different embedding models yielded similar results, highlighting similarities between different learned representations despite different training pipelines. By framing semantic navigation as a structured trajectory through embedding space, bridging cognitive modeling with learned representation, thereby establishing a pipeline for quantifying semantic representation dynamics with applications in clinical research, cross-linguistic analysis, and the assessment of artificial cognition.</p></details> | <details><summary>10 pa...</summary><p>10 pages, 6 figures (excluding refs/appendix). Accepted to ICLR 2026</p></details> |
| **[AGMA: Adaptive Gaussian Mixture Anchors for Prior-Guided Multimodal Human Trajectory Forecasting](https://arxiv.org/abs/2602.04204v2)** | 2026-04-14 | <details><summary>Show</summary><p>Human trajectory forecasting requires capturing the multimodal nature of pedestrian behavior. However, existing approaches suffer from prior misalignment. Their learned or fixed priors often fail to capture the full distribution of plausible futures, limiting both prediction accuracy and diversity. We theoretically establish that prediction error is lower-bounded by prior quality, making prior modeling a key performance bottleneck. Guided by this insight, we propose AGMA (Adaptive Gaussian Mixture Anchors), which constructs expressive priors through two stages: extracting diverse behavioral patterns from training data and distilling them into a scene-adaptive global prior for inference. Extensive experiments on ETH-UCY, Stanford Drone, and JRDB datasets demonstrate that AGMA achieves state-of-the-art performance, confirming the critical role of high-quality priors in trajectory forecasting.</p></details> | <details><summary>Withd...</summary><p>Withdrawn for substantial revision and will be re-uploaded as a new manuscript</p></details> |
| **[Uncertainty Guided Exploratory Trajectory Optimization for Sampling-Based Model Predictive Control](https://arxiv.org/abs/2604.12149v1)** | 2026-04-13 | <details><summary>Show</summary><p>Trajectory optimization depends heavily on initialization. In particular, sampling-based approaches are highly sensitive to initial solutions, and limited exploration frequently leads them to converge to local minima in complex environments. We present Uncertainty Guided Exploratory Trajectory Optimization (UGE-TO), a trajectory optimization algorithm that generates well-separated samples to achieve a better coverage of the configuration space. UGE-TO represents trajectories as probability distributions induced by uncertainty ellipsoids. Unlike sampling-based approaches that explore only in the action space, this representation captures the effects of both system dynamics and action selection. By incorporating the impact of dynamics, in addition to the action space, into our distributions, our method enhances trajectory diversity by enforcing distributional separation via the Hellinger distance between them. It enables a systematic exploration of the configuration space and improves robustness against local minima. Further, we present UGE-MPC, which integrates UGE-TO into sampling-based model predictive controller methods. Experiments demonstrate that UGE-MPC achieves higher exploration and faster convergence in trajectory optimization compared to baselines under the same sampling budget, achieving 72.1% faster convergence in obstacle-free environments and 66% faster convergence with a 6.7% higher success rate in the cluttered environment compared to the best-performing baseline. Additionally, we validate the approach through a range of simulation scenarios and real-world experiments. Our results indicate that UGE-MPC has higher success rates and faster convergence, especially in environments that demand significant deviations from nominal trajectories to avoid failures. The project and code are available at https://ogpoyrazoglu.github.io/cuniform_sampling/.</p></details> | <details><summary>This ...</summary><p>This paper has been accepted for presentation at the IEEE International Conference on Robotics and Automation (ICRA) 2026</p></details> |
