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.

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.

Previous literature on policy diversity in reinforcement learning (RL) either focuses on the online setting or ignores the policy performance. In contrast, offline RL, which aims to learn high-quality policies from batched data, has yet to fully leverage the intrinsic diversity of the offline dataset. Addressing this dichotomy and aiming to balance quality and diversity poses a significant challenge to extant methodologies. This paper introduces a novel approach, termed Stylized Offline RL (SORL), which is designed to extract high-performing, stylistically diverse policies from a dataset characterized by distinct behavioral patterns. Drawing inspiration from the venerable Expectation-Maximization (EM) algorithm, SORL innovatively alternates between policy learning and trajectory clustering, a mechanism that promotes policy diversification. To further augment policy performance, we introduce advantage-weighted style learning into the SORL framework. Experimental evaluations across multiple environments demonstrate the significant superiority of SORL over previous methods in extracting high-quality policies with diverse behaviors. A case in point is that SORL successfully learns strong policies with markedly distinct playing patterns from a real-world human dataset of a popular basketball video game "Dunk City Dynasty."

Reinforcement Learning (RL) has demonstrated substantial potential across diverse fields, yet understanding its decision-making process, especially in real-world scenarios where rationality and safety are paramount, is an ongoing challenge. This paper delves in to Explainable RL (XRL), a subfield of Explainable AI (XAI) aimed at unravelling the complexities of RL models. Our focus rests on state-explaining techniques, a crucial subset within XRL methods, as they reveal the underlying factors influencing an agent's actions at any given time. Despite their significant role, the lack of a unified evaluation framework hinders assessment of their accuracy and effectiveness. To address this, we introduce XRL-Bench, a unified standardized benchmark tailored for the evaluation and comparison of XRL methods, encompassing three main modules: standard RL environments, explainers based on state importance, and standard evaluators. XRL-Bench supports both tabular and image data for state explanation. We also propose TabularSHAP, an innovative and competitive XRL method. We demonstrate the practical utility of TabularSHAP in real-world online gaming services and offer an open-source benchmark platform for the straightforward implementation and evaluation of XRL methods. Our contributions facilitate the continued progression of XRL technology.

Multi-turn response selection is a challenging task due to its high demands on efficient extraction of the matching features from abundant information provided by context utterances. Since incorporating syntactic information like dependency structures into neural models can promote a better understanding of the sentences, such a method has been widely used in NLP tasks. Though syntactic information helps models achieved pleasing results, its application in retrieval-based dialogue systems has not been fully explored. Meanwhile, previous works focus on intra-sentence syntax alone, which is far from satisfactory for the task of multi-turn response where dialogues usually contain multiple sentences. To this end, we propose SIA, Syntax-Informed Attention, considering both intra- and inter-sentence syntax information. While the former restricts attention scope to only between tokens and corresponding dependents in the syntax tree, the latter allows attention in cross-utterance pairs for those syntactically important tokens. We evaluate our method on three widely used benchmarks and experimental results demonstrate the general superiority of our method on dialogue response selection.

Self-supervised monocular depth estimation (MDE) models universally suffer from the notorious edge-fattening issue. Triplet loss, as a widespread metric learning strategy, has largely succeeded in many computer vision applications. In this paper, we redesign the patch-based triplet loss in MDE to alleviate the ubiquitous edge-fattening issue. We show two drawbacks of the raw triplet loss in MDE and demonstrate our problem-driven redesigns. First, we present a min. operator based strategy applied to all negative samples, to prevent well-performing negatives sheltering the error of edge-fattening negatives. Second, we split the anchor-positive distance and anchor-negative distance from within the original triplet, which directly optimizes the positives without any mutual effect with the negatives. Extensive experiments show the combination of these two small redesigns can achieve unprecedented results: Our powerful and versatile triplet loss not only makes our model outperform all previous SoTA by a large margin, but also provides substantial performance boosts to a large number of existing models, while introducing no extra inference computation at all.

