As embodied intelligence emerges as a core frontier in artificial intelligence research, simulation platforms must evolve beyond low-level physical interactions to capture complex, human-centered social behaviors. We introduce FreeAskWorld, an interactive simulation framework that integrates large language models (LLMs) for high-level behavior planning and semantically grounded interaction, informed by theories of intention and social cognition. Our framework supports scalable, realistic human-agent simulations and includes a modular data generation pipeline tailored for diverse embodied tasks.To validate the framework, we extend the classic Vision-and-Language Navigation (VLN) task into a semantically enriched Direction Inquiry setting, wherein agents can actively seek and interpret navigational guidance. We present and publicly release FreeAskWorld, a large-scale benchmark dataset comprising reconstructed environments, six diverse task types, 16 core object categories, 63,429 annotated sample frames, and more than 17 hours of interaction data to support training and evaluation of embodied AI systems. We benchmark VLN models, and human participants under both open-loop and closed-loop settings. Experimental results demonstrate that models fine-tuned on FreeAskWorld outperform their original counterparts, achieving enhanced semantic understanding and interaction competency. These findings underscore the efficacy of socially grounded simulation frameworks in advancing embodied AI systems toward sophisticated high-level planning and more naturalistic human-agent interaction.

Abstract Due to the bucket effect, dual-stack hosts face more severe security risks than single-stack hosts, making the discovery and identification of dual-stack hosts particularly important. Traditional studies employ methods such as domain name association and service fingerprinting for dual-stack identification; however, these methods suffer from incomplete identification and limited dual-stack scale. To solve this issue, we introduce the Trilink algorithm, which performs dual-stack host discovery and identification, as well as conducts security analysis, by verifying whether IPv6 addresses conform to the potential dual-stack address format standards, comparing the consistency of port fingerprints between IPv4 and IPv6, and utilizing IP geolocation and IP address ASN matching. The results show that we have discovered a total of 204,825 dual-stack devices across 118 countries and 269 autonomous systems. Meanwhile, our research reveals that dual-stack devices have 27% higher asset exposure across common service types than single-stack devices.

Abstract Cyberspace Surveying and Mapping (CSM) involves the identification and analysis of digital assets to support network management and security, yet its domain-specific named entity recognition (NER) remains underexplored. A key challenge is the semantic gap between general-domain corpora and CSM domain texts, the suboptimal performance of existing named entity recognition (NER) models in accurately identifying entities within CSM data. To tackle obstacles, we proposed a NER model CyMapNER for the CSM domain. A clear definition of named entity categories pertinent to the CSM domain was established initially, followed by the creation of a dedicated NER dataset tailored to this domain. Subsequently, we present a domain adaptation training framework that integrates large language models. It combines with data augments, pseudo-labeling and domain-adaptive pretraining to enhance the adaptability of the NER model. The comparative experimental results demonstrate that CyMapNER models outperforms traditional NER models in CSM datasets. The results reveal that by domain adaptation training framework, the recognition accuracy of CyMapNER model reaches 97%, which achieves an improvement from 5.6% to 18.3% over the state-of-the-art NER models, and it performs well in recognizing complex and sparse entities, highlighting its effectiveness in handling the intricacies of CSM data.

Money laundering is the process of hiding the origin of illicit funds to make them appear legitimate, thereby threatening the integrity of financial systems. To detect money laundering activities, graph neural networks (GNNs) have been widely adopted to model complex relational structures in transaction networks. However, a closer inspection of real-world money laundering cases reveals that launderers deliberately establish connections with multiple licit accounts to mask their illicit attributes. Such disguising behavior introduces network heterogeneity, which contradicts the fundamental assumption of homophily for most GNNs. Additionally, money launderers further conceal their activities by obscuring illicit fund flows through multihop transaction paths. This strategy poses a significant challenge for GNNs, as their limited receptive fields struggle to capture such long-range dependencies. To address these challenges, we propose a dual-view graph representation learning method, named DC-LCG, to detect money laundering. DC-LCG employs complementary local and contextual views to expose disguises and trace illicit flows, respectively. The local view implements a soft-label-guided dynamic grouping and aggregation method that separates nodes into illicit and licit groups, performing probability-weighted aggregations to mitigate network heterogeneity and expose disguises within transaction networks. The contextual view employs a dynamic path pruning method to filter licit nodes and enhance paths relevance, followed by multipath semantic fusion through transformer-based encoding to capture long-range dependencies across multihop transaction paths. A mutual attention mechanism integrates both views to create comprehensive node representations. Experiments on three public transaction datasets show that DC-LCG outperforms state-of-the-art baselines by 2%–10% across evaluation metrics.

