Hemodynamic stress due to the anatomical variations in the cerebrovascular system may lead to the development of intracranial aneurysms. Therefore, these anatomical variations at specific brain locations can serve as imaging markers for aneurysm detection. Graph neural networks have recently gained significant importance for capturing rich representations of complex, irregular structures like the cerebrovascular system. In this work, we propose a graph-based computing approach that uses the graph representation of the cerebrovascular system for detecting and localizing intracranial aneurysms in 3D TOFMRA. To the best of our knowledge, this is the first method that represents 3D TOF-MRA as a graph structure while incorporating anatomical imaging markers for aneurysm detection. The proposed approach utilizes sparsity information in the spectral domain to identify localized events within the graph structure, which serve as strong indicators of aneurysms. Additionally, we employ a graph contrastive loss to enhance graph embeddings, effectively distinguishing aneurysms and improving the overall efficiency of the method. We train and evaluate our model using cross-validation on two 3D TOF-MRA datasets: the publicly available LAUSANNE dataset and the ADAM challenge dataset. On the LAUSANNE dataset, our best model achieved a sensitivity of 87% with a false positive rate (FPR) of 0.43. For the ADAM dataset, the model achieved a sensitivity of 81% with an FPR of 0.17. Incorporating anatomical knowledge into graph construction significantly reduces the FPR compared to state-of-the-art (SOTA) models, thereby enhancing the reliability of the proposed method.
The rapid evolution of Artificial Intelligence (AI) has catalyzed a transition from reactive, task-specific agents toward Agentic AI – autonomous systems capable of independent reasoning, goal-setting, and recursive planning. Despite extensive research and application, existing literature remains fragmented, often conflating individual autonomy with collective agency. This paper provides a comprehensive systematic review that delineates the transition from individual artificial agency (I-AA) to social artificial agency (S-AA). We introduce a unified architectural framework based on a continuous six-component cognitive loop: perception, reasoning, planning, memory, action, and learning. Our taxonomy categorizes agents into four foundational paradigms: traditional, large language model (LLM)-based, embodied, and human digital twin (HDT)-based, while further defining three advanced Agentic AI configurations: agentic LLM-based, agentic LLM+embodied, and agentic LLM+HDT systems. By distinguishing between localized agency in I-AA and emergent agency in S-AA, we explore the complexities of a macro-scale society of heterogeneous agentic ecosystems.
Explainable artificial intelligence (XAI) has become essential for enhancing transparency and trust in artificial intelligence systems applied to education (AIED). However, widely used local explanation methods such as LIME often suffer from instability and inconsistencies between local explanations and global model predictions, which limits their reliability. To address this issue, we propose Inter-model Stacking of Local Explanations (ISLE), an innovative framework that combines LIME generated local predictions derived from multiple heterogeneous models and aggregates them using a stacking mechanism to improve the coherence and reliability of explanations. SMOTE is used as a preprocessing step to handle class imbalance and improve predictive performance. Experiments conducted on a student performance dataset show that ISLE significantly improves explanation quality compared to LIME and SHAP. More specifically, explanation fidelity increases from 66.7% to 93.3%, while stability improves notably (e.g., from 0.40 to 0.80 for the SVM model). In addition, predictive accuracy reaches 96.3% on the balanced dataset. An ablation study further confirms the robustness of the proposed stacking mechanism across different model configurations. It also highlights the impact of class rebalancing and base model selection on ISLE performance, while confirming its ability to produce consistent explanations under varying experimental settings. These results demonstrate that ISLE produces more stable, faithful, and coherent local explanations, thereby enhancing transparency, accountability, and trust in AI-based decision support systems in education. Due to its model-agnostic design, the proposed framework can also be adapted to other domains requiring reliable and consistent explanations.
Recently, the Learning-to-Improve paradigm has shown significant promise in solving routing optimization problems. However, most studies have mainly focused on transformer-based encoder architectures, which tend to aggregate information across the entire instances. These methods often overlook the crucial topological relationships between nodes, leading to excessive computational overhead and suboptimal performance as the problem size grows. To tackle these limitations, we design a dynamic topological graph reinforcement learning (DTGRL) framework that utilizes a bi-level strategy to guide the agent toward the most valuable actions. At the encoding stage, we design a novel Dynamic Topological Graph Attention (DTGA) module. It integrates geometric priors and semantic similarity to generate adaptive structural topology masks that effectively filter out global noise while enforcing a locality-centric inductive bias. At the decoding stage, we introduce a Sparse Compatibility Layer (SCL) that prunes the expansive action space to encourage exploration while exploiting higher-value actions. In our experiments, we train the agent using an n-step proximal policy optimization (PPO) approach. The experimental results demonstrate that DTGRL significantly outperforms the existing Learning-to-Improve methods and showcases superior generalization capabilities across various datasets and benchmarks of different sizes.
