Shaofan Liu, Guoqiang Zhang, Shihan Dou, Huiyuan Zheng, Yiming Zhou, Junjie Ye, Shaowen Wang, Shichun Liu, Jiazheng Zhang, Tao Gui, Qi Zhang, Xuanjing Huang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Zhiheng Xi, Dingwen Yang, Jiaqi Liu, Jixuan Huang, Honglin Guo, Baodai Huang, Tinggang Chen, Qi Zhang, Zhonghang Lu, Chenyu Liu, Jiajun Sun, Jiazheng Zhang, Dingwei Zhu, Xin Guo, Junzhe Wang, Zhihao Zhang, Yuming Yang, Junjie Ye, Minghe Gao, Dongrui Liu, Jiaming Ji, Guohao Li, Tao Gui, Qi Zhang, Xuanjing Huang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Dingwei Zhu, Shihan Dou, Zhiheng Xi, Senjie Jin, Guoqiang Zhang, Jiazheng Zhang, Junjie Ye, Mingxu Chai, Enyu Zhou, Ming Zhang, Yuhui Wang, Caishuang Huang, Chenhao Huang, Yunke Zhang, Yuran Wang, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Chenhao Huang, Ziyu Shen, Yicong Ren, Huiyuan Zheng, Jiazheng Zhang, Mingxu Chai, Ming Zhang, Shihan Dou, Fan Mo, Jie Shi, Tao Gui, Qi Zhang, Xuanjing Huang. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Intelligent transportation systems (ITS) involve data management and operation among multiple parties, making the trustworthiness and transparency of centralized data a highly challenging issue. Blockchain data storage, characterized by its immutability and multi-party collaboration, has emerged as a mainstream technology for trustworthy data sharing among multiple parties. However, the current on-chain data structures based on transactions, e.g., Ethereum’s MPT, struggle to address the scalability and efficient on-chain and off-chain collaboration required for data management with high spatio-temporal characteristics, as seen in intelligent transportation. In this paper, we propose a spatio-temporal scalable Merkle Patricia Tree (sMPT) structure for hierarchical organization of on-chain data objects (DOs), which is mapped to the off-chain transportation data entries through a DO packaging mechanism. The experimental evaluation results demonstrate the effectiveness of the proposed sMPT structure in basic functionality, like on-chain storage and sMPT compression. In terms of efficiency, sMPT outperforms the original MPT in retrieval and verification, particularly in batch verification.

Small samples and significant inter-subject variability are the two main challenges in current electroencephalogram (EEG) based Motor Imagery (MI) Brain-Computer Interface (BCI) decoding methods. To overcome these challenges, we proposed an EEG-based decoding method for MI intentions in mixed-subject settings with adversarial disentanglement, which utilize the EEG decoding focusing on MI related task information and decrease the inference of inter-subject variability under mixed-subject setting. The method includes three main modules: data augmentation module, dual-label training module, disentanglement training module. It first uses a mixed-subject settings approach, which involves shuffling the data from all subjects to augment the data for a single model. We then create a dual-label dataset using motor imagery labels and identity labels. Finally, a disentanglement training strategy is employed to optimize the negative entropy loss, measuring the inter-subject variability. Our experiment results show that our method achieves higher accuracy compared to traditional one-to-one model training methods and lower variance with the mixed-subject settings. It has achieved a $\mathbf{7 5. 9 3 \%}$ average classification accuracy across four classes on the BCIC-IV-2a dataset with the best classification accuracy reaches $\mathbf{9 0. 2 8 \%}$, indicating that our model has the capability to disentangle identity-related information during the feature extraction and has more stable performance across different subjects.