| **[Temporal Flattening in LLM-Generated Text: Comparing Human and LLM Writing Trajectories](https://arxiv.org/abs/2604.12097v1)** | 2026-04-13 | <details><summary>Show</summary><p>Large language models (LLMs) are increasingly used in daily applications, from content generation to code writing, where each interaction treats the model as stateless, generating responses independently without memory. Yet human writing is inherently longitudinal: authors' styles and cognitive states evolve across months and years. This raises a central question: can LLMs reproduce such temporal structure across extended time periods? We construct and publicly release a longitudinal dataset of 412 human authors and 6,086 documents spanning 2012--2024 across three domains (academic abstracts, blogs, news) and compare them to trajectories generated by three representative LLMs under standard and history-conditioned generation settings. Using drift and variance-based metrics over semantic, lexical, and cognitive-emotional representations, we find temporal flattening in LLM-generated text. LLMs produce greater lexical diversity but exhibit substantially reduced semantic and cognitive-emotional drift relative to humans. These differences are highly predictive: temporal variability patterns alone achieve 94% accuracy and 98% ROC-AUC in distinguishing human from LLM trajectories. Our results demonstrate that temporal flattening persists regardless of whether LLMs generate independently or with access to incremental history, revealing a fundamental property of current deployment paradigms. This gap has direct implications for applications requiring authentic temporal structure, such as synthetic training data and longitudinal text modeling.</p></details> | <details><summary>25 pa...</summary><p>25 pages, 6 figures. To appear in Findings of ACL 2026</p></details> |
| **[VISTA: Validation-Informed Trajectory Adaptation via Self-Distillation](https://arxiv.org/abs/2604.12044v1)** | 2026-04-13 | <details><summary>Show</summary><p>Deep learning models may converge to suboptimal solutions despite strong validation accuracy, masking an optimization failure we term Trajectory Deviation. This is because as training proceeds, models can abandon high generalization states for specific data sub-populations, thus discarding previously learned latent features without triggering classical overfitting signals. To address this problem we introduce VISTA, an online self-distillation framework that enforces consistency along the optimization trajectory. Using a validation-informed Marginal Coverage score, VISTA identifies expert anchors, which are earlier model states that retain specialized competence over distinct data regions. A coverage-weighted ensemble of these anchors is integrated online during training, regularizing the loss landscape and preserving mastered knowledge. When evaluated across multiple benchmarks, VISTA demonstrates improved robustness and generalization over standard training and prior self-distillation methods, while a lightweight implementation reduces storage overhead by 90% without performance loss.</p></details> | |
| **[Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration](https://arxiv.org/abs/2604.11446v1)** | 2026-04-13 | <details><summary>Show</summary><p>Recently, scaling reinforcement learning with verifiable rewards (RLVR) for large language models (LLMs) has emerged as an effective training paradigm for significantly improving model capabilities, which requires guiding the model to perform extensive exploration and learning, leading to substantial computational overhead and becoming a key challenge. To reduce the number of training steps, Prior work performs linear extrapolation of model parameters. However, the dynamics of model parameter updates during RLVR training remain insufficiently understood. To further investigate the evolution of LLMs during RLVR training, we conduct empirical experiments and find that the rank-1 subspace of the model does not evolve linearly, and its dominance over the original parameters is further amplified during LoRA training. Based on the above insights, we propose the \textbf{N}onlinear \textbf{Ext}rapolation of low-rank trajectories (\textbf{NExt}), a novel framework that models and extrapolates low-rank parameter trajectories in a nonlinear manner. Concretely, we first train the model using LoRA and extract the rank-1 subspace of parameter differences at multiple training steps, which is then used for the subsequent nonlinear extrapolation. Afterward, we utilized the extracted rank-1 subspace to train a predictor, which can model the trajectory of parameter updates during RLVR, and then perform the predict-extend process to extrapolate model parameters, achieving the acceleration of RLVR. To further study and understand NExt, we conduct comprehensive experiments that demonstrate the effectiveness and robustness of the method. Our method reduces computational overhead by approximately 37.5\% while remaining compatible with a wide range of RLVR algorithms and tasks. We release our code in https://github.com/RUCAIBox/NExt.</p></details> | Working in progress |