While Multimodal Large Language Models (MLLMs) have shown great promise in mathematical reasoning, existing research has predominantly focused on single-visual problems, largely overlooking the complex, multi-visual scenarios common in real-world mathematics. In this paper, we introduce Multi-Visual Attention Prompting on Image (MVAPI), a novel, training-free, and plug-and-play method designed specifically to enhance the multi-visual reasoning abilities of MLLMs. Essentially, MVAPI leverages an auxiliary model to generate query-guided attention heatmaps, which are overlaid onto input images to guide MLLM’s focus toward the most salient, task-relevant visual evidence. To rigorously evaluate MVAPI’s effectiveness in a real-world mathematical setting, we introduce MV-MATH, a new and challenging benchmark featuring 2,009 multi-visual mathematical problems with fine-grained annotations from authentic educational contexts. Our extensive experiments yield two key findings. First, the evaluation on MV-MATH reveals a substantial performance gap between current MLLMs and human capabilities, confirming the profound challenge of this domain. Second, MVAPI consistently and significantly boosts the performance of various MLLMs on MV-MATH. Furthermore, its effectiveness generalizes robustly to other visual reasoning tasks, validating MVAPI as a powerful method for enhancing multi-visual reasoning. Our code and dataset are available.
This article designs an adaptive fuzzy bipartite consensus control method for nonlinear multi-agent systems (MASs) by using the small-gain theorem (SGT). To reduce communication burden, an event-triggered mechanism (ETM) is constructed. The proposed ETM adjusts the dynamic threshold according to the predefined-time tracking errors. The fuzzy logic systems (FLSs) are embedded into the backstepping framework to approximate the unknown nonlinear functions of the MASs. The SGT can be used to simplify the construction of the controller to enhance the robustness of the system. The closed-loop system is transformed into a large-scale system consisting of input-to-state stability (ISS) subsystems. In addition, the time-varying tuning function (TVTF) is also used to set the stabilization time of the system and improve the convergence speed. Finally, simulation results verify the effectiveness of the proposed algorithm.
Federated Learning (FL) provides an effective framework for large model training or adaption, which achieve privacy preservation and reducing the need for extensive data transmission. However, in Federated Learning, the heterogeneity of the data distributions between clients often hinders optimized model fusion, causing local models to converge prematurely to suboptimal solutions. In this paper, we propose AntiTrap-FL, an efficient federated learning approach designed to help clients escape from such local traps. AntiTrap-FL identifies trapped clients by analyzing gradient and accuracy trends. Then, it pairs these clients with the most distant partners in parameter space, introducing perturbations that help them escape local traps. To stabilize knowledge transfer, AntiTrap-FL applies symmetric or asymmetric parameter corrections with adaptive weighting. Comprehensive theoretical analysis provides strong convergence guarantees,and extensive experiments show that AntiTrap-FL achieves up to 4.05% improvement in accuracy over existing FL methods under Non-IID conditions, while maintaining the computational efficiency of edge devices. Additionally, experiments on large vision model fine-tuning show that AntiTrap-FL consistently outperforms baseline methods across varying client scales, achieving up to 4.82% improvement over existing FL methods.
This study presents an optimization strategy for classifiers that rely on the perplexity of paired language models. Perplexity-based features are commonly employed in diverse tasks such as human–machine text discrimination, stylometry, authorship attribution, reading-time prediction, sentiment analysis, and Alzheimer’s disease detection. We identify a systematic Dominant-Model Bias, wherein one model disproportionately favors its own class, thereby degrading classification accuracy. This bias tends to amplify under conditions of training data imbalance. We provide both empirical evidence and a formal characterization of this phenomenon, and we introduce the Delta recalibration strategy to mitigate it. Experiments on independent tasks—Alzheimer’s disease detection, authorship attribution, and native language identification—demonstrate that the Delta recalibration strategy consistently enhances classification accuracy. Its benefits increase with growing class imbalance: in highly skewed scenarios, accuracy improvements reach up to 20% over the unoptimized baseline.11 The code to replicate the reported experiments is available on Github.
Mamba has demonstrated significant potential in image super-resolution due to its linear computational complexity and excellent long-range modeling capabilities. Existing studies typically employ multi-directional scanning to overcome Mamba’s inherent causal constraints, enhancing spatial relationship modeling. However, multi-directional scanning significantly increases computational overhead, undermining Mamba’s advantage in terms of computational complexity. In this work, we conduct a systematic analysis of multi-directional scanning schemes through LAM visualization results and quantitative metric evaluation. Then, we propose CAMSR, a non-causal lightweight super-resolution model based on Mamba that achieves similar content perception. Specifically, it uses a content-aware sequence generator to cluster content-similar feature tokens and generate a reordered sequence of similar feature clusters. Subsequently, a content-aware state-space equation facilitates long-range pixel interactions and captures global context through prompt learning. Finally, spatial and channel-level attention mechanisms further refine features, achieving an effective balance between reconstruction quality and computational complexity. The experimental results demonstrate that our approach achieves superior performance compared with state-of-the-art methods while using fewer parameters. The code is available at https://github.com/nathan66666/CAMSR.git.
Incremental Named Entity Recognition (INER) stands as a pivotal task in information extraction, emphasizing the successive identification of new entity types within unstructured text. Faced with the continuous influx of entity types, INER grapples with two significant challenges: the widespread issue of catastrophic forgetting and the unique shift issue of the non-entity type semantics. While pseudo-labeling-based INER methods have proven effective in addressing these challenges, a previously overlooked issue arises: the biased context problem. Our analysis shows that, in new sentences, the contextual associations of tokens representing old entity types exhibit a significantly stronger bias towards new entity types compared to their contexts in old sentences. This tendency intensifies the degradation of old knowledge while promoting the overfitting of new knowledge. To solve this biased context, we propose a Type-Balanced Contextual Learning (TBCL) method, featuring a sentence-duplet learning scheme and a contextual consistency loss. This approach offers a fresh perspective for INER through context analysis. Extensive experiments across ten INER settings on three highly recognized datasets showcase the efficacy of our TBCL method, highlighting its proficiency in resolving the biased context issue inherent in pseudo-labeling based INER approaches.
Large Language Models suffer from the hallucination that leads to the generation of factually incorrect and logically inconsistent responses. To make a solution to this problem, we propose the SIC-Autonomous Ensemble (SICAE), a Self Iterative Contradiction Autonomous Ensembling framework, for mitigating component LLM hallucination and gaining performance with model ensembling and self-iterative contradiction refinement. We use self-correcting loops for each component LLM for knowledge refinement before aligning the components for generating candidate responses for ranking. Then top candidate responses are selected as intermediate responses and fused to generate the final response. Our framework incorporates three modules, self-iterative refinement, ranking module, and fusion module where final response is obtained using an autonomous weight update mechanism from a pool of candidate LLM responses. To keep the framework computationally less heavy, we are using low-parameter open-source LLMs to generate candidate responses. To ensure the generalizability of our framework, we are evaluating the responses using three benchmark datasets containing factual and logical reasoning questions and proposing an autonomous hyperparameter selection technique for SIC-AE. We validate our approach while comparing the performance of SIC-AE with larger parameterized model such as llama-2-70B and existing state of the art self-iterative and hallucination mitigation techniques while evaluating on corresponding benchmarks as well. Results are evaluated for base LLMs, and after integrating self-iterative contradiction refinement, and finally for the proposed ensemble framework. We achieved a comparative higher accuracy of 1-5% than the SOTA self-refinement techniques and see further improvement of 1-8% in generating responses on different benchmarks for hallucination mitigation while adding LLM ensemble to our framework.
In the realm of fashion design, sketches serve as a medium for expressing distinctive drawing styles and creative intent, capturing intricate details like stroke variations and texture nuances. The advent of sketch-to-image translation technology has notably aided designers. However, existing methods often compromise these sketch details during image generation, resulting in images that deviate from the intended structural and stylistic characteristics of the input sketch. This limitation hampers the ability to offer designers a precise preview of the final output. To overcome this challenge, we introduce HAIFIT, a novel approach that transforms sketches into high-fidelity, lifelike clothing images by integrating multi-scale features and capturing multi-directional feature dependencies to encourage structurally consistent representations. In addition, we develop a diffusion-based variant, D-HAIFIT, to provide a complementary benchmark for evaluating structural consistency and generative fidelity. Through extensive qualitative and quantitative evaluations conducted on the HAIFashion dataset, our method demonstrates superior experimental performance compared to existing approaches, generating clothing images with improved structural consistency and fine-grained detail preservation for practical fashion design workflows. Furthermore, HAIFIT achieves faster training and inference, contributing to improved computational efficiency and reduced design iteration time.