Percolation theory shows that removing a small fraction of critical nodes can lead to the disintegration of a large network into many disconnected tiny subnetworks. The network dismantling task focuses on how to efficiently select the least such critical nodes. Most existing approaches focus on measuring nodes’ importance from either functional or topological viewpoint. Different from theirs, we argue that nodes’ importance can be measured from both of the two complementary aspects: The functional importance can be based on the nodes’ competence in relaying network information; While the topological importance can be measured from nodes’ regional structural patterns. In this paper, we propose an unsupervised learning framework for network dismantling, called DCRS, which encodes and fuses both node diffusion competence and role significance. Specifically, we propose a graph diffusion neural network which emulates information diffusion for competence encoding; We divide nodes with similar egonet structural patterns into a few roles, and construct a role graph on which to encode node role significance. The DCRS converts and fuses the two encodings to output a final ranking score for selecting critical nodes. Experiments on both real-world networks and synthetic networks demonstrate that our scheme significantly outperforms the state-of-the-art competitors for its mostly requiring much fewer nodes to dismantle a network.

This article develops a fuzzy-neural controller for the kinematic and collaborative control of multimanipulator systems. The entire control scheme is designed based on quadratic programming and implemented by a constructed fuzzy-neural controller. A hybrid minimum joint velocity-acceleration index is introduced to adjust the operating performance of each manipulator and reduce the kinetic energy consumption of the system. Besides, a simple but effective set of membership functions and rules are used to describe the variation of controller parameters caused by the operational complexity and vagueness during task executions. The stability and robustness of the controller are verified through theoretical analysis. Finally, simulations and experimental studies of the multimanipulator system are carried out supporting the practicality of our findings.

Can we employ one neural model to efficiently dismantle many complex yet unique networks? This article provides an affirmative answer. Diverse real-world systems can be abstracted as complex networks each consisting of many functional nodes and edges. Percolation theory has indicated that removing only a few vital nodes can cause the collapse of whole network. However, finding the least number of such vital nodes is a rather challenging task for large networks due to its NP-hardness. Previous studies have proposed many centrality measures and heuristic algorithms to tackle this network dismantling (ND) problem. Different from theirs, this article tries to approach the ND task by designing a neural model which can be trained from tiny synthetic networks but will be applied for various real-world networks. It seems a discouraging mission at first sight, as network sizes and topologies are quite different across distinct real-world networks. Nonetheless, this article initiates insightful efforts of designing and training a neural influence ranking model (NIRM). Experiments on fifteen real-world networks validate its effectiveness for its mostly requiring fewer vital nodes to dismantle a network, compared with the state-of-the-art competitors. The key to its success lies in that our NIRM can efficiently encode both local structural and global topological signals for ranking nodes, in addition to our innovative labelling method in training dataset construction.

Whether it be congestion control in cities or massive access in the Internet, these dynamic behaviors can be abstracted as flow demand between origin-destination node pairs (OD pairs) in the network. Links in complex systems are with notable heterogeneity, which means the volume of flow varies greatly, resulting in some critical links being more likely to congest under the flow attack, reducing the service capability of the system, and even causing network collapses. To explore how flow dynamics influences the network functionality and stability under congestion, we propose a link-based flow attack strategy that significantly degrades the service capability between OD pairs. In this approach, we first extract the routing paths and score the vulnerability of links between OD pairs, then an attack flow allocation rule based on critical links is designed to efficiently attack the target flow between OD pairs. Experiments on real-world networks show that the proposed strategy can quickly identify critical links and accurately attack the target flow. Besides, the proposed method provides positive and unique insights for defense strategy and network topology optimization.

In order to leverage the unique advantages of redundant manipulators, avoiding the singularity during motion planning and control should be considered as a fundamental issue to handle. In this article, a distributed scheme is proposed to improve the manipulability of redundant manipulators in a group. To this end, the manipulability index is incorporated into the cooperative control of multiple manipulators in a distributed network, which is used to guide manipulators to adjust to the optimal spatial position. Moreover, from the perspective of game theory, this article formulates the problem into a Nash equilibrium. Then, a neural network with anti-noise ability is constructed to seek and approximate the optimal strategy profile of the Nash equilibrium problem with time-varying parameters. Theoretical analyses show that the neural network model has the superior global convergence and noise immunity. Finally, simulation results demonstrate that the neural network is effective in real-time cooperative motion generation of multiple redundant manipulators under perturbations in distributed networks.