Language-Conditioned Manipulation (LCM) facilitates human-robot interaction via Behavioral Cloning (BC), which learns control policies from human demonstrations and serves as a cornerstone of embodied AI. Overcoming compounding errors in sequential action decisions remains a central challenge to improving BC performance. Existing approaches mitigate compounding errors through data augmentation, expressive representation, or temporal abstraction. However, they suffer from physical discontinuities and semantic-physical misalignment, leading to inaccurate action cloning and intermittent execution. In this paper, we present Continuous vision-language-action Co-Learning with Semantic-Physical Alignment (CCoL), a novel BC framework that ensures temporally consistent execution and fine-grained semantic grounding. It generates robust and smooth action execution trajectories through continuous co-learning across vision, language, and proprioceptive inputs (i.e., robot internal states). Meanwhile, we anchor language semantics to visuomotor representations by a bidirectional cross-attention to learn contextual information for action generation, successfully overcoming the problem of semantic-physical misalignment. Extensive experiments show that CCoL achieves an average 8.0% relative improvement across three simulation suites, with up to 19.2% relative gain in human-demonstrated bimanual insertion tasks. Real-world tests on a 7-DoF robot further confirm CCoL’s generalization under unseen and noisy object states.

Network traffic anomaly detection represents a critical cybersecurity task, yet widespread encryption makes this task increasingly challenging. In response, image-based methods that model traffic as visual patterns have emerged as the dominant approach. However, this work pioneers the identification of a pervasive "full-frequency"characteristic and an associated limitation termed "spectral mismatch"within this paradigm. Specifically, while encrypted traffic exhibits prominent high-frequency components, mainstream reconstruction methods demonstrate an inherent bias toward learning low-frequency information. This fundamental mismatch results in incomplete representations that consequently degrade anomaly detection performance. To address this challenge, we propose FreeUp, a novel frequency-decoupled framework designed explicitly for encrypted traffic analysis. FreeUp decomposes traffic data into distinct low- and high-frequency bands, processing them through separate, dedicated branches along with a customized training strategy that ensures stable and independent frequency-specific learning. Furthermore, recognizing that simple reconstruction error proves inadequate for evaluating dual-branch architectures, we introduce an uncertainty-inspired fusion scoring mechanism. This mechanism quantifies the reconstruction uncertainty of the frequency-specific branches and dynamically integrates their outputs, yielding a more comprehensive and reliable anomaly score. Extensive experiments across multiple benchmarks demonstrate that FreeUp consistently outperforms state-of-the-art baselines. The code is available at https://github.com/ikun0124/FreeUp.

Graph Neural Networks (GNNs) are promising for Encrypted Malicious Traffic Detection (EMTD), yet practical deployments often face weak information: broken graph structures, incomplete node features, and scarce training data. Prior methods partially mitigate these issues but still suffer from (i) restricted information propagation range in graph structures, (ii) imprecise graph structure reconstruction resulting in erroneous or missing connections, and (iii) absence of a unified framework to address multiple facets of information sparsity jointly. In response, we propose TrustWI, an uncertainty-aware multi-view framework. It builds three complementary views to recover and enrich signal under weak information: (i) long-range propagation to expand information flow, (ii) post-propagation structural augmentation to repair broken connections, and (iii) view interaction modeling to capture cross-view synergy. We further develop an evidential, uncertainty-aware fusion that quantifies prediction uncertainty at both the view level and the global level, yielding robust decisions. Extensive evaluations across three benchmarks validate the effectiveness of TrustWI, demonstrating substantial improvements in accuracy and trustworthiness under weak information conditions. Notably, our approach advances the state-of-the-art AUC from 85.45% to 89.57% in extreme information-constrained scenarios.

Deep learning has revolutionized autonomous driving; nevertheless, its inherent opacity hinders explainability, an essential requirement for public trust and regulatory approval. Existing explainable autonomous driving research typically employs a multi-task framework, simultaneously generating driving actions and their corresponding explanations (collectively called categories). Most methods use a two-stage approach: extracting category-related features and modeling category correlations separately. This separation overlooks the potential synergy between these two processes. Moreover, existing approaches often rely on simple linear combinations of task-specific losses, which may fail to optimally balance action and explanation objectives. To address these limitations, we propose Dual-Attention with Multi-Objective optimization (DAMO). DAMO introduces a dual-attention mechanism that alternates between cross-attention for category representation learning and self-attention for category correlation modeling, fostering mutual enhancement. Additionally, we devise a multi-objective optimization algorithm that dynamically balances tasks and achieves Pareto optimality with theoretical guarantees. Extensive evaluations on two benchmarks show that DAMO surpasses state-of-the-art baselines and a large vision-language model, delivering up to 13.9% performance improvement and enhanced generalization across diverse driving scenarios.

Network traffic anomaly detection is pivotal in cybersecurity, especially as data volume grows and security requirement intensifies. This study addresses critical limitations in existing reconstruction-based methods, which quantify anomalies relying on intra-sample differences and struggle to detect drifted anomalies. In response, we propose a novel approach, the Uncertainty-Inspired Inter-Sample Differences (UnDiff) method, which leverages model uncertainty to enhance anomaly detection capabilities, particularly in scenarios involving anomaly drift. By employing evidential learning, the UnDiff model gathers evidence to minimize uncertainty in normal network traffic, enhancing its ability to differentiate between normal and anomalous traffic. To overcome the limitations of intra-sample difference quantification in reconstruction-based methods, we propose a novel anomaly score based on inter-sample uncertainty deviation that directly quantifies the anomaly degree. Benefiting from a concise model design and parameterized uncertainty quantification, UnDiff achieves high efficiency. Extensive experiments on three benchmarks demonstrate UnDiff's superior performance in detecting both undrifted and drifted anomalies with minimal computational overhead.

