While learning to rank (LTR) has been widely used in web search to prioritize most relevant webpages among the retrieved contents subject to the input queries, the traditional LTR models fail to deliver decent performance due to two main reasons: 1) the lack of well-annotated query-webpage pairs with ranking scores to cover search queries of various popularity, and 2) ill-trained models based on a limited number of training samples with poor generalization performance. To improve the performance of LTR models, tremendous efforts have been done from above two aspects, such as enlarging training sets with pseudo-labels of ranking scores by self-training, or refining the features used for LTR through feature extraction and dimension reduction. Though LTR performance has been marginally increased, we still believe these methods could be further improved in the newly-fashioned “interpolating regime”. Specifically, instead of lowering the number of features used for LTR models, our work proposes to transform original data with random Fourier feature, so as to over-parameterize the downstream LTR models (e.g., GBRank or LightGBM) with features in ultra-high dimensionality and achieve superb generalization performance. Furthermore, rather than self-training with pseudo-labels produced by the same LTR model in a “self-tuned” fashion, the proposed method incorporates the diversity of prediction results between the listwise and pointwise LTR models while co-training both models with a cyclic labeling-prediction pipeline in a “ping-pong” manner. We deploy the proposed Co-trained and Over-parameterized LTR system COLTR at Baidu search and evaluate COLTR with a large number of baseline methods. The results show that COLTR could achieve $\Delta NDCG_{4}$ =3.64% $\sim$ 4.92%, compared to baselines, under various ratios of labeled samples. We also conduct a 7-day A/B Test using the realistic web traffics of Baidu Search, where we can still observe significant performance improvement around $\Delta NDCG_{4}$ =0.17% $\sim$ 0.92% in real-world applications. COLTR performs consistently both in online and offline experiments.

Temporal Graph Neural Networks (TGNNs) have become indispensable for analyzing dynamic graphs in critical applications such as social networks, communication systems, and financial networks. However, the robustness of TGNNs against adversarial attacks, particularly sophisticated attacks that exploit the temporal dimension, remains a significant challenge. Existing attack methods for Spatio-Temporal Dynamic Graphs (STDGs) often rely on simplistic, easily detectable perturbations (e.g., random edge additions/deletions) and fail to strategically target the most influential nodes and edges for maximum impact. We introduce the High Impact Attack (HIA), a novel restricted black-box attack framework specifically designed to overcome these limitations and expose critical vulnerabilities in TGNNs. HIA leverages a data-driven surrogate model to identify structurally important nodes (central to network connectivity) and dynamically important nodes (critical for the graph’s temporal evolution). It then employs a hybrid perturbation strategy, combining strategic edge injection (to create misleading connections) and targeted edge deletion (to disrupt essential pathways), maximizing TGNN performance degradation. Importantly, HIA minimizes the number of perturbations to enhance stealth, making it more challenging to detect. Comprehensive experiments on five real-world datasets and four representative TGNN architectures (TGN, JODIE, DySAT, and TGAT) demonstrate that HIA significantly reduces TGNN accuracy on the link prediction task, achieving up to a 35.55% decrease in Mean Reciprocal Rank (MRR) – a substantial improvement over state-of-the-art baselines. These results highlight fundamental vulnerabilities in current STDG models and underscore the urgent need for robust defenses that account for both structural and temporal dynamics. Code and Data are available at https://github.com/ryandhjeon/hia.

The traditional level set algorithm selects the position of the initial contour randomly and lacks the processing of edge information. Therefore, it cannot accurately extract the edge of the brain tissue. In order to solve this problem, this paper proposes a level set algorithm that fuses partition and Canny function. Firstly, the idea of partition is fused, and the initial contour position is selected by combining the morphological information of each region, so that the initial contour contains more brain tissue regions, and the efficiency of brain tissue extraction is improved. Secondly, the canny operator is fused in the energy functional, which improves the accuracy of edge detection of rhesus monkey brain tissue while retaining the advantage of the traditional level set algorithm in processing an uneven gray image. Experimental results show that the algorithm can accurately extract the brain tissue of rhesus monkeys with an accuracy of up to 86%.

Vascular stents are crucial devices in the treatment of cardiovascular diseases, and their structural design and function critically affect therapeutic efficacy and patient prognosis. Conventional stents can effectively restore vascular patency by providing mechanical support to blood vessels. However, they still face significant challenges including restenosis, thrombosis, and limited adaptability to complex patient-specific lesion characteristics. To address these limitations, drug delivery offers an important strategy to modulate the pathological microenvironment, enhance long-term vascular healing, and reduce systemic side effects. Meanwhile, advances in computational simulations have provided powerful tools for optimizing stent design through structural mechanics, hemodynamics, and drug release modeling. Computational approaches enable the rational design of stent architectures with improved mechanical stability, vascular compatibility, and therapeutic regulation. Consequently, the development of vascular stents is evolving toward the synergistic integration of drug delivery, structural optimization, and intelligent design. This review summarizes the latest advances in functional vascular stents, clinical applications and computational design. This work aims to provide valuable insights for the engineering of efficient, precise, and intelligent vascular stents for cardiovascular therapies.