Space-air-ground integrated network (SAGIN), as an integration of interconnected space, air, and ground network segments, is expected to see prevalent usage as part of intelligent transportation systems (ITS), providing an enhanced service provision in terms of coverage, flexibility and reliability. However, restricted by the limited and unbalanced network resources, the efficiency and security of the underlying connectivities of SAGIN are of utmost concern for ITS applications. In this paper, a weighted fractional Fourier transform (WFRFT) based parallel complex spreading (PCS) approach is proposed to improve the communication efficiency and security of SAGIN at the physical (PHY-) layer. The concept of WFRFT along with the direct sequence spread spectrum technology establish the security kernel of the proposed scheme. The practicability of the complex-valued WFRFT-spreading architecture is verified by studying the correlation properties of the WFRFT-spreading signals. Taking advantages of the signal uniqueness of WFRFT, the proposed scheme is capable of providing more flexibility in signal characteristic control. Moreover, the complex-valued WFRFT-spreading processing makes the proposed scheme inherently robust against the large Doppler shift distortions in SAGIN. Simulation results demonstrate the superiority of the proposed WFRFT-PCS scheme in terms of communication efficiency and PHY-layer security. Finally, as a proof of concept, an all-digital FPGA prototype system is designed to show the practicability and the performance enhancement of the proposed scheme.

In this paper, we propose an adaptive multi-attributes based physical layer authentication framework for enhanced authenticity provisioning. Instead of optimizing the "threshold" for a preset PHY-layer signature, this paper resort to exploiting and selecting multiple historical better performed PHY-layer attributes for authentication enhancement. In particular, the authenticator of the proposed scheme is designed to be capable of recording the historically performance of each potential attribute. Based on which, the most effective PHY-layer attributes (MEA) would be chosen to improve the reliability of the PHY-layer authentication. This paper experimentally proves that the dimension extension on PHY-layer signature attributes effectively enhances authenticator's capability in signal discrimination. However, with more attribute to observe, it also complicates the predicting and authenticating procedure. Therefore, a learning-based search algorithm is then formulated to facilitate the MEA selection procedure. Both theoretical analysis and experiment results are given to demonstrate the efficiency and superiority of the proposed scheme.

Cross-modal retrieval aims to retrieve relevant data across different modalities (e.g., texts vs. images). The common strategy is to apply element-wise constraints between manually labeled pair-wise items to guide the generators to learn the semantic relationships between the modalities, so that the similar items can be projected close to each other in the common representation subspace. However, such constraints often fail to preserve the semantic structure between unpaired but semantically similar items (e.g. the unpaired items with the same class label are more similar than items with different labels). To address the above problem, we propose a novel cross-modal similarity transferring (CMST) method to learn and preserve the semantic relationships between unpaired items in an unsupervised way. The key idea is to learn the quantitative similarities in single-modal representation subspace, and then transfer them to the common representation subspace to establish the semantic relationships between unpaired items across modalities. Experiments show that our method outperforms the state-of-the-art approaches both in the class-based and pair-based retrieval tasks.

Genetic Algorithm (GA) has been successfully applied to codebook design for vector quantization and its candidate solutions are normally turned by LBG algorithm. In this paper, to solve premature phenomenon and falling into local optimum of GA, a new Genetic Simulated Annealing-based Kernel Vector Quantization (GSAKVQ) is proposed from a different point of view. The simulated annealing (SA) method proposed in this paper can approach the optimal solution faster than the other candidate approaches. In the frame of GA, firstly, a new special crossover operator and a mutation operator are designed for the partition-based code scheme, and then a SA operation is introduced to enlarge the exploration of the proposed algorithm, finally, the Kernel function-based fitness is introduced into GA in order to cluster those datasets with complex distribution. The proposed method has been extensively compared with other algorithms on 17 datasets clustering and four image compression problems. The experimental results show that the algorithm can achieve its superiority in terms of clustering correct rate and peak signal-to-noise ratio (PSNR), and the robustness of algorithm is also very good. In addition, we took “Lena” as an example and added Gaussian noise into the original image then adopted the proposed algorithm to compress the image with noise. Compared to the original image with noise, the reconstructed image is more distinct, and with the parameter value increasing, the value of PSNR decreases.

The paper proposes an 8-bit AMOLED driver IC with a polynomial interpolation DAC. This architecture maintains high-accuracy AMOLED panels with 8-bit compensated gamma correction and supporting low-complex configuration which results in additional occupied die area. The proposed driver consists of a 6-bit gamma correction resistor-string DAC and a 2-bit polynomial interpolation current-modulation sub-DAC. The two-stage DAC leads to a compact die size compared with conventional 8-bit resister-string DAC, and the polynomial interpolation method provides high accurate grey level voltages than linear one. The AMOLED driver was realized in 0.35-μm CMOS process with DNL and INL of 0.43 LSB and 0.43 LSB.