The computational preservation of ancient texts faces unique challenges in non-Chinese linguistic systems, particularly Tibetan manuscripts requiring specialized processing. This study presents an intelligent segmentation framework for classical Tibetan manuscripts through synergistic integration of structural analysis and deep learning. Our principal innovations comprise: (1) A systematic Tibetan Unicode normalization with Vertical Combination Character (VