Yubo Shan, Kun Zhang, Qiming Xu, Liping Cao, Yingying Cao, Jian Zhang, Yu Wang, Jingyuan Li, Yuanzhuo Wang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Unmanned aerial vehicle (UAV) ad-hoc network is expected to play an important role in the integrated sensing and communication (ISAC) due to its flexible topology and low cost, enabling scalable connectivity. However, the line-of-sight and node mobility of UAVs lead to severe wireless interference and highly dynamic network topology, making the design of distributed medium access control protocols for large-scale UAV adhoc network a critical problem. Here, we propose H-SATMAC, a hybrid self-adaptive TDMA-based MAC protocol for largescale UAV ad-hoc networks. In order to jointly consider the transmission of the periodic and aperiodic packets, we design a hybrid channel resource scheduling method based on time slot groups. The consecutive free time slots in the group are used as the contention window for CSMA-based transmissions. We utilize a dynamic mapping of slot groups and the geohash coding system to avoid hidden terminal problem and loadbalance multiple group resources. Besides, an enhanced time slot adjustment and adaptive frame length method is designed to achieve better channel utilization while avoiding channel collisions between nodes. We conduct theoretical analysis and extensive simulations to evaluate H-SATMAC. Simulation results show that H-SATMAC achieves 22 and above 64 that of the reference protocol.

The rapid advancement of generative models has led to the widespread emergence of highly realistic synthetic images, making the detection of AI-generated content increasingly critical. In particular, diffusion models have recently achieved unprecedented levels of visual fidelity, further raising concerns. While most existing approaches rely on supervised learning, zero-shot detection methods have attracted growing interest due to their ability to bypass data collection and maintenance. Nevertheless, the performance of current zero-shot methods remains limited. In this paper, we introduce a novel zero-shot AI-generated image detection method. Unlike previous works that primarily focus on identifying artifacts in the final generated images, our work explores features within the image generation process that can be leveraged for detection. Specifically, we simulate the image sampling process via diffusion-based inversion and observe that the denoising outputs of generated images converge to the target image more rapidly than those of real images. Inspired by this observation, we compute the similarity between the original image and the outputs along the denoising trajectory, which is then used as an indicator of image authenticity.Since our method requires no training on any generated images, it avoids overfitting to specific generative models or dataset biases. Experiments across a wide range of generators demonstrate that our method achieves significant improvements over state-of-the-art supervised and zero-shot counterparts.

Pre-trained language models are increasingly being used in multi-document summarization tasks. However, these models need large-scale corpora for pre-training and are domain-dependent. Other non-neural unsupervised summarization approaches mostly rely on key sentence extraction, which can lead to information loss. To address these challenges, we propose a lightweight yet effective unsupervised approach called GLIMMER: a Graph and LexIcal features based unsupervised Multi-docuMEnt summaRization approach. It first constructs a sentence graph from the source documents, then automatically identifies semantic clusters by mining low-level features from raw texts, thereby improving intra-cluster correlation and the fluency of generated sentences. Finally, it summarizes clusters into natural sentences. Experiments conducted on Multi-News, Multi-XScience and DUC-2004 demonstrate that our approach outperforms existing unsupervised approaches. Furthermore, it surpasses state-of-the-art pre-trained multi-document summarization models (e.g. PEGASUS and PRIMERA) under zero-shot settings in terms of ROUGE scores. Additionally, human evaluations indicate that summaries generated by GLIMMER achieve high readability and informativeness scores. Our code is available at https://github.com/Oswald1997/GLIMMER.

Abstract Entity recognition of product titles is essential for retrieving and recommending product information. Due to the irregularity of product title text, such as informal sentence structure, a large number of professional attribute words, a large number of unrelated independent entities of various combinations, the existing general named entity recognition model is limited in the e‐commerce field of product title entity recognition. Most of the current studies focus on only one of the two challenges instead of considering the two challenges together. Our approach proposes NEZHA‐CNN‐GlobalPointer architecture with the addition of label semantic network, and uses multigranularity contextual and label semantic information to fully capture the internal structure and category information of words and texts to improve the entity recognition accuracy. Through a series of experiments, we proved the efficiency of our approach over a dataset of Chinese product titles from JD.com, improving the F1‐value by 5.98%, when compared to the BERT‐LSTM‐CRF model on the product title corpus.

Due to the development of web services, many social network sites, as well as online shopping sites have been booming in the past decade, where it is a common phenomenon that people are likely to use multiple services at the same time. On the one hand, previous research findings indicate the data sparsity issues of online shopping accounts, which is caused by the heavy-tailed distribution of user information. On the other hand, in social network sites, the personal information and the corresponding statuses of an account are abundant, and their genuineness is guaranteed either by the service provider, or by the willingness of the account owner to connect to his or her friends in reality. Making use of the correlation between accounts of a same individual is a crucial prerequisite for many interesting cross network applications, such as improving the recommendation performance of the online shopping sites using extra information from social network services. In this paper, we firstly propose a game-theoretic method to identify correlation accounts of individuals between social network sites and online shopping sites with stable matching model, incorporating account profiles as well as historical behaviors. Using the above account relationships, we then put forward a predicting method that combines heterogeneous social network information and online shopping information, to predict the purchasing behaviors. The results show that our method identifies up to 70 % of the correlation accounts between Facebook and eBay, one of the most popular social network sites and online shopping sites in the world, respectively. The experimental results also show that using the correlation account sets, the accuracy of our purchase predicting method outperforms the state-of-the-art methods by 5 %.

ABSTRACT In this paper, we propose a novel modeling method attack–defense stochastic game Petri nets (or ADSGN) to model and analyze the security issues in enterprise network. We firstly give the definition and modeling method algorithm of ADSGN and then propose the algorithm of the strategy. The proposed ADSGN method is successfully applied to describe the attack and defense courses in the enterprise network. Finally, we analyze the mean time to first security breach and the mean time to security breach in the enterprise network quantifiably, and proved that our method can also be applied to other areas with respect to game issues. Copyright © 2012 John Wiley & Sons, Ltd.

In this study, an automatic framework based on text classification is proposed to identify and filter vulgar content in eMule. Filename is used as the feature to carry out the elementary research on the effectiveness of our framework, although filename may be changed freely by eMule users. We aim to achieve high accuracy when identifying and filtering vulgar content, thus to raise the quality of the content delivered in eMule to a higher level.

This paper proposes an efficient algorithm for P2P file sharing systems based on WiMAX mesh mode and Wi-Fi technologies. Wireless networks in our system are hierarchically divided into three layers: Wi-Fi based wireless local area networks under a subscriber station; the mesh network of subscriber stations under a base station; the network of base stations. File lookup procedure may go through three steps: the requesting end host firstly looks up for the requested file within it's neighbor end hosts under the same subscribe station; if fails, then it sends lookup messages to the nearest subscriber stations in the mesh network following to a changed dynamic source routing protocol; if both the steps fail, then the requesting end host searches the requested file through the chord-based base stations' overlay. By statistical analysis and simulations, we prove that our layered P2P file sharing system can reduce the number of lookup messages in physical networks and prevent over expenses of precious bandwidth in wireless metropolitan area networks