Fixed length time series data is seldom found in real world datasets. In cases such as language, wildlife, and machining processes, data can vary in length. Similarly to real-world scenarios, it is not always feasible to retrain a Machine Learning (ML) model to handle new and old data simultaneously. Continual Learning (CL) was introduced to adapt ML systems to new data while retaining performance on past information and minimizing large training runs. Replay-based methods which use a memory buffer to augment incoming data have emerged as the preeminent approach type for CL. While CL has been applied to many scenarios including time series and images, their performance has yet to be evaluated on Variable-Length Time Series (VLTS) data such as handwriting trajectories, industrial sensing, insect wingbeat spectrograms, and spoken digits. When implementing CL-ML systems, factors affecting performance and implementation cost are important research areas in ML. This paper reports an empirical comparison of padding choices, ML models, CL methods, replay buffer size, computational cost, and accuracy on 4 VLTS datasets. The role of padding in transforming VLTS is examined, with experiments showing different mechanisms affect CL methods dissimilarly with padding responsible for an average of 32.3% accuracy range within CL methods. The computational load-accuracy tradeoff analysis shows that traditional methods such as a Multi-layer Perceptron coupled with Experience Replay and a small buffer improved memory and energy-accuracy efficiency by 111.5% and 14.6%, respectively.
This study presents one of the first systematic investigations of domain-adaptive pretraining for propaganda technique detection in Lithuanian. We perform masked language modeling-based domain-adaptive pretraining on a corpus of 63,648 news articles from non-credible outlets. We evaluate its impact using masked-language probing, propaganda technique recognition through sequence tagging and sentence classification, and comparison with a large language model in a zero-shot setting. In addition to quantitative evaluation, we conduct a qualitative analysis based on a case study of annotation behavior. The results show that domain-adaptive pretraining improves propaganda technique detection in Lithuanian, enhances the ranking of contextually meaningful terms, and improves performance for most techniques, with gains varying across tasks.
Accurate traffic prediction is critical for the development of smart cities, but remains difficult due to complex spatio-temporal dependencies in road networks. Existing methods typically rely on either intra-mixing techniques that process each node independently with shared parameters, or intermixing models that capture aggregate spatial traffic dynamics. However, these approaches often overlook key flow exchange mechanisms or introduce spurious dependencies. To overcome these limitations, we propose a Dual mixing Multi-scale Spatio-Temporal neural network (DiMST), tailored for traffic prediction. DiMST integrates three principal components: (i) a temporal encoder that fuses raw traffic sequences with periodic contextual information; (ii) a spatial encoder that encodes node identities and positional relationships by leveraging spectral representations in both graph and hypergraph domains; and (iii) a dual mixing multi-scale spatio-temporal encoder comprising intra-and inter-mixing layers, realized through multilayer perceptrons and graph and hypergraph wavelet networks across multiple spectral resolutions, enables more accurate modeling of complex dependencies in traffic data. Extensive experiments on real-world traffic datasets demonstrate the effectiveness and superiority of the proposed model for traffic prediction.
This paper studies optimal aggregative coordination in open multi-agent systems, where agent membership, communication topology, and local objectives may vary over time. The problem is formulated as a distributed aggregative optimization task, in which each agent’s local objective depends on its own decision variable and an aggregate generated by all currently active agents. An open-network distributed aggregative gradient tracking algorithm with a residual handoff mechanism for departing agents is developed, which preserves aggregate and gradient-tracking balance across topology transitions. Furthermore, an auxiliary frozen closed-network iteration is introduced, based on which a one-step open-network error recursion is derived by bounding the effects of optimal-point variation, arrivals, departures, and objective switching. Under suitable contraction and handoff small-gain conditions, an explicit ultimate bound is established for the normalized error relative to the optimal solution trajectory. The bound separates the effects of optimal-point variation, objective-switching variation, and open-network membership changes, and quantifies the influence of arrivals, departures, and residual handoff on the tracking accuracy. Numerical experiments on open multi-robot surveillance problems support the theoretical findings and demonstrate the effectiveness of the proposed method under dynamic network changes.
