ABSTRACT Recent studies have integrated reputation mechanisms into practical byzantine fault tolerance (PBFT) by evaluating nodes based on their historical performance‐nodes with superior performance receive higher reputations, while those with poorer performance receive lower reputations. Typically, the node with the highest reputation is selected as the primary to reduce the frequency of time‐consuming view changes—a protocol employed to rectify issues arising from a faulty primary. However, such reputation‐based approaches face two significant challenges: maintaining real‐time reputation accuracy requires updating node reputations after each consensus round, leading to considerable computational overhead, and selecting the highest‐reputation node renders it a prime target for malicious attacks. To address these challenges, we propose the adaptive reputation‐based PBFT algorithm with verifiable random function (VRF)‐driven view changes (ARVPBFT). ARVPBFT incorporates an adaptive reputation mechanism that dynamically adjusts the frequency of reputation updates based on view changes, substantially reducing computational overhead. Moreover, by integrating VRFs into the view‐change protocol, ARVPBFT ensures an unpredictable and fair selection among high‐reputation nodes, thereby further enhancing system security. Theoretical analysis and simulation results demonstrate that ARVPBFT significantly outperforms existing algorithms, ultimately achieving a more stable and efficient consensus mechanism.

Digital orthodontics increasingly depends on accurate 3D dental models, yet conventional intraoral scanning remains inaccessible in remote tele-orthodontics, which typically relies on sparse smartphone imagery. While 3D Gaussian Splatting (3DGS) shows promise for novel view synthesis, its application to the standard clinical triad of unposed anterior and bilateral buccal photographs is challenging. The limitations of sparse-view photometric supervision, combined with large baselines, inconsistent illumination, and specular surfaces, can destabilize simultaneous pose and geometry estimation, often inducing frequency bias and over-smoothed reconstructions that lose critical diagnostic details. To address these issues, we propose Dental3R, a pose-free, graph-guided pipeline for robust, highfidelity reconstruction from sparse intraoral photographs. Our method first constructs a Geometry-Aware Pairing Strategy (GAPS) to select a compact subgraph of high-value image pairs, improving correspondence matching, stabilizing geometry initialization, and reducing memory usage. Leveraging on the recovered poses and point cloud, we train the 3DGS model with a wavelet-regularized objective. By enforcing band-limited fidelity via a discrete wavelet transform, our approach preserves fine enamel boundaries and interproximal edges while suppressing high-frequency artifacts. We validate our approach on a largescale dataset of 950 clinical cases and an additional video-based test set of 195 cases, demonstrating that Dental3R effectively handles sparse, unposed inputs and achieves superior novel-view synthesis quality over state-of-the-art methods.

Reliable 3D-2D alignment between intraoral scan (IOS) models and lateral cephalometric radiographs is critical for orthodontic diagnosis, yet conventional intensity-driven registration methods struggle under real clinical conditions, where cephalograms exhibit magnification, distortion, low-contrast dental crowns, and acquisition-dependent variation. These factors hinder the stability of appearance-based metrics and often lead to convergence failures or anatomically implausible alignments. To address these limitations, we propose DentalSCR, named for its silhouette-to-contour registration scheme, a pose-stable and contour-guided framework for accurate and interpretable alignment that achieves state-of-the-art performance. Our method constructs a U-Midline Dental Axis (UMDA) to establish a unified cross-arch anatomical coordinate system, stabilizing initialization and standardizing projection geometry across cases. Using this reference frame, we generate radiograph-like projections via a surface-based DRR (Digitally Reconstructed Radiograph) formulation with coronal-axis perspective and Gaussian splatting, which preserves clinically accurate magnification and emphasizes external silhouettes. Registration is formulated as a 2D similarity transform optimized with a symmetric bidirectional Chamfer distance under a hierarchical coarse-to-fine schedule, enabling both large capture range and subpixel-level contour agreement. We evaluate DentalSCR on 34 expert-annotated cases. Results demonstrate substantial reductions in landmark error, particularly at posterior teeth, tighter lower-jaw dispersion, and low Chamfer and controlled Hausdorff distances. These findings indicate that DentalSCR robustly handles real-world cephalograms and delivers high-fidelity, clinically inspectable 3D-2D alignment, consistently outperforming baselines and establishing a new state-of-the-art.

