Many real-world applications require generating a chronological report from an evolving document stream; Timeline Summarization (TLS) provides a standard testbed for this setting. While large language models (LLMs) improve event synthesis, most LLM-based TLS systems remain monolithic: they repeatedly process overlapping evidence and often mirror the corpus’ bursty reporting patterns, producing redundant timelines with temporal/topical imbalance and high cost. We propose MAS-TLS, a multi-agent framework that casts TLS as a newsroom-like collaboration. A master editor steers balanced coverage by allocating system-visible evidence with a coverage–diversity objective; specialist reporter agents independently draft time-anchored, evidence-grounded events while cross-reviewing to limit redundancy; an adjudication round reconciles competing drafts and consolidates duplicates into a global timeline; and a non-stationary Bayesian controller adaptively staffs agents under token/time budgets. Experiments on three benchmarks show that MAS-TLS improves semantic coverage and temporal grounding while substantially reducing token usage and latency.

This paper investigates movable-antenna (MA) enabled intelligent reflecting surface (IRS)-aided integrated sensing and communication (ISAC) systems, where an MA-enabled base station (BS) serves multiple downlink communication users (CUs) and performs direction-of-arrival (DOA) estimation for a target. The goal is to improve communication performance while satisfying a Cram´er–Rao bound (CRB) requirement for sensing. To balance performance and computational complexity, two MA control schemes including element-wise and array-wise control schemes are considered, allowing antenna elements to adjust their positions individually or in groups as arrays. Two communication rate performance metrics including the sum-rate and minimum-rate are considered to evaluate the throughput and fairness of multi-user communications. To solve the non-convex optimization problems, we develop a product Riemannian manifold optimization (PRMO) method that constructs a product Riemannian manifold space (PRMS) and integrates a penalty method with a Riemannian Broyden–Fletcher–Goldfarb–Shanno (RBFGS) algorithm. Simulation results validate the effectiveness of the proposed PRMO method and show that MA offers advantages over conventional fixed-position antenna (FPA) in IRS-aided ISAC systems. Moreover, simulation results show that while the element-wise control scheme yields the best overall performance, the array-wise control reduces the execution time by over 60% while sacrificing no more than 5% of the achievable communication rate compared with the element-wise control.

Intelligent reflecting surface (IRS) and movable antenna (MA) technologies have been proposed to enhance wireless communications by creating favorable channel conditions. This paper investigates the joint beamforming and antenna position optimization for MA-enabled IRS (MA-IRS)-aided multi-user multiple-input single-output (MU-MISO) communication systems, where the MA-IRS is deployed to aid the communication between the MA-enabled base station (BS) and user equipment (UE). In contrast to conventional fixed position antenna (FPA)-enabled IRS (FPA-IRS), the positions of the reflecting elements of the MA-IRS can be controlled to enhances the wireless channel. To verify the system’s effectiveness and optimize its performance, we formulate a sum-rate maximization problem with a minimum rate threshold constraint for the MU-MISO communication. To tackle the non-convex problem, a product Riemannian manifold optimization (PRMO) method is proposed for the joint optimization of the beamforming and MA positions. Specifically, a product Riemannian manifold space (PRMS) is constructed and the corresponding Riemannian gradient is derived for updating the variables, and the Riemannian exact penalty (REP) method and a Riemannian Broyden-Fletcher-Goldfarb-Shanno (RBFGS) algorithm is exploited to obtain a feasible solution over the PRMS. Simulation results demonstrate that compared with the conventional FPA-IRS-aided communications, the reflecting elements of the MA-IRS can move to the positions with higher channel gain, thus enhancing the system performance. Furthermore, it is shown that optimizing the positions of the reflecting elements brings higher performance gain than controlling the phase shifts of the IRS, and integrating MA with IRS leads to higher performance gains compared to integrating MA with BS.

Driven by intelligent reflecting surface (IRS) and movable antenna (MA) technologies, movable IRS (MIRS) has been proposed to improve the adaptability and performance of conventional IRS, enabling flexible adjustment of the IRS reflecting element positions. This paper investigates MIRS-aided integrated sensing and communication (ISAC) systems. The objective is to minimize the power required for satisfying the quality-of-service (QoS) of sensing and communication by jointly optimizing the MIRS element positions, IRS reflection coefficients, transmit beamforming, and receive filters. To balance the performance-cost trade-off, we proposed two MIRS schemes: element-wise control and array-wise control, where the positions of individual reflecting elements and arrays consisting of multiple elements are controllable, respectively. To address the joint beamforming and position optimization, a product Riemannian manifold optimization (PRMO) method is proposed, where the variables are updated over a constructed product Riemannian manifold space (PRMS) in parallel via penalty-based transformation and Riemannian Broyden–Fletcher–Goldfarb–Shanno (RBFGS) algorithm. Simulation results demonstrate that the proposed MIRS outperforms conventional IRS in power minimization with both element-wise control and array-wise control. Specifically, with different system parameters, the minimum power is achieved by the MIRS with the element-wise control scheme, while suboptimal solution and higher computational efficiency are achieved by the MIRS with array-wise control scheme.