Heterogeneous data, specifically non-independent and identically distributed (non-IID) data, remains a fundamental challenge that degrades the performance of federated learning (FL). This degradation can be alleviated by employing pretrained diffusion models to generate high-quality synthetic data to facilitate training. However, centralized fine-tuning requires access to client data, which conflicts with the decentralized training paradigm of FL. Moreover, the continuous optimization of local models causes knowledge to drift away from the original distribution, impairing the utility of the synthetic data in mitigating data heterogeneity. To address these issues, we propose a novel framework, termed federated diffusion learning with dual-side calibration (FedDiDC), which effectively enhances the global model’s accuracy across heterogeneous distributions without compromising data privacy. Specifically, we decouple the conventional diffusion process into federated fine-tuning of lightweight embedding networks on clients and centralized generation on the server, thereby avoiding direct transmission of raw client data. To further enhance the data utility and tackle the non-IID challenge, a dual-side calibration mechanism is designed: client-side calibration aligns the local optimization trajectory towards the actual data distribution by adjusting the local loss function, and server-side calibration groups clients according to distributional statistics and performs cluster-wise client selection and aggregation, which guides the model aggregation within statistically balanced client clusters. Experimental results on benchmark datasets, including CIFAR-10, CIFAR-100, and Tiny-ImageNet, show the effectiveness of the proposed framework. Particularly under extreme non-IID settings (β = 0.1), FedDiDC achieves up to a 17.76% accuracy improvement compared to existing baseline methods.
With the rapid development of the Industrial Internet of Things (IIoT), the large-scale acquisition of industrial time-series data has become increasingly feasible, providing valuable temporal insights for timely decision-making. Nonetheless, efficient data transmission is often constrained by communication bandwidth limitations. Consequently, the monitoring data are frequently sampled at sparse intervals in practical industrial scenarios, potentially obscuring fine-grained temporal patterns and reducing the effectiveness of downstream analytical tasks. To tackle this challenge, a novel fine-grained data reconstruction framework is proposed for sparsely sampled industrial time-series. Specifically, a semantic-aware loss function is designed to align network output with the ground truth while preserving structural patterns and semantic richness. Additionally, domain knowledge that incorporates measurement and correlation constraints is embedded into data reconstruction via an augmented Lagrangian-based learning paradigm. In this scheme, the reconstructed time-series maintain numerical alignment with coarse-grained observations and preserve intrinsic physical dependencies, facilitating reliable downstream analytical tasks. Extensive experiments on the C-MAPSS dataset, as well as a real-world steel conveyor roller dataset, demonstrate that the proposed framework outperforms state-of-the-art approaches across different downstream analytical tasks. The code is publicly available on https://github.com/ydzhang-cyber/FDRF.
3D anomaly detection has recently emerged as an effective means of high-precision inspection for industrial products. However, most existing methods are typically trained in a single category-specific manner and face significant challenges in multi-category 3D anomaly detection. In this study, we propose an Information-aware Reconstruction model for Multi-category 3D Anomaly Detection (IRM3D-AD). Firstly, an Information Compression Module (ICM) is introduced to improve category specificity by removing redundant group-level features. Then, an Information-aware Mask Attention (IMA) mechanism is developed to mask key features dynamically by evaluating their information contents, thereby enhancing representation ability for all categories. Finally, an Information-aware Encoder and Decoder (IED) enforced by IMA is presented to identify anomalies from multiple categories by calculating reconstruction errors, which is optimized using information bottleneck constraints to maintain specificity and generalization. Experimental results demonstrate that our method outperforms both single-category and multicategory methods, achieving an average object-level AUROC improvement of 5.7%, 3.3%, and 6.3% on Anomaly-ShapeNet, Real3D-AD, and MulSen-AD, respectively.
While latent variable models have been commonly used for industrial soft sensing in the past decade, the performance was recently improved by the idea of deep learning. Through layer-by-layer feature extraction across different layers of the deep model, much more features can be explored from the original process data compared to the shallow model. However, using more features does not mean more satisfactory soft sensing performance, instead, the overfitting risk could be increased and the model interpretability may be reduced due to the large number of deep latent features. In this paper, a sparse learning and regularization method is introduced for modeling the set of latent features captured from the deep latent variable regression model. Through the introductions of both ℓ1 norm and ℓ2 norm into the regression model, feature selection and parameter regularization can be simultaneously implemented. A detailed industrial application example is used to demonstrate the feasibility and effectiveness of the proposed method. Compared to the basic latent variable regression model, the soft sensing performance has been significantly improved (more than 20%) by the sparse learning algorithm.