In robot-assisted minimally invasive surgery, accurate 3D reconstruction from endoscopic video is vital for downstream tasks and improved outcomes. However, endoscopic scenarios present unique challenges, including photometric inconsistencies, non-rigid tissue motion, and view-dependent highlights. Most 3DGS-based methods that rely solely on appearance constraints for optimizing 3DGS are often insufficient in this context, as these dynamic visual artifacts can mislead the optimization process and lead to inaccurate reconstructions. To address these limitations, we present EndoWave, a unified spatiotemporal Gaussian Splatting framework by incorporating an optical flow-based geometric constraint and a multi-resolution rational wavelet supervision. First, we adopt a unified spatiotemporal Gaussian representation that directly optimizes primitives in a 4D domain. Second, we propose a geometric constraint derived from optical flow to enhance temporal coherence and effectively constrain the 3D structure of the scene. Third, we propose a multi-resolution rational orthogonal wavelet as a constraint, which can effectively separate the details of the endoscope and enhance the rendering performance. Extensive evaluations on two real surgical datasets, EndoNeRF [1] and StereoMIS [2], demonstrate that our method EndoWave achieves state-of-theart reconstruction quality and visual accuracy compared to the baseline method.

Accurate prediction of changes in protein-protein binding affinity influenced by mutations (i.e.,$\Delta\Delta G)$is essential for understanding the structure and function of proteins and elucidating the underlying mechanisms of complex diseases. We introduce a novel multi-scale feature fusion network for protein-protein$\Delta\Delta G$prediction, aiming to reduce the dependency of previous methods on intricate biological features and expert-driven knowledge, and demonstrate its effectiveness in the challenging and important domain of protein data. Specifically, we employ multi-scale modeling of protein complexes, and introduce self-attention mechanisms and various extraction modules to comprehensively capture the features. The proposed method effectively learns the complete biological regulation of complexes and incorporates interactions between amino acids. Extensive experiments on three benchmark datasets demonstrate that our proposed framework significantly outperforms the state-of-the-art methods for$\Delta\Delta G$prediction while also providing excellent performance in the domain of membrane protein design.

A structured understanding of intraoral 3D scans is essential for digital orthodontics. However, existing deep-learning approaches rely heavily on modality-specific training, large annotated datasets, and controlled scanning conditions, which limit generalization across devices and hinder deployment in real clinical workflows. Moreover, raw intraoral meshes exhibit substantial variation in arch pose, incomplete geometry caused by occlusion or tooth contact, and a lack of texture cues, making unified semantic interpretation highly challenging. To address these limitations, we propose ArchMap, a training-free and knowledge-guided framework for robust structured dental understanding. ArchMap first introduces a geometry-aware arch-flattening module that standardizes raw 3D meshes into spatially aligned, continuity-preserving multi-view projections. We then construct a Dental Knowledge Base (DKB) encoding hierarchical tooth ontology, dentition-stage policies, and clinical semantics to constrain the symbolic reasoning space. We validate ArchMap on 1060 pre-/post-orthodontic cases, demonstrating robust performance in tooth counting, anatomical partitioning, dentition-stage classification, and the identification of clinical conditions such as crowding, missing teeth, prosthetics, and caries. Compared with supervised pipelines and prompted VLM baselines, ArchMap achieves higher accuracy, reduced semantic drift, and superior stability under sparse or artifact-prone conditions. As a fully training-free system, ArchMap demonstrates that combining geometric normalization with ontology-guided multimodal reasoning offers a practical and scalable solution for the structured analysis of 3D intraoral scans in modern digital orthodontics.

