The complexity of financial data, characterized by its variability and low signal-to-noise ratio, necessitates advanced methods in quantitative investment that prioritize both performance and interpretability.Transitioning from early manual extraction to genetic programming, the most advanced approach in the alpha factor mining domain currently employs reinforcement learning to mine a set of combination factors with fixed weights. However, the performance of resultant alpha factors exhibits inconsistency, and the inflexibility of fixed factor weights proves insufficient in adapting to the dynamic nature of financial markets. To address this issue, this paper proposes a two-stage formulaic alpha generating framework AlphaForge, for alpha factor mining and factor combination. This framework employs a generative-predictive neural network to generate factors, leveraging the robust spatial exploration capabilities inherent in deep learning while concurrently preserving diversity. The combination model within the framework incorporates the temporal performance of factors for selection and dynamically adjusts the weights assigned to each component alpha factor. Experiments conducted on real-world datasets demonstrate that our proposed model outperforms contemporary benchmarks in formulaic alpha factor mining. Furthermore, our model exhibits a notable enhancement in portfolio returns within the realm of quantitative investment and real money investment.

Visual question generation (VQG) aims to generate questions from images automatically. While existing studies primarily focus on the quality of generated questions, such as fluency and relevance, the difficulty of the questions is also a crucial factor in assessing their quality. Question difficulty directly impacts the effectiveness of VQG systems in applications like education and human-computer interaction, where appropriately challenging questions can stimulate learning interest and improve interaction experiences. However, accurately defining and controlling question difficulty is a challenging task due to its multidimensional and subjective nature. In this paper, we propose a new definition of the difficulty of questions, i.e., being positively correlated with the number of reasoning steps required to answer a question. For our definition, we construct a corresponding dataset and propose a benchmark as a foundation for future research. Our benchmark is designed to progressively increase the reasoning steps involved in generating questions. Specifically, we first extract the relationships among objects in the image to form a reasoning chain, then gradually increase the difficulty by rewriting the generated question to include more reasoning sub-chains. Experimental results on our constructed dataset show that our benchmark significantly outperforms existing baselines in controlling the reasoning chains of generated questions, producing questions with varying difficulty levels.

Code search aims to quickly locate target code snippets from databases using natural language queries, which promotes code reusability. Existing methods can effectively obtain aligned token-level and query word-level features. However, these studies usually represent the semantics of code and query by averaging the features of each token and word respectively, which makes it difficult to accurately capture the code details that are closely related to the query. To address this issue, we propose a fine-grained code search model that consists of a cross-modal encoder, a mapping layer, and a classification layer. Specifically, we utilize a pre-trained model, GraphCodeBERT, in the cross-modal encoder to align features. In the mapping layer, we introduce a co-attention network to capture the fine-grained interactions between code and query, ensuring a model can precisely identify key code segments relevant to the query. Finally, in the classification layer, we incorporate instruction learning techniques that leverage contextual reasoning to improve the accuracy of query-code matching. Experimental results show that our proposed model significantly outperforms existing methods across multiple programming language datasets.

DNA methylation plays a crucial role in human diseases pathogenesis. Substantial experimental evidence from clinical and biological studies has confirmed numerous methylation-disease associations, which provide valuable prior knowledge for advancing precision medicine through biomarker discovery and disease subtyping. To systematically mine reliable methylation prior knowledge from known DNA methylation-disease associations and develop robust computational methods for precision medicine applications, we propose MethPriorGCN. By integrating layer attention mechanisms and feature weighting mechanisms, MethPriorGCN not only identified reliable methylation digital biomarkers but also achieved superior disease subtype classification accuracy.

Digital Twin (DT) technology represents a cutting-edge methodology that digitally maps physical entities with high fidelity, leading to the Digital Twin Network (DTN) through its integration with network technologies. DTN establishes bidirectional communication between virtual and physical spaces, enabling real-time monitoring, dynamic optimization, and precise control of physical networks. This addresses challenges posed by network expansion and service diversification, revolutionizing the management and optimization of complex network systems. Despite its potential, DTN implementation remains challenging, with research still nascent and lacking detailed guidelines. This paper aims to bridge this gap by presenting a comprehensive survey of the reference architecture for real-world DTN implementation and its key enabling technologies. It begins by defining the conceptual foundation of DTN and reviewing related architectural studies. This is followed by the proposal of a universal and scalable modular DTN architecture, encompassing the physical layer, data layer, DT model layer, and service layer. We then explore the critical enabling technologies required for implementing this architecture and analyze applications enhanced by DTN. Notably, We propose a five-level digital twin model evolution taxonomy framework that systematically reveals the evolution path from basic mapping to ultra-high-fidelity autonomous inference. This framework provides a structured evaluation benchmark for optimizing and advancing digital twin models. Finally, we discuss the primary open issues in DTN, offering theoretical and practical guidance for future research in this field.

Defect detection is a pivotal aspect ensuring product quality and production efficiency in industrial manufacturing. Existing studies on defect detection predominantly focus on locating defects through bounding boxes and classifying defect types. However, their methods can only provide limited information and fail to meet the requirements for further processing after detecting defects. To this end, we propose a novel task called defect detection report generation, which aims to provide more comprehensive and informative insights into detected defects in the form of text reports. For this task, we propose some new datasets, which contain 16 different materials and each defect contains a detailed report of human constructs. In addition, we propose a knowledge-aware report generation model as a baseline for future research, which aims to incorporate additional knowledge to generate detailed analysis and subsequent processing related to defect in images. By constructing defect report datasets and proposing corresponding baselines, we chart new directions for future research and practical applications of this task.

We study the security issue of distributed state estimation under data integrity attacks over wireless sensor networks. We design a detector based on statistical learning to judge the compromised estimate sent from the neighboring sensors. To obtain the best estimation performances, we find an optimal estimator for sensors equipped with the malicious data detector, and find a sufficient condition to ensure the stability of the trace of estimation error covariances (EECs). In addition, we explore the relationship between the steady-state EEC and the parameters of the detector. Finally, by numerical simulations, we show the performances of several typical detectors proposed in the existing works, and verify the influence of the detector parameters on the estimation performances.