In this paper, we focus on the joint beamforming for intelligent reflecting surface (IRS) aided integrated sensing and communication (ISAC) systems, where a multi-antenna base station (BS) performs multi-user multi-input single-output (MU-MISO) communication and radar sensing simultaneously. Specifically, the direction-of-arrival (DoA) estimation is considered as the task of radar sensing, and we aim to optimize the MU-MISO communication while enhancing the estimation accuracy by ensuring a Cramér-Rao bound (CRB) lower bound. First, for the CRB-constrained sum rate maximization problem, we propose a product Riemannian manifold optimization (PRMO) framework to solve the problems without relaxing the objective functions. Specifically, a product Riemannian manifold space (PRMS) is constructed to satisfy the constraints of the precoding matrix and IRS phase shifts, and the constraint of the CRB threshold is tackled by a Riemannian exact penalty (REP) method. A parallel Riemannian Broyden-Fletcher–Goldfarb-Shanno (P-RBFGS) algorithm is derived to update the parameters over the PRMS. Then, considering the fairness of the MU-MISO communication, the PRMO is further extended to tackle the CRB-constrained max-min optimization by maximizing the minimum rate among all users. Simulation results demonstrate that with the same CRB constraint, the PRMO outperforms the existing method in sum rate maximization with lower computational complexity, and the extended PRMO enables the users to obtain approximately equal rates, thus guaranteeing the fairness of the system.

Cross-media search from large-scale social network big data has become increasingly valuable in our daily life because it can support querying different data modalities. Deep hash networks have shown high potential in achieving efficient and effective cross-media search performance. However, due to the fact that social network data often exhibit text sparsity, diversity, and noise characteristics, the search performance of existing methods often degrades when dealing with this data. In order to address this problem, this article proposes a novel end-to-end cross-media semantic correlation learning model based on a deep hash network and semantic expansion for social network cross-media search (DHNS). The approach combines deep network feature learning and hash-code quantization learning for multimodal data into a unified optimization architecture, which successfully preserves both intramedia similarity and intermedia correlation, by minimizing both cross-media correlation loss and binary hash quantization loss. In addition, our approach realizes semantic relationship expansion by constructing the image-word relation graph and mining the potential semantic relationship between images and words, and obtaining the semantic embedding based on both internal graph deep walk and an external knowledge base. Experimental results demonstrate that DHNS yields better cross-media search performance on standard benchmarks.

Cross-media search is useful for getting more comprehensive and richer information about social network hot topics or events. To solve the problems of feature heterogeneity and semantic gap of different media data, existing deep cross-media quantization technology provides an efficient and effective solution for cross-media common semantic representation learning. However, due to the fact that social network data often exhibits semantic sparsity, diversity, and contains a lot of noise, the performance of existing cross-media search methods often degrades. To address the above issue, this paper proposes a novel fine-grained cross-media representation learning model with deep quantization attention network for social network cross-media search (CMSL). First, we construct the image-word semantic correlation graph, and perform deep random walks on the graph to realize semantic expansion and semantic embedding learning, which can discover some potential semantic correlations between images and words. Then, in order to discover more fine-grained cross-media semantic correlations, a multi-scale fine-grained cross-media semantic correlation learning method that combines global and local saliency semantic similarity is proposed. Third, the fine-grained cross-media representation, cross-media semantic correlations and binary quantization code are jointly learned by a unified deep quantization attention network, which can preserve both inter-media correlations and intra-media similarities, by minimizing both cross-media correlation loss and binary quantization loss. Experimental results demonstrate that CMSL can generate high-quality cross-media common semantic representation, which yields state-of-the-art cross-media search performance on two benchmark datasets, NUS-WIDE and MIR-Flickr 25k.

Time series classification and class imbalance problem are two common issues in a multitude of real-life scenarios. This paper simultaneously explores both issues with deep convolution neural networks (CNNs). Because standard networks treat the majority and minority classes with same class weights, most CNN-based networks fail to classify imbalanced time series. Until recently, there is very little work applying deep learning to imbalanced time series classification (ITSC). Thus, we propose an adaptive cost-sensitive learning strategy to address the ITSC problem. The standard CNN is modified to a cost-sensitive network (CS-CNN), which is able to punish the misclassified samples using a class-dependent cost matrix. Moreover, this cost matrix is automatically updated based on overall class distribution and the CS-CNN’s training performance. The proposed method is extended to FCN, LSTM-FCN and ResNet. It is experimentally tested on five public benchmark UCR datasets and a real-life large volume dataset. Four cost-sensitive CNN-based networks are compared with several data samplers and two traditional ITSC methods. The modified networks are superior in all metrics. Results show that cost-sensitive networks successfully complete the ITSC tasks.

Warehouse management is an important issue in supply chain management. Among all warehouse operations, "order-picking" is the most expensive one and its cost is mainly due to the travelling expenses. In this paper, we study the capacitated warehouse routing problem (CWRP) so as to save the travelling cost, i.e., travelling distance in order-picking. The problem is shown to be strongly NP-hard. However, by noting that the unconstrained routing problem can be tackled by a dynamic programming method, a search heuristic, which is based on the very large-scale neighborhood (VLSN) technique, was designed to solve the capacity-constrained version. We compared the computational results with solutions obtained from branch-and-price method, which are within 1% error bound and identified that our heuristic is efficient in getting high quality solutions of CWRP