Naturalistic driving action recognition is essential for vehicle cabin monitoring systems. However, the complexity of real-world backgrounds presents significant challenges for this task, and previous approaches have struggled with practical implementation due to their limited ability to observe subtle behavioral differences and effectively learn inter-frame features from video. In this paper, we propose a novel Spatial-Temporal Perception (STP) architecture that emphasizes both temporal information and spatial relationships between key objects, incorporating a causal decoder to perform behavior recognition and temporal action localization. Without requiring multimodal input, STP directly extracts temporal and spatial distance features from RGB video clips. Subsequently, these dual features are jointly encoded by maximizing the expected likelihood across all possible permutations of the factorization order. By integrating temporal and spatial features at different scales, STP can perceive subtle behavioral changes in challenging scenarios. Additionally, we introduce a causal-aware module to explore relationships between video frame features, significantly enhancing detection efficiency and performance. We validate the effectiveness of our approach using two publicly available driver distraction detection benchmarks. The results demonstrate that our framework achieves state-of-the-art performance.

4D millimeter-wave (MMW) radar, which provides both height information and dense point cloud data over 3D MMW radar, has become increasingly popular in 3D object detection. In recent years, radar-vision fusion models have demonstrated performance close to that of LiDAR-based models, offering advantages in terms of lower hardware costs and better resilience in extreme conditions. However, many radar-vision fusion models treat radar as a sparse LiDAR, underutilizing radar-specific information. Additionally, these multi-modal networks are often sensitive to the failure of a single modality, particularly vision. To address these challenges, we propose the Radar Depth Lift-Splat-Shoot (RDL) module, which integrates radar-specific data into the depth prediction process, enhancing the quality of visual Bird's-Eye View (BEV) features. We further introduce a Unified Feature Fusion (UFF) approach that extracts BEV features across different modalities using shared module. To assess the robustness of multimodal models, we develop a novel Failure Test (FT) ablation experiment, which simulates vision modality failure by injecting Gaussian noise. We conduct extensive experiments on the View-of-Delft (VoD) and TJ4D datasets. The results demonstrated that our proposed Unified BEVFusion (UniBEVFusion) network significantly outperforms state-of-the-art models on the TJ4D dataset, with improvements of 3.96% in 3D and 4.17% in BEV object detection accuracy.

Over the past decade, the size of neural network models has gradually increased in both breadth and depth, leading to a growing interest in the application of neural network pruning. Unstructured pruning provides fine-grained sparsity and achieves better inference acceleration under specific hardware support. Unstructured Pruning at Initialization (PaI) optimizes the iterative pruning pipeline, but sparse weights increase the risk of underfitting during training. More importantly, almost all PaI algorithms focus only on obtaining the best pruning mask without considering whether the retained weights are suitable for training. Introducing Lipschitz constants during model initialization can reduce the risk of model underfitting and overfitting. As a result, we firstly analyze the impact of Lipschitz initialization on model training and propose the Repaired Initialization (ReI) algorithm for common modules with BatchNorm. Then, we utilize the same idea to repair the weight of unstructured pruned model, and name it Repaired Pruning at Initialization Resilience (RePaIR) algorithm. Extensive experiments and demonstrate that our proposed ReI and RePaIR can improve the training robustness of unpruned and pruned models, respectively, and achieve up to 1.7% accuracy gain with the same sparse pruning mask on TinyImageNet. Furthermore, we provide an improved SynFlow algorithm called Repair SynFlow (ReSynFlow), which employs Lipschitz scaling to overcome the problem of score computation in deeper models. ReSynFlow can effectively improve the maximum compression rate and is suitable for deeper models, with an accuracy improvement of up to 1.3% compared to the SynFlow algorithm on TinyImageNet.

