The task of dynamic graph link prediction is to forecast the evolution of complex systems. Empirical observations reveal that interactions within these systems exhibit an Entangled Spatio-Temporal Pattern, which manifests through three interrelated phenomena, namely Latent High-Order Bridges, Multi-Frequency Temporal Dynamics, and Spatio-Temporal Entanglement, with stronger structural ties facilitating tolerance for longer temporal gaps. However, limited by computationally prohibitive multi-hop sampling or inefficient long-sequence modeling, existing methods struggle to capture this complex pattern. Inspired by State-Space Models (SSMs) like Mamba for efficient long-range modeling yet aiming to address their native agnosticism to structural and multi-frequency dynamics, we propose a framework named DyGHydra, which couples a tailored Continuous-Time Hierarchical Mamba (CT-HMamba) backbone with a multi-hop structural encoder. The framework first employs the multi-hop structural encoder to reveal latent high-order interactions, extracting interaction-level cross-hop features. Subsequently, the CT-HMamba backbone utilizes these features to address multi-frequency dynamics through a hierarchical architecture, decomposing interaction history to simultaneously model high-frequency bursts and long-term trends. To capture the spatio-temporal entanglement, CT-HMamba further tailors its core state-space mechanism to be co-driven by physical time and structural context. Specifically, physical time governs the state transition decay to reflect temporal forgetting, while structural context modulates the input-output projections to prioritize topologically significant events. Extensive experiments on eleven real-world datasets show that DyGHydra achieves state-of-the-art performance across most settings for both transductive and inductive link prediction, validating its effectiveness in modeling complex temporal dynamics with superior efficiency.

Creating photorealistic and animatable 3D head avatars across multiple views is still an ongoing challenge in AR/VR applications. Although previous studies adopt Neural Radiance Fields (NeRF) with 3D Morphable Model (3DMM) as a prior to produce impressive results in generating 3D heads, they incur considerable time costs and lack rendering quality. In this paper, we propose a novel approach called MGHead that synthesizes high-fidelity dynamic 3D head avatar with realistic appearance and complex deformation. It exploits anchor-based 3D Gaussians to model geometric shape and extends the fundamental deformation structure of a parametric morphable face model to each fixed point, providing greater robustness in responding to expressive variations. Notably, we introduce an expression and pose-dependent attribute adapter that injects driving signals into anchor features to refine neural Gaussian attributes. This adjustment compensates for the deficiencies of linear blend skinning in capturing high-frequency dynamics effectively, further improving the expressive realism and natural appearance of head avatar. Extensive experiments demonstrate the superiority of our model in visual detail quality and quantitative evaluations.

The structure of the backbone network is complex, and the characteristics of multi-layer architecture and non-independent IP layer links lead to a lack of suitable reliability assessment models and methods to evaluate the reliability of the backbone network. To this end, this paper uses decision diagram methods to model the dependency relationship between IP layer links and optical layer components, relaxing the assumption of independent network link failures. The decision diagram can logically combine features, and while retaining the original connectivity reliability and capacity reliability solution methods, it supplements the dependency relationship and inter-layer relationship of the network with subgraph merging operations. In addition, the issue of capacity reliability or business reliability for multi-terminals and all-terminals has not yet yielded a suitable solution. This paper uses the directed acyclic graph feature of the decision diagram to design a state expansion algorithm, which can be used to solve the multi-terminal capacity availability of multi-state networks. Finally, based on the easy-to-parallel characteristics of the decision diagram, parallel methods are designed to parallelize the entire process of network reliability evaluation, which can alleviate the problem of state space explosion.

Knowledge tracing defines the task of predicting future performance of students based on their historical interactions. Recently, some graph-based methods try to capture correspondence between questions and concepts by constructing the question-concept bipartite graph to tackle the knowledge tracing problem. However, they fail to explicitly integrate such intrinsic relations into the final answer predictor due to the sparse data. In this paper, we propose a novel Multi-relation Enhanced Graph-based Model for Knowledge Tracing (MGKT) to tackle the above problem. More specifically, MGKT constructs graph structure to explore multiple relations such as the high-order association among questions and the similarity of question’s attributes. In addition, two self-supervised training strategies, namely hypergraph contrast learning and hypergraph reconstruction, are proposed to incorporate these special correlations into question representations. Extensive experiments demonstrate that MGKT outperforms state-of-the-art knowledge tracing methods on three benchmark datasets.

Super-resolution combined with novel image synthesis is an advanced image processing method to synthesize low-resolution images into new high-resolution images. NeRF-SR is the first model to obtain decent multi-view super-resolution results with only low-resolution input images, but the super-sampling method implemented using the original Nerf’s MLP network cannot represent the complex details of the scene well. We consider that the volume density and color features obtained by the MLP network do not take into account the global geometry along the ray and the color relationship between the sampling points. To tackle this challenge, we introduce an attention-based model and auto-encoding network to synthesize high-fidelity views from low-resolution input to high-resolution output. The attention-based model mixes the pixel color information of the sampling points on each ray and supervises using ground-truth colors. At the same time, the auto-encoding network learns the global geometry along the ray. Experimental results demonstrate that our model can produce high-quality results for high-resolution new view synthesis, both on synthetic and real-world datasets.

Community detection is a well-established problem and nontrivial task in complex network analysis. The goal of community detection is to discover community structures in complex networks. In recent years, many existing works have been proposed to handle this task, particularly nonnegative matrix factorization-based method, e.g. HNMF, BNMF, which is interpretable and can learn latent features of complex data. These methods usually decompose the original matrix into two matrixes, in one matrix, each column corresponds to a representation of community and each column of another matrix indicates the membership between overall pairs of communities and nodes. Then they discover the community by updating the two matrices iteratively and learn the shallow feature of the community. However, these methods either ignore the topological structure characteristics of the community or ignore the microscopic community structure properties. In this paper, we propose a novel model, named Modularized Deep NonNegative Matrix Factorization (MDNMF) for community detection, which preserves both the topology information and the instinct community structure properties of the community. The experimental results show that our proposed models can significantly outperform state-of-the-art approaches on several well-known dataset.