| **[dTRPO: Trajectory Reduction in Policy Optimization of Diffusion Large Language Models](https://arxiv.org/abs/2603.18806v2)** | 2026-04-13 | <details><summary>Show</summary><p>Diffusion Large Language Models (dLLMs) introduce a new paradigm for language generation, which in turn presents new challenges for aligning them with human preferences. In this work, we aim to improve the policy optimization for dLLMs by reducing the cost of the trajectory probability calculation, thereby enabling scaled-up offline policy training. We prove that: (i) under reference policy regularization, the probability ratio of the newly unmasked tokens is an unbiased estimate of that of intermediate diffusion states, and (ii) the probability of the full trajectory can be effectively estimated with a single forward pass of a re-masked final state. By integrating these two trajectory reduction strategies into a policy optimization objective, we propose Trajectory Reduction Policy Optimization (dTRPO). We evaluate dTRPO on 7B dLLMs across instruction-following and reasoning benchmarks. Results show that it substantially improves the core performance of state-of-the-art dLLMs, achieving gains of up to 9.6% on STEM tasks, up to 4.3% on coding tasks, and up to 3.0% on instruction-following tasks. Moreover, dTRPO exhibits strong training efficiency due to its offline, single-forward nature, and achieves improved generation efficiency through high-quality outputs.</p></details> | |
| **[Learning from Contrasts: Synthesizing Reasoning Paths from Diverse Search Trajectories](https://arxiv.org/abs/2604.11365v1)** | 2026-04-13 | <details><summary>Show</summary><p>Monte Carlo Tree Search (MCTS) has been widely used for automated reasoning data exploration, but current supervision extraction methods remain inefficient. Standard approaches retain only the single highest-reward trajectory, discarding the comparative signals present in the many explored paths. Here we introduce \textbf{Contrastive Reasoning Path Synthesis (CRPS)}, a framework that transforms supervision extraction from a filtering process into a synthesis procedure. CRPS uses a structured reflective process to analyze the differences between high- and low-quality search trajectories, extracting explicit information about strategic pivots and local failure modes. These insights guide the synthesis of reasoning chains that incorporate success patterns while avoiding identified pitfalls. We show empirically that models fine-tuned on just 60K CRPS-synthesized examples match or exceed the performance of baselines trained on 590K examples derived from standard rejection sampling, a 20$\times$ reduction in dataset size. Furthermore, CRPS improves generalization on out-of-domain benchmarks, demonstrating that learning from the contrast between success and failure produces more transferable reasoning capabilities than learning from success alone.</p></details> | |
| **[Reliable and Real-Time Highway Trajectory Planning via Hybrid Learning-Optimization Frameworks](https://arxiv.org/abs/2508.04436v2)** | 2026-04-13 | <details><summary>Show</summary><p>Autonomous highway driving involves high-speed safety risks due to limited reaction time, where rare but dangerous events may lead to severe consequences. This places stringent requirements on trajectory planning in terms of both reliability and computational efficiency. This paper proposes a hybrid highway trajectory planning (H-HTP) framework that integrates learning-based adaptability with optimization-based formal safety guarantees. The key design principle is a deliberate division of labor: a learning module generates a traffic-adaptive velocity profile, while all safety-critical decisions including collision avoidance and kinematic feasibility are delegated to a Mixed-Integer Quadratic Program (MIQP). This design ensures that formal safety constraints are always enforced, regardless of the complexity of multi-vehicle interactions. A linearization strategy for the vehicle geometry substantially reduces the number of integer variables, enabling real-time optimization without sacrificing formal safety guarantees. Experiments on the HighD dataset demonstrate that H-HTP achieves a scenario success rate above 97% with an average planning-cycle time of approximately 54 ms, reliably producing smooth, kinematically feasible, and collision-free trajectories in safety-critical highway scenarios.</p></details> | |