Predicting reactants from a specified core product remains a critical challenge in retrosynthesis prediction. While semi-template-based and graph-edit-based methods have shown promising results in accuracy and interpretability, they struggle to handle complex reactions. In this paper, complex reactions refer to chemical reactions involving the participation of multiple bonds, such as those involving the multiple reaction center or the same leaving group being attached to multiple atoms. To address these limitations, we propose RetroSiG (Retrosynthesis via Search in (Hyper) Graph), a semi-template-based framework that reformulates retrosynthesis as a two-phase search problem: (i) reaction center identification as a search task in the product molecular graph, and (ii) leaving group completion as a search task in the leaving group hypergraph. RetroSiG’s novel search mechanism systematically explores subgraphs by leveraging reinforcement learning to guide node selection at each step. This approach ensures connectivity and efficient decision-making, thereby enabling the effective handling of complex reaction predictions. In addition, RetroSiG incorporates the one-hop constraint, a domain-specific prior inspired by the observation that reaction center molecular subgraphs and leaving group subgraphs are almost always connected. This constraint focuses exploration on first-order neighbors, significantly reducing the search space and improving computational efficiency without compromising accuracy. Furthermore, RetroSiG leverages a hypergraph structure to model implicit dependencies among leaving groups, which enhances robustness for reactions with multiple leaving group configurations. Comprehensive experiments demonstrate RetroSiG’s competitive performance across standard benchmarks, while ablation studies confirm the contributions of its key design components, including the hypergraph and the one-hop constraint. Our results highlight RetroSiG’s scalability and effectiveness in handling diverse and complex retrosynthesis tasks.

Semi-supervised semantic segmentation allows model to mine effective supervision from unlabeled data to complement label-guided training. Recent research has primarily focused on consistency regularization techniques, exploring perturbation-invariant training at both the image and feature levels. In this work, we proposed a novel feature-level consistency learning framework named Density-Descending Feature Perturbation (DDFP). Inspired by the low-density separation assumption in semi-supervised learning, our key insight is that feature density can shed a light on the most promising direction for the segmentation classifier to explore, which is the regions with lower density. We propose to shift features with confident predictions towards lower-density regions by perturbation injection. The perturbed features are then super-vised by the predictions on the original features, thereby compelling the classifier to explore less dense regions to effectively regularize the decision boundary. Central to our method is the estimation of feature density. To this end, we introduce a lightweight density estimator based on normalizing flow, allowing for efficient capture of the feature density distribution in an online manner. By extracting gradients from the density estimator, we can determine the direction towards less dense regions for each feature. The proposed DDFP outperforms other designs on feature-level perturbations and shows state of the art performances on both Pascal VOC and Cityscapes dataset under various partition protocols. The project is available at https://github.com/Gavinwxy/DDFP.

Since primary nodes play a critical leadership role in PBFT (Practical Byzantine Fault Tolerance) consensus algorithm, it is mandatory to perform an update process for eliminating the malicious primary nodes so as to maintain the security level of PBFT. As it is convenient to calculate node reputations, most of existing updating schemes select the node with the highest reputation as the primary node in every consensus round. However, the round-by-round reputation update mechanism inevitably increases the communication overhead and consensus latency. To reduce the number of update times, we propose an algorithm based on an adaptive reputation mechanism, named Commit Block PBFT or CBPBFT for short. In this mechanism, a node’s reputation is determined by the number of its committed blocks during the most recent period as a primary node. As the reputation update adaptively occurs according to the number of blocks committed by the primary node, the mechanism significantly decreases the frequency of reputation updates, and hence increases the consensus performance. Experimental results show that, CBPBFT reduces the probability of a Byzantine node gaining leadership by 15% and decreases communication latency by 15% to 32% in comparison with the state-of-the art.

Recent semi-supervised semantic segmentation methods combine pseudo labeling and consistency regularization to enhance model generalization from perturbation-invariant training. In this work, we argue that adequate supervision can be extracted directly from the geometry of feature space. Inspired by density-based unsupervised clustering, we propose to leverage feature density to locate sparse regions within feature clusters defined by label and pseudo labels. The hypothesis is that lower-density features tend to be under-trained compared with those densely gathered. Therefore, we propose to apply regularization on the structure of the cluster by tackling the sparsity to increase intra-class compactness in feature space. With this goal, we present a Density-Guided Contrastive Learning (DGCL) strategy to push anchor features in sparse regions toward cluster centers approximated by high-density positive keys. The heart of our method is to estimate feature density which is defined as neighbor compactness. We design a multi-scale density estimation module to obtain the density from multiple nearest-neighbor graphs for robust density modeling. Moreover, a unified training framework is proposed to combine label-guided self-training and density-guided geometry regularization to form complementary supervision on unlabeled data. Experimental results on PAS-CAL VOC and Cityscapes under various semi-supervised settings demonstrate that our proposed method achieves state-of-the-art performances. The project is available at https://github.com/Gavinwxy/DGCL.