In recommender systems, reinforcement learning solutions have effectively boosted recommendation performance because of their ability to capture long-term user-system interaction. However, the action space of the recommendation policy is a list of items, which could be extremely large with a dynamic candidate item pool. To overcome this challenge, we propose a hyper-actor and critic learning framework where the policy decomposes the item list generation process into a hyper-action inference step and an effect-action selection step. The first step maps the given state space into a vectorized hyper-action space, and the second step selects the item list based on the hyper-action. In order to regulate the discrepancy between the two action spaces, we design an alignment module along with a kernel mapping function for items to ensure inference accuracy and include a supervision module to stabilize the learning process. We build simulated environments on public datasets and empirically show that our framework is superior in recommendation compared to standard RL baselines.

We investigate the problem of video Referring Expression Comprehension (REC), which aims to localize the referent objects described in the sentence to visual regions in the video frames. Despite the recent progress, existing methods suffer from two problems: 1) inconsistent localization results across video frames; 2) confusion between the referent and contextual objects. To this end, we propose a novel Dual Correspondence Network (dubbed as DCNet) which explicitly enhances the dense associations in both the inter-frame and cross-modal manners. Firstly, we aim to build the inter-frame correlations for all existing instances within the frames. Specifically, we compute the inter-frame patch-wise cosine similarity to estimate the dense alignment and then perform the inter-frame contrastive learning to map them close in feature space. Secondly, we propose to build the fine-grained patch-word alignment to associate each patch with certain words. Due to the lack of this kind of detailed annotations, we also predict the patch-word correspondence through the cosine similarity. Extensive experiments demonstrate that our DCNet achieves state-of-the-art performance on both video and image REC benchmarks. Furthermore, we conduct comprehensive ablation studies and thorough analyses to explore the optimal model designs. Notably, our inter-frame and cross-modal contrastive losses are plug-and-play functions and are applicable to any video REC architectures. For example, by building on top of Co-grounding, we boost the performance by 1.48% absolute improvement on [email protected] for VID-Sentence dataset.

Image fusion integrates a series of images acquired from different sensors,e.g., infrared and visible, outputting an image with richer information than either one. Traditional and recent deep-based methods have difficulties in preserving prominent structures and recovering vital textural details for practical applications. In this article, we propose a deep network for infrared and visible image fusion cascading a feature learning module with a fusion learning mechanism. Firstly, we apply a coarse-to-fine deep architecture to learn multi-scale features for multi-modal images, which enables discovering prominent common structures for later fusion operations. The proposed feature learning module requires no well-aligned image pairs for training. Compared with the existing learning-based methods, the proposed feature learning module can ensemble numerous examples from respective modals for training, increasing the ability of feature representation. Secondly, we design an edge-guided attention mechanism upon the multi-scale features to guide the fusion focusing on common structures, thus recovering details while attenuating noise. Moreover, we provide a new aligned infrared and visible image fusion dataset, RealStreet, collected in various practical scenarios for comprehensive evaluation. Extensive experiments on two benchmarks, TNO and RealStreet, demonstrate the superiority of the proposed method over the state-of-the-art in terms of both visual inspection and objective analysis on six evaluation metrics. We also conduct the experiments on the FLIR and NIR datasets, containing foggy weather and poor light conditions, to verify the generalization and robustness of the proposed method.

Current data-center applications tend to process increasingly large volume of data sets. The caching effect of page cache is reduced by its limited capacity. Emerging flash-based solid state drives (SSD) have latency and price advantages compared to hard disk and DRAM. Thus, SSD-based caching is widely deployed in data centers. However, SSD caching faces two challenges. First, SSD has limited write endurance, which requires cache manager to reduce write amount to SSD. Second, data-center workloads exhibit a diverse I/O access patterns, which requires one to figure out SSD caching friendly access patterns. This paper first classifies 6 I/O access patterns among 32 data-center workloads using a cost-benefit analysis. We derive implications for designing SSD cache from analyzing the access patterns. We then propose an SSD cache manager S-RAC with re-adding blocks and ghost cache adaptation to retain SSD friendly blocks in SSD. The experimental evaluation shows the efficiency of S-RAC in reducing SSD write amount while improving/maintaining cache hit ratio.