Large Vision--Language Models (LVLMs) frequently fail on knowledge-intensive educational video QA despite the presence of requisite visual evidence. Through region-level analysis, we identify a systematic evidence-suppression pattern: task-critical tokens (e.g., diagrams) exhibit lower representational energy than distractors at the encoder output, rendering them prone to persistent attention neglect during decoding. While a controlled study shows that performance is sensitive to the strength and amount of injected candidate evidence signals, we find that rigid heuristics are insufficient due to sensitivity to token quality. To address this, we propose Bi-level Active Evidence Injection (BAEI), a decoding-time intervention that keeps the LVLM backbone frozen. BAEI employs a lightweight Injection Policy Network (IPN), optimized via GRPO, to dynamically select candidate evidence tokens and predict their token-wise injection strengths. The framework operates on two levels: increasing the contribution of candidate evidence-related signals in shallow layers and performing adaptive correction in deep layers triggered by predictive entropy. Experiments on educational benchmarks demonstrate consistent gains, validating decoding-time evidence intervention as an effective solution for factual alignment. The code is available at https://github.com/diojojolc-cell/BAEI.

With the widespread adoption of online education platforms, an increasing number of students are gaining new knowledge through Massive Open Online Courses (MOOCs). Exercise recommendation have made strides toward improving student learning outcomes. However, existing methods not only struggle with high dropout rates but also fail to match the diverse learning pace of students. They frequently face difficulties in adjusting to inactive students' learning patterns and in accommodating individualized learning paces, resulting in limited accuracy and diversity in recommendations. To tackle these challenges, we propose Neural Re-ranking for Diversified Exercise Recommendation (in short, NR4DER). NR4DER first leverages the mLSTM model to improve the effectiveness of the exercise filter module. It then employs a sequence enhancement method to enhance the representation of inactive students, accurately matches students with exercises of appropriate difficulty. Finally, it utilizes neural re-ranking to generate diverse recommendation lists based on individual students' learning histories. Extensive experimental results indicate that NR4DER significantly outperforms existing methods across multiple real-world datasets and effectively caters to the diverse learning pace of students.

Methods based on variational bayes theorytare widely used to detect community structures in networks. In recent years, many related methods have emerged that provide valuable insights into variational bayes theory. Remarkably, a fundamental assumption remains incomprehensible. Variational bayes-based methods typically employ a posterior distribution that follows a gaussian distribution to approximate the unknown prior distribution. However, the complexity and irregularity of node distributions in real-world networks prompt us to consider what characteristics of network information are suitable for the posterior distribution. Mathematically, inappropriate low- and high-frequency signals in expectation inference and variance inference can intensify the adverse effects of community distortion and ambiguity. To analysis these two phenomena and propose reasonable countermeasures, we conduct an empirical study. It is found that appropriately compressing low-frequency signals during expectation inference and amplifying high-frequency signals during variance inference are effective strategies. Based on these two strategies, this paper proposes a novel variational bayes plug-in, namely VBPG, to boost the performance of existing variational bayes-based community detection methods. Specifically, we modulate the frequency signals during expectation and variance inference to generate a new gaussian distribution. This strategy improves the fitting accuracy between the posterior distribution and the unknown true distribution without altering the modules of existing methods. The comprehensive experimental results validate that methods using VBPG achieve competitive performance improvements in most cases.

Existing community detection methods for attributed multiplex networks focus on exploiting the complementary information from different topologies, while they are paying little attention to the role of attributes. However, we observe that real attributed multiplex networks exhibit two unique features, namely, consistency and homogeneity of node attributes. Therefore, in this paper, we propose a novel method, called ACDM, which is based on these two characteristics of attributes, to detect communities on attributed multiplex networks. Specifically, we extract commonality representation of nodes through the consistency of attributes. The collaboration between the homogeneity of attributes and topology information reveals the particularity representation of nodes. The comprehensive experimental results on real attributed multiplex networks well validate that our method outperforms state-of-the-art methods in most networks.

Since existing methods are often not effective to detect communities with multiple topics in attributed networks, we propose a method named SSAGCN via Autoencoder-style self-supervised learning. SSAGCN firstly designs an adaptive graph convolutional network (AGCN), which is treated as the encoder for fusing topology information and attribute information automatically, and then utilizes a dual decoder to simultaneously reconstruct network topology and attributes. By further introducing the modularity maximization and the joint optimization strategies, SSAGCN can detect communities with multiple topics in an end-to-end manner. Experimental results show that SSAGCN outperforms state-of-the-art approaches, and also can be used to conduct topic analysis well.