In the current era of multi-modal and large models gradually revealing their potential, neural network pruning has emerged as a crucial means of model compression. It is widely recognized that models tend to be over-parameterized, and pruning enables the removal of unimportant weights, leading to improved inference speed while preserving accuracy. From early methods such as gradient-based, and magnitude-based pruning to modern algorithms like iterative magnitude pruning, lottery ticket hypothesis, and pruning at initialization, researchers have strived to increase the compression ratio of model parameters while maintaining high accuracy. Currently, mainstream algorithms focus on the global pruning of neural networks using various scoring functions, followed by different pruning strategies to enhance the accuracy of sparse model. Recent studies have shown that random pruning with varying layer-wise sparsity ratio has achieved robust results for large models and out-of-distribution data. Based on this discovery, we propose a new score called FeatIO, which is based on module input and output feature map sizes. As a score function used in PaI, FeatIO surpasses the performance of other PaI score functions. Additionally, we propose a novel pruning strategy called Pruning with Layer-wise Sparsity Ratio (PLSR), which conbines the layer-wise sparsity ratios and magnitude-based score function, resulting in optimal evaluation performance. Almost all algorithms exhibit improved performance when using our novel pruning strategy. The combination of PLSR and FeatIO consistently outperforms other algorithms in testing, demonstrating the significant potential of our proposed approach. Our code will be available here.

In order to regain the motor control of upper limbs, stroke patients should go through various exercises to resume finger, hand and arm functions. During such exercises, they need constant assistance, guidance and support from either therapists or caregivers. Due to the increase of aging population, the demand for technology support in home-based stroke recovery has rapidly increased in the last decade. This paper presents an interactive prototype designed to facilitate finger grasping, hand gripping and arm reaching exercises at home. It consists of a portable device with light, audio feedback and a computer game with two scenes and visual guidance. Preliminary usability testing in the community with elderly persons indicates that this device is easy to follow, and enjoyable to play. These trials explore the possibility and feasibility of implementing such tangible interactive training at home or in community rehab centers, inspiring us to improve such designs further to support active rehabilitation.

Recent semi-supervised semantic segmentation methods focus on mining extra supervision from unlabeled data by generating pseudo labels. However, noisy labels are inevitable in this process which prevent effective self-supervision. This paper proposes that noisy labels can be corrected based on semantic connections among features. Since a segmentation classifier produces both high and low-quality predictions, we can trace back to feature encoder to investigate how a feature in a noisy group is related to those in the confident groups. Discarding the weak predictions from the classifier, rectified predictions are assigned to the wrongly predicted features through the feature relations. The key to such an idea lies in mining reliable feature connections. With this goal, we propose a class-agnostic relation network to precisely capture semantic connections among features while ignoring their semantic categories. The feature relations enable us to perform effective noisy label corrections to boost self-training performance. Extensive experiments on PASCAL VOC and Cityscapes demonstrate the state-of-the-art performances of the proposed methods under various semi-supervised settings.

Multiple Instance Learning (MIL) has been widely applied in pathology towards solving critical problems such as automating cancer diagnosis and grading, predicting patient prognosis, and therapy response. Deploying these models in a clinical setting requires careful inspection of these black boxes during development and deployment to identify failures and maintain physician trust. In this work, we propose a simple formulation of MIL models, which enables interpretability while maintaining similar predictive performance. Our Additive MIL models enable spatial credit assignment such that the contribution of each region in the image can be exactly computed and visualized. We show that our spatial credit assignment coincides with regions used by pathologists during diagnosis and improves upon classical attention heatmaps from attention MIL models. We show that any existing MIL model can be made additive with a simple change in function composition. We also show how these models can debug model failures, identify spurious features, and highlight class-wise regions of interest, enabling their use in high-stakes environments such as clinical decision-making.

