Modeling and forecasting interval-valued time series (ITS) have attracted considerable attention due to their growing presence in various contexts. To the best of our knowledge, there have been no efforts to model large-scale ITS. In this paper, we propose a feature extraction procedure for large-scale ITS, which involves key steps such as auto-segmentation and clustering, and feature transfer learning. This procedure can be seamlessly integrated with any suitable prediction models for forecasting purposes. Specifically, we transform the automatic segmentation and clustering of ITS into the estimation of Toeplitz sparse precision matrices and assignment set. The majorization-minimization algorithm is employed to convert this highly non-convex optimization problem into two subproblems. We derive efficient dynamic programming and alternating direction method to solve these two subproblems alternately and establish their convergence properties. By employing the Joint Recurrence Plot (JRP) to image subsequence and assigning a class label to each cluster, an image dataset is constructed. Then, an appropriate neural network is chosen to train on this image dataset and used to extract features for the next step of forecasting. Real data applications demonstrate that the proposed method can effectively obtain invariant representations of the raw data and enhance forecasting performance.

Despite exceptional capabilities in knowledge-intensive tasks, Large Language Models (LLMs) face a critical gap in understanding how they internalize new knowledge, particularly how to structurally embed acquired knowledge in their neural computations. We address this issue through the lens of knowledge circuit evolution, identifying computational subgraphs that facilitate knowledge storage and processing. Our systematic analysis of circuit evolution throughout continual pre-training reveals several key findings: (1) the acquisition of new knowledge is influenced by its relevance to pre-existing knowledge; (2) the evolution of knowledge circuits exhibits a distinct phase shift from formation to optimization; (3) the evolution of knowledge circuits follows a deep-to-shallow pattern. These insights not only advance our theoretical understanding of the mechanisms of new knowledge acquisition in LLMs, but also provide potential implications for improving continual pre-training strategies to enhance model performance. Code and data will be available at https://github.com/zjunlp/DynamicKnowledgeCircuits.

As societal awareness of climate change grows, corporate climate policy engagements are attracting attention. We propose a dataset to estimate corporate climate policy engagement from various PDF-formatted documents. Our dataset comes from LobbyMap (a platform operated by global think tank InfluenceMap) that provides engagement categories and stances on the documents. To convert the LobbyMap data into the structured dataset, we developed a pipeline using text extraction and OCR. Our contributions are: (i) Building an NLP dataset including 10K documents on corporate climate policy engagement.

Training Neural Ordinary Differential Equations (ODEs) is often computationally expensive. Indeed, computing the forward pass of such models involves solving an ODE which can become arbitrarily complex during training. Recent works have shown that regularizing the dynamics of the ODE can partially alleviate this. In this paper we propose a new regularization technique: randomly sampling the end time of the ODE during training. The proposed regularization is simple to implement, has negligible overhead and is effective across a wide variety of tasks. Further, the technique is orthogonal to several other methods proposed to regularize the dynamics of ODEs and as such can be used in conjunction with them. We show through experiments on normalizing flows, time series models and image recognition that the proposed regularization can significantly decrease training time and even improve performance over baseline models.

As societal awareness of climate change grows, corporate climate policy engagements are attracting attention. We propose a dataset to estimate corporate climate policy engagement from various PDF-formatted documents. Our dataset comes from LobbyMap (a platform operated by global think tank InfluenceMap) that provides engagement categories and stances on the documents. To convert the LobbyMap data into the structured dataset, we developed a pipeline using text extraction and OCR. Our contributions are: (i) Building an NLP dataset including 10K documents on corporate climate policy engagement.

The paper uses structured machine learning regressions for nowcasting with panel data consisting of series sampled at different frequencies. Motivated by the problem of predicting corporate earnings for a large cross-section of firms with macroeconomic, financial, and news time series sampled at different frequencies, we focus on the sparse-group LASSO regularization which can take advantage of the mixed frequency time series panel data structures. Our empirical results show the superior performance of our machine learning panel data regression models over analysts' predictions, forecast combinations, firm-specific time series regression models, and standard machine learning methods.

Rockwell Automation, the world's largest company dedicated to industrial automation and digital transformation, announced that it acquired Knowledge Lens. Based in Bengaluru, India, Knowledge Lens is a services and solutions provider that delivers actionable business insights from enterprise data, combining digital technologies with deep data science, artificial intelligence (AI), and engineering expertise. Knowledge Lens will join Rockwell's premier digital services business, Kalypso, to accelerate transformational outcomes for more manufacturers around the world. Rockwell's digital transformation services business is one of its fastest growing, as demand to scale connectivity across the enterprise and enable data-driven predictive and prescriptive insights increases. Together with Kalypso, Knowledge Lens will significantly expand Rockwell's capabilities to unlock the power of data, enable autonomous manufacturing, and drive continuous optimization for more manufacturers.

Bringing together resources from government, civil society and the private sector, the multi-stakeholder initiative was developed by Turkey's largest industrial conglomerate and an international company developing a'digital twin' using proprietary AI technology. Previous research has identified AI and machine learning as useful tools for reducing wildfire risk, but they have not been fully utilized. The FireAId pilot shows how to unlock its potential and scale it for immediate use.

The Air Force Research Laboratory (AFRL) has awarded BAE Systems a $17 million contract to introduce artificial intelligence (AI) into an interactive game environment to support air operations planning in contested environments as part of the Fight Tonight programme. Under the Technical Area 2, Plan Gaming and Outcome Analysis contract, BAE Systems' FAST Labs R&D unit, alongside subcontractors Uncharted Software and Kestrel Institute, will develop a solution to rapidly generate and review multiple operational plans and select the most robust. 'This technology is about using AI to provide commanders with more options faster and with more details,' said Mike Miller, technical director for FAST Labs. 'The drag-and-drop video game-like interactions would reduce the time it takes to make a series of incremental adjustments to a plan from hours to minutes.' The proposed solution will provide an interactive user interface that enables planners to explore and access plausible'futures' in a dynamic environment.

Rockwell Automation, the world's largest company dedicated to industrial automation and digital transformation, announced that it has signed a definitive agreement to acquire CUBIC, a company that specializes in modular systems for the construction of electrical panels. CUBIC, founded in 1973, serves fast-growing industries, such as renewable energy, data centers, and infrastructure, and is headquartered in Bronderslev, Denmark. CUBIC's efficient and flexible modular systems combined with Rockwell's intelligent devices and industry expertise will benefit customers by offering faster time to market, enabling broader plant-wide applications for intelligent motor control, and generating smart data to increase sustainability and productivity. CUBIC's established partner model will allow Rockwell to build an expanded Partner Network for intelligent motor control offerings in Asia, Europe, and Latin America. The company will bring new customers and partners in hybrid and process industries.