| **[Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference Optimization](https://arxiv.org/abs/2604.11259v1)** | 2026-04-13 | <details><summary>Show</summary><p>Mobile GUI agents powered by Multimodal Large Language Models (MLLMs) can execute complex tasks on mobile devices. Despite this progress, most existing systems still optimize task success or efficiency, neglecting users' privacy personalization. In this paper, we study the often-overlooked problem of agent personalization. We observe that personalization can induce systematic structural heterogeneity in execution trajectories. For example, privacy-first users often prefer protective actions, e.g., refusing permissions, logging out, and minimizing exposure, leading to logically different execution trajectories from utility-first users. Such variable-length and structurally different trajectories make standard preference optimization unstable and less informative. To address this issue, we propose Trajectory Induced Preference Optimization (TIPO), which uses preference-intensity weighting to emphasize key privacy-related steps and padding gating to suppress alignment noise. Results on our Privacy Preference Dataset show that TIPO improves persona alignment and distinction while preserving strong task executability, achieving 65.60% SR, 46.22 Compliance, and 66.67% PD, outperforming existing optimization methods across various GUI tasks. The code and dataset will be publicly released at https://github.com/Zhixin-L/TIPO.</p></details> | <details><summary>10 pa...</summary><p>10 pages, 6 figures, 3 tables</p></details> |
| **[MapATM: Enhancing HD Map Construction through Actor Trajectory Modeling](https://arxiv.org/abs/2604.11081v1)** | 2026-04-13 | <details><summary>Show</summary><p>High-definition (HD) mapping tasks, which perform lane detections and predictions, are extremely challenging due to non-ideal conditions such as view occlusions, distant lane visibility, and adverse weather conditions. Those conditions often result in compromised lane detection accuracy and reduced reliability within autonomous driving systems. To address these challenges, we introduce MapATM, a novel deep neural network that effectively leverages historical actor trajectory information to improve lane detection accuracy, where actors refer to moving vehicles. By utilizing actor trajectories as structural priors for road geometry, MapATM achieves substantial performance enhancements, notably increasing AP by 4.6 for lane dividers and mAP by 2.6 on the challenging NuScenes dataset, representing relative improvements of 10.1% and 6.1%, respectively, compared to strong baseline methods. Extensive qualitative evaluations further demonstrate MapATM's capability to consistently maintain stable and robust map reconstruction across diverse and complex driving scenarios, underscoring its practical value for autonomous driving applications.</p></details> | <details><summary>6 pag...</summary><p>6 pages, 4 figures, 5 tables</p></details> |
| **[VERTIGO: Visual Preference Optimization for Cinematic Camera Trajectory Generation](https://arxiv.org/abs/2604.02467v2)** | 2026-04-13 | <details><summary>Show</summary><p>Cinematic camera control relies on a tight feedback loop between director and cinematographer, where camera motion and framing are continuously reviewed and refined. Recent generative camera systems can produce diverse, text-conditioned trajectories, but they lack this "director in the loop" and have no explicit supervision of whether a shot is visually desirable. This results in in-distribution camera motion but poor framing, off-screen characters, and undesirable visual aesthetics. In this paper, we introduce VERTIGO, the first framework for visual preference optimization of camera trajectory generators. Our framework leverages a real-time graphics engine (Unity) to render 2D visual previews from generated camera motion. A cinematically fine-tuned vision-language model then scores these previews using our proposed cyclic semantic similarity mechanism, which aligns renders with text prompts. This process provides the visual preference signals for Direct Preference Optimization (DPO) post-training. Both quantitative evaluations and user studies on Unity renders and diffusion-based Camera-to-Video pipelines show consistent gains in condition adherence, framing quality, and perceptual realism. Notably, VERTIGO reduces the character off-screen rate from 38% to nearly 0% while preserving the geometric fidelity of camera motion. User study participants further prefer VERTIGO over baselines across composition, consistency, prompt adherence, and aesthetic quality, confirming the perceptual benefits of our visual preference post-training.</p></details> | <details><summary>28 pa...</summary><p>28 pages, 10 figures, ECCV 2026</p></details> |