Autonomous driving systems rely on precise trajectory prediction for safe and efficient motion planning. Despite considerable efforts to enhance prediction accuracy, inherent uncertainties persist due to data noise and incomplete observations. Many strategies entail formalizing prediction outcomes into distributions and utilizing variance to represent uncertainty. However, our experimental investigation reveals that existing trajectory prediction models yield unreliable uncertainty estimates, necessitating additional customized calibration processes. On the other hand, directly applying current calibration techniques to prediction outputs may yield sub-optimal results due to using a universal scaler for all predictions and neglecting informative data cues. In this paper, we propose Customized Calibration Temperature with Regularizer (CCTR), a generic framework that calibrates the output distribution. Specifically, CCTR 1) employs a calibration-based regularizer to align output variance with the discrepancy between prediction and ground truth and 2) generates a tailor-made temperature scaler for each prediction using a post-processing network guided by context and historical information. Extensive evaluation involving multiple prediction and planning methods demonstrates the superiority of CCTR over existing calibration algorithms and uncertainty-aware methods, with significant improvements of 11%-22% in calibration quality and 17%-46% in motion planning.

Graph Neural Networks (GNNs) have recently received significant research attention due to their superior performance on a variety of graph-related learning tasks. Most of the current works focus on either static or dynamic graph settings, addressing a single particular task, e.g., node/graph classification, link prediction. In this work, we investigate the question: can GNNs be applied to continuously learning a sequence of tasks? Towards that, we explore the Continual Graph Learning (CGL) paradigm and present the Experience Replay based framework ER-GNN for CGL to alleviate the catastrophic forgetting problem in existing GNNs. ER-GNN stores knowledge from previous tasks as experiences and replays them when learning new tasks to mitigate the catastrophic forgetting issue. We propose three experience node selection strategies: mean of feature, coverage maximization, and influence maximization, to guide the process of selecting experience nodes. Extensive experiments on three benchmark datasets demonstrate the effectiveness of our ER-GNN and shed light on the incremental graph (non-Euclidean) structure learning.

Trajectory-User Linking (TUL) refers to classifying trajectories into the corresponding generated users and has emerged as an essential spatio-temporal data mining task with a broad spectrum of applications, ranging from personalized location recommendation and trip planning to criminal behavior detection and object tracking. Despite the progress made by recent deep learning-based human mobility learning models, some critical factors related to personal context and user-location interactions have not yet been fully explored. Besides, existing works suffer from high computational cost issues due to the increased complexity of trajectory learning and contextual location embedding. In this work, we propose a novel end-to-end model called GNNTUL, composed of a graph neural network (GNN) module and a classifier, to effectively and efficiently learn human mobility and associate the traces to the users in online social networks. GNNTUL is the first GNN-based human mobility learning model exploiting implicit transition patterns behind sparse user traces in online social networks while extracting users' unique motion features and discriminating the motion traces. Extensive experiments conducted on two real- world datasets demonstrate the superiority of GNNTUL over several state-of-the-art baselines in terms of both linking accuracy and learning efficiency.

Network alignment (NA) - i.e., linking entities from different networks (also known as identity linkage) - is a fundamental problem in many application domains. Recent advances in deep graph learning have inspired various auspicious approaches for tackling the NA problem. However, most of the existing works suffer from efficiency and generalization, due to complexities and redundant computations.We approach the NA from a different perspective, tackling it via meta-learning in a semi-supervised manner, and propose an effective and efficient approach called Meta-NA - a novel, conceptually simple, flexible, and general framework. Specifically, we reformulate NA as a one-shot classification problem and address it with a graph meta-learning framework. Meta-NA exploits the meta-metric learning from known anchor nodes to obtain latent priors for linking unknown anchor nodes. It contains multiple sub-networks corresponding to multiple graphs, learning a unified metric space, where one can easily link entities across different graphs. In addition to the performance lift, Meta-NA greatly improves the anchor linking generalization, significantly reduces the computational overheads, and is easily extendable to multi-network alignment scenarios. Extensive experiments conducted on three real-world datasets demonstrate the superiority of Meta-NA over several state-of-the-art baselines in terms of both alignment accuracy and learning efficiency.

Meta-learning has received a tremendous recent attention as a possible approach for mimicking human intelligence, i.e., acquiring new knowledge and skills with little or even no demonstration. Most of the existing meta-learning methods are proposed to tackle few-shot learning problems such as image and text, in rather Euclidean domain. However, there are very few works applying meta-learning to non-Euclidean domains, and the recently proposed graph neural networks (GNNs) models do not perform effectively on graph few-shot learning problems. Towards this, we propose a novel graph meta-learning framework -- Meta-GNN -- to tackle the few-shot node classification problem in graph meta-learning settings. It obtains the prior knowledge of classifiers by training on many similar few-shot learning tasks and then classifies the nodes from new classes with only few labeled samples. Additionally, Meta-GNN is a general model that can be straightforwardly incorporated into any existing state-of-the-art GNN. Our experiments conducted on three benchmark datasets demonstrate that our proposed approach not only improves the node classification performance by a large margin on few-shot learning problems in meta-learning paradigm, but also learns a more general and flexible model for task adaption.