Accurate prediction of a patient's length-of-stay (LOS) in the hospital enables an efficient and effective management of hospital beds. This paper studies LOS prediction for pediatric patients with respiratory diseases using three decision tree methods: Bagging, Adaboost, and Random forest. A data set of 11,206 records retrieved from the hospital information system is used for analysis after preprocessing and transformation through a computation and an expansion method. Two tests, namely bisection test and periodic test, are designed to assess the performance of the prediction methods. Bagging shows the best result on the bisection test (0.296 RMSE, 0.831 R2, and 0.723 Acc ± 1) for the testing set of the whole data test. The performances of the three methods are similar on the periodic test, whereas Adaboost performs slightly better than the other two methods. Results indicate that the three methods are all effective for the LOS prediction. This study also investigates the importance of different data fields to the LOS prediction, and finds that hospital treatment-related data fields contribute more to the LOS prediction than other categories of fields.

Microbial ecosystems are complex, by analyzing co-occurrence modules of microbial communities, we can better understand the conditions of microbial interactions in each environment, and help understand the interaction patterns that maintain the stability of microbial communities. Imbalances in human microbiome are closely related to human disease. Previous modular clustering analysis was based only on the relationship between paired microorganisms. In this paper, we propose calculating the logical relationship between microbial triplet in human body by information entropy and construct a hypergraph based on the triplet network. Based on the hypergraph clustering, we proposed a novel hypergraph clustering algorithm based on intra-class scatter matrix (HCIS) to reconstruct hyperedge similarity, and selected the optimal cluster number by maximizing modularity to analyze higher-order module of microorganisms. The clustering results verify the effectiveness and feasibility of HCIS algorithm for higher-order microbial module analysis.

Passengers move between urban places for diverse interests and drive the metropolitan regions as the aggregation of urban places to group into network communities. This paper aims to examine the relationship between the spatial patterns (represented by the network communities) of mobility flows and places of interest (POIs). Furtherly, it intends to identify the categories of POIs that play the most significant role in shaping the spatial patterns of mobility flows. To achieve these purposes, we partition the study area into disjoint regions and construct the network with each partitioned region as a node and connection between them as links weighted by the mobility flows. The community detection algorithm is implemented on the network to discover spatial mobility patterns, and the multiclass classification based on the logistic regression method is adopted to classify spatial communities featured by POIs. Taking the taxi systems of Shanghai and Beijing as examples, we detect spatial communities based on the movement strengths among regions. Then we investigate their correlations with POIs. It finds that communities’ modularity correlates linearly with POIs; particularly governments, hotels, and the traffic facilities are of the most significance for generating the mobility patterns. This study can provide valuable insight into understanding the spatial mobility patterns from the perspective of POIs.

This letter proposes a generalized method to construct complex wavelets under the framework of rational multiresolution analysis, MRA(M), where M is a rational number. Theorems and examples are given for the construction of complex rational orthogonal wavelets (CROWs) whose real and imaginary parts form an exact Hilbert transform pair. Since the classical Mallat's MRA is a special case of the rational MRA(M) with M=2, the theorems hold for the construction of complex dyadic wavelets. Based on a rational MRA(M) with 1<M<2, the constructed CROWs not only achieve the benefit by capturing the phase information that the real-valued wavelets are lacking but also have the unique fine rational orthogonal property that is suited for specific application scenarios where binary orthogonality achieved by dyadic wavelets is not sufficient for the scale resolution. The CROWs' application in communications as the modulation signal pulse for PSK/QAM signaling is discussed. Specific communication scenarios that could benefit from the properties of this class of complex wavelets include the communication through a multipath/Doppler channel and new CROW-based multicarrier modulation (MCM)/orthogonal frequency division multiplexing (OFDM) systems