| **[From Topology to Trajectory: LLM-Driven World Models For Supply Chain Resilience](https://arxiv.org/abs/2604.11041v1)** | 2026-04-13 | <details><summary>Show</summary><p>Semiconductor supply chains face unprecedented resilience challenges amidst global geopolitical turbulence. Conventional Large Language Model (LLM) planners, when confronting such non-stationary "Policy Black Swan" events, frequently suffer from Decision Paralysis or a severe Grounding Gap due to the absence of physical environmental modeling. This paper introduces ReflectiChain, a cognitive agentic framework tailored for resilient macroeconomic supply chain planning. The core innovation lies in the integration of Latent Trajectory Rehearsal powered by a generative world model, which couples reflection-in-action (System 2 deliberation) with delayed reflection-on-action. Furthermore, we leverage a Retrospective Agentic RL mechanism to enable autonomous policy evolution during the deployment phase (test-time). Evaluations conducted on our high-fidelity benchmark, Semi-Sim, demonstrate that under extreme scenarios such as export bans and material shortages, ReflectiChain achieves a 250% improvement in average step rewards over the strongest LLM baselines. It successfully restores the Operability Ratio (OR) from a deficient 13.3% to over 88.5% while ensuring robust gradient convergence. Ablation studies further underscore that the synergy between physical grounding constraints and double-loop learning is fundamental to bridging the gap between semantic reasoning and physical reality for long-horizon strategic planning.</p></details> | |
| **[Online Covariance Estimation in Averaged SGD: Improved Batch-Mean Rates and Minimax Optimality via Trajectory Regression](https://arxiv.org/abs/2604.10814v1)** | 2026-04-12 | <details><summary>Show</summary><p>We study online covariance matrix estimation for Polyak--Ruppert averaged stochastic gradient descent (SGD). The online batch-means estimator of Zhu, Chen and Wu (2023) achieves an operator-norm convergence rate of $O(n^{-(1-α)/4})$, which yields $O(n^{-1/8})$ at the optimal learning-rate exponent $α\rightarrow 1/2^+$. A rigorous per-block bias analysis reveals that re-tuning the block-growth parameter improves the batch-means rate to $O(n^{-(1-α)/3})$, achieving $O(n^{-1/6})$. The modified estimator requires no Hessian access and preserves $O(d^2)$ memory. We provide a complete error decomposition into variance, stationarity bias, and nonlinearity bias components. A weighted-averaging variant that avoids hard truncation is also discussed. We establish the minimax rate $Θ(n^{-(1-α)/2})$ for Hessian-free covariance estimation from the SGD trajectory: a Le Cam lower bound gives $Ω(n^{-(1-α)/2})$, and a trajectory-regression estimator--which estimates the Hessian by regressing SGD increments on iterates--achieves $O(n^{-(1-α)/2})$, matching the lower bound. The construction reveals that the bottleneck is the sublinear accumulation of information about the Hessian from the SGD drift.</p></details> | |
| **[Adaptive H-EFT-VA: A Provably Safe Trajectory Through the Trainability-Expressibility Landscape of Variational Quantum Algorithms](https://arxiv.org/abs/2604.10607v1)** | 2026-04-12 | <details><summary>Show</summary><p>H-EFT-VA established a physics-informed solution to the Barren Plateau (BP) problem via a hierarchical EFT UV-cutoff, guaranteeing gradient variance in Omega(1/poly(N)). However, localization restricts the ansatz to a polynomial subspace, creating a reference-state gap for states distant from |0>^N. We introduce Adaptive H-EFT-VA (A-H-EFT) to navigate the trainability-expressibility tradeoff by expanding the reachable Hilbert space along a safe trajectory. Gradient variance is maintained in Omega(1/poly(N)) if sigma(t) <= 0.5/sqrt(LN) (Theorem 1). A Safe Expansion Corollary and Monotone Growth Lemma confirm expansion without discontinuous jumps. Benchmarking across 16 experiments (up to N=14) shows A-H-EFT achieves fidelity F=0.54, doubling static H-EFT-VA (F=0.27) and outperforming HEA (F~0.01), with gradient variance >= 0.5 throughout. For Heisenberg XXZ (Delta_ref=1), A-H-EFT identifies the negative ground state while static methods fail. Results are statistically significant (p < 10^-37). Robustness over three decades of hyperparameters enables deployment without search. This is the first rigorously bounded trajectory through the VQA landscape.</p></details> | 17 figures |
| **[Early Decisions Matter: Proximity Bias and Initial Trajectory Shaping in Non-Autoregressive Diffusion Language Models](https://arxiv.org/abs/2604.10567v1)** | 2026-04-12 | <details><summary>Show</summary><p>Diffusion-based language models (dLLMs) have emerged as a promising alternative to autoregressive language models, offering the potential for parallel token generation and bidirectional context modeling. However, harnessing this flexibility for fully non-autoregressive decoding remains an open question, particularly for reasoning and planning tasks. In this work, we investigate non-autoregressive decoding in dLLMs by systematically analyzing its inference dynamics along the temporal axis. Specifically, we uncover an inherent failure mode in confidence-based non-autoregressive generation stemming from a strong proximity bias-the tendency for the denoising order to concentrate on spatially adjacent tokens. This local dependency leads to spatial error propagation, rendering the entire trajectory critically contingent on the initial unmasking position. Leveraging this insight, we present a minimal-intervention approach that guides early token selection, employing a lightweight planner and end-of-sequence temperature annealing. We thoroughly evaluate our method on various reasoning and planning tasks and observe substantial overall improvement over existing heuristic baselines without significant computational overhead.</p></details> | |
| **[Tracing Prompt-Level Trajectories to Understand Student Learning with AI in Programming Education](https://arxiv.org
gitextract_uotra79q/ ├── .github/ │ ├── ISSUE_TEMPLATE.md │ └── workflows/ │ └── update.yaml ├── .gitignore ├── README.md ├── main.py └── utils.py
SYMBOL INDEX (10 symbols across 1 files) FILE: utils.py function remove_duplicated_spaces (line 13) | def remove_duplicated_spaces(text: str) -> str: function request_paper_with_arXiv_api (line 16) | def request_paper_with_arXiv_api(keyword: str, max_results: int, link: s... function filter_tags (line 49) | def filter_tags(papers: List[Dict[str, str]], target_fileds: List[str]=[... function get_daily_papers_by_keyword_with_retries (line 60) | def get_daily_papers_by_keyword_with_retries(keyword: str, column_names:... function get_daily_papers_by_keyword (line 70) | def get_daily_papers_by_keyword(keyword: str, column_names: List[str], m... function generate_table (line 80) | def generate_table(papers: List[Dict[str, str]], ignore_keys: List[str] ... function back_up_files (line 128) | def back_up_files(): function restore_files (line 133) | def restore_files(): function remove_backups (line 138) | def remove_backups(): function get_daily_date (line 143) | def get_daily_date():
Condensed preview — 6 files, each showing path, character count, and a content snippet. Download the .json file or copy for the full structured content (430K chars).
[
{
"path": ".github/ISSUE_TEMPLATE.md",
"chars": 9968,
"preview": "---\ntitle: Latest 15 Papers - April 20, 2026\nlabels: documentation\n---\n**Please check the [Github](https://github.com/ze"
},
{
"path": ".github/workflows/update.yaml",
"chars": 1079,
"preview": "name: Update\n\non:\n label:\n types:\n - created # for test\n schedule:\n - cron: '30 16 * * 0-4' # 00:30 Beiji"
},
{
"path": ".gitignore",
"chars": 3120,
"preview": "# dir\n__pycache__/\n.vscode/\n\n# file\n*.npz\n*.npy\n*.csv\n*.pkl\n*.h5\n*.pt\ncore*\n*.p\n*.pickle\n*.pyc\n*.txt\n\n*.py[cod]\n*$py.cla"
},
{
"path": "README.md",
"chars": 405315,
"preview": "# Daily Papers\nThe project automatically fetches the latest papers from arXiv based on keywords.\n\nThe subheadings in the"
},
{
"path": "main.py",
"chars": 3015,
"preview": "import sys\nimport time\nimport pytz\nfrom datetime import datetime\n\nfrom utils import get_daily_papers_by_keyword_with_ret"
},
{
"path": "utils.py",
"chars": 6111,
"preview": "import os\nimport time\nimport pytz\nimport shutil\nimport datetime\nfrom typing import List, Dict\nimport urllib, urllib.requ"
}
]
About this extraction
This page contains the full source code of the zezhishao/DailyArXiv GitHub repository, extracted and formatted as plain text for AI agents and large language models (LLMs). The extraction includes 6 files (418.6 KB), approximately 86.1k tokens, and a symbol index with 10 extracted functions, classes, methods, constants, and types. Use this with OpenClaw, Claude, ChatGPT, Cursor, Windsurf, or any other AI tool that accepts text input. You can copy the full output to your clipboard or download it as a .txt file.
Extracted by GitExtract — free GitHub repo to text converter for AI. Built by Nikandr Surkov.