Due to the long-range modeling ability and linear complexity property, Mamba has attracted considerable attention in point cloud analysis. Despite some interesting progress, related work still suffers from imperfect point cloud serialization, insufficient high-level geometric perception, and overfitting of the selective state space model (S6) at the core of Mamba. To this end, we resort to an SSM-based point cloud network termed CloudMamba to address the above challenges. Specifically, we propose sequence expanding and sequence merging, where the former serializes points along each axis separately and the latter serves to fuse the corresponding higher-order features causally inferred from different sequences, enabling unordered point sets to adapt more stably to the causal nature of Mamba without parameters. Meanwhile, we design chainedMamba that chains the forward and backward processes in the parallel bidirectional Mamba, capturing high-level geometric information during scanning. In addition, we propose a grouped selective state space model (GS6) via parameter sharing on S6, alleviating the overfitting problem caused by the computational mode in S6. Experiments on various point cloud tasks validate CloudMamba's ability to achieve state-of-the-art results with significantly less complexity.

Huawei Ji, Yuanhao Sun, Yuan Jin, Cheng Deng, Jiaxin Ding, Luoyi Fu, Xinbing Wang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

In modern orchard management, precision agriculture plays a crucial role. However, traditional methods for assessing fruit tree growth often suffer from limitations such as insufficient accuracy and low efficiency. To address these challenges, this study proposes a precise monitoring approach for fruit tree growth by integrating 3D LiDAR SLAM (Simultaneous Localization and Mapping) with point cloud optimization. A mobile robot equipped with a LiDAR sensor performs high-precision environmental scanning within a structured orchard, utilizing SLAM algorithms to generate a three-dimensional orchard map and construct detailed 3D models of trees. Based on these models, key parameters such as trunk diameter at breast height, tree height, and branch dimensions are quantitatively extracted. Experimental results indicate that the proposed method achieves measurement errors of less than 3% for both trunk diameter and tree height, demonstrating strong adaptability to different environments and high measurement efficiency. Compared to traditional manual measurements, this approach effectively overcomes challenges in complex orchard scenarios, providing reliable technical support for fruit tree growth monitoring and scientific management. Furthermore, this study lays a solid foundation for the integration and advancement of 3D LiDAR SLAM technology in precision agriculture.

The attention mechanism has become a dominant operator in point cloud learning, but its quadratic complexity leads to limited inter-point interactions, hindering long-range dependency modeling between objects. Due to excellent long-range modeling capability with linear complexity, the selective state space model (S6), as the core of Mamba, has been exploited in point cloud learning for long-range dependency interactions over the entire point cloud. Despite some significant progress, related works still suffer from imperfect point cloud serialization and lack of locality learning. To this end, we explore a state space model-based point cloud network termed HydraMamba to address the above challenges. Specifically, we design a shuffle serialization strategy, making unordered point sets better adapted to the causal nature of S6. Meanwhile, to overcome the deficiency of existing techniques in locality learning, we propose a ConvBiS6 layer, which is capable of capturing local geometries and global context dependencies synergistically. Besides, we propose MHS6 by extending the multi-head design to S6, further enhancing its modeling capability. HydraMamba achieves state-of-the-art results on various tasks at both object-level and scene-level. The code is available at https://github.com/Point-Cloud-Learning/HydraMamba.

The performance of the neighborhood rough set model in feature selection is limited by nonobjective parameter selection method, the uncertainty measures considered only from a single view, and high time cost caused by processing high-dimensional data. To solve the above problems, this study first defines the interclass boundary to granulate the samples in different classes, and three types of neighborhood concepts—negative perspective, neutral perspective, and positive perspective—are put forward based on different cognitive perspectives. Then, the concept of the multiperspective rough set model is developed. The most prominent feature of this model is the discovery of differences between classes from the given data, without any parameters. Second, by integrating the information theory and algebraic views under the multiperspective rough set model, multiview entropy measures are proposed to effectively measure the uncertainty in data. Moreover, a nonmonotonic feature selection algorithm based on the mutual information in the multiview entropy measures under the neutral perspective as the evaluation function of feature importance is designed to resolve the disadvantages of the algorithms based on the monotone evaluation function. Finally, Information Gain is introduced to preliminarily decrease the dimension of high-dimensional data sets to promote classification accuracy and reduce time consumption. The experimental results confirm that the proposed algorithm is efficient in eliminating noise and increasing classification accuracy.

Solar insecticidal lamps Internet of Things (SIL-IoT) is a new green prevention and control technology for pest management. In the implementation of SIL-IoT to large-scale regions, two practical issues remain to be solved, that is: 1) scheduling the cleaning tasks of SILs periodically and 2) minimizing the insecticidal efficiency reduction over time. As smartphones are widely available among farmers across the globe, mobile crowdsensing (MCS) for agricultural data collection becomes a cost-effective and efficient solution by integrating participatory sensing based on a large group of individuals. This article proposes an MCS-enabled framework to address the SIL maintenance problem (SILMP) and perform system analysis by considering both the partition structure of farmland and the insecticidal efficiency of SILs. In addition, considering the farmland’s practical natural geographical features, we propose dividing the regions of interest into numerous subareas, where each subarea can be considered a separate partition. Finally, we formulate the SILMP framework as two subproblems, i.e., path planning and task selection, and propose two different methods to tackle each problem based on the concept of greedy algorithm. Simulation results show that our proposed methods have improved performance in the tradeoff between task cost and insecticidal efficiency and outperform the three selected baseline algorithms.