Search

Identifying anomalies from time series data plays an important role in various fields such as infrastructure security, intelligent operation and maintenance, and space exploration. Current research focuses on detecting the anomalies after they occur, which can lead to significant financial/reputation loss or infrastructure damage. In this work we instead study a more practical yet very challenging problem, time series anomaly prediction, aiming at providing early warnings for abnormal events before their occurrence. To tackle this problem, we introduce a novel principled approach, namely future context modeling (FCM). Its key insight is that the future abnormal events in a target window can be accurately predicted if their preceding observation window exhibits any subtle difference to normal data. To effectively capture such differences, FCM first leverages long-term forecasting models to generate a discriminative future context based on the observation data, aiming to amplify those subtle but unusual difference. It then models a normality correlation of the observation data with the forecasting future context to complement the normality modeling of the observation data in foreseeing possible abnormality in the target window. A joint variate-time attention learning is also introduced in FCM to leverage both temporal signals and features of the time series data for more discriminative normality modeling in the aforementioned two views. Comprehensive experiments on five datasets demonstrate that FCM gains good recall rate (70\%+) on multiple datasets and significantly outperforms all baselines in F1 score. Code is available at https://github.com/mala-lab/FCM., Comment: 11 pages, 5 figures, submitted to KDD conference

Large language models (LLMs) have demonstrated remarkable potential in solving complex tasks across diverse domains, typically by employing agentic workflows that follow detailed instructions and operational sequences. However, constructing these workflows requires significant human effort, limiting scalability and generalizability. Recent research has sought to automate the generation and optimization of these workflows, but existing methods still rely on initial manual setup and fall short of achieving fully automated and effective workflow generation. To address this challenge, we reformulate workflow optimization as a search problem over code-represented workflows, where LLM-invoking nodes are connected by edges. We introduce AFlow, an automated framework that efficiently explores this space using Monte Carlo Tree Search, iteratively refining workflows through code modification, tree-structured experience, and execution feedback. Empirical evaluations across six benchmark datasets demonstrate AFlow's efficacy, yielding a 5.7% average improvement over state-of-the-art baselines. Furthermore, AFlow enables smaller models to outperform GPT-4o on specific tasks at 4.55% of its inference cost in dollars. The code will be available at https://github.com/geekan/MetaGPT.

The attainment of autonomous operations in mobile computing devices has consistently been a goal of human pursuit. With the development of Large Language Models (LLMs) and Visual Language Models (VLMs), this aspiration is progressively turning into reality. While contemporary research has explored automation of simple tasks on mobile devices via VLMs, there remains significant room for improvement in handling complex tasks and reducing high reasoning costs. In this paper, we introduce MobileExperts, which for the first time introduces tool formulation and multi-agent collaboration to address the aforementioned challenges. More specifically, MobileExperts dynamically assembles teams based on the alignment of agent portraits with the human requirements. Following this, each agent embarks on an independent exploration phase, formulating its tools to evolve into an expert. Lastly, we develop a dual-layer planning mechanism to establish coordinate collaboration among experts. To validate our effectiveness, we design a new benchmark of hierarchical intelligence levels, offering insights into algorithm's capability to address tasks across a spectrum of complexity. Experimental results demonstrate that MobileExperts performs better on all intelligence levels and achieves ~ 22% reduction in reasoning costs, thus verifying the superiority of our design.

The spectral flux density of stars can indicate their atmospheric physical properties. A detector can obtain any band flux density at the design stage. However, the band flux density is confirmed and fixed in the process of operation because of the restriction of filters. Other band flux densities cannot be obtained through the same detector. In this study, a computational model of stellar spectral flux density is established based on basic physical parameters which are effective temperature and angular parameter. The stochastic particle swarm optimization algorithm is adopted to address this issue with appropriately chosen values of the algorithm parameters. Four star catalogues are studied and consist of the Large Sky Area Multi-Object Fibre Spectroscopic Telescope (LAMOST), Wide-field Infrared Survey Explorer (WISE), Midcourse Space Experiment (MSX), and Two Micron All Sky Survey (2MASS). The given flux densities from catalogues are input parameters. Stellar effective temperatures and angular parameters are inversed using the given flux densities according to SPSO algorithm. Then the flux density is calculated according to Planck's law on the basis of stellar effective temperatures and angular parameters. The calculated flux density is compared with the given value from catalogues. It is found that the inversion results are in good agreement for all bands of the MSX and 2MASS catalogues, whereas they do not agree well in some bands of the LAMOST and WISE catalogues. Based on the results, data from the MSX and 2MASS catalogues can be used to calculate the spectral flux density at different wavelengths of given wavelength ranges. The stellar flux density is obtained and can provide data support and an effective reference for detection and recognition of stars., Comment: 18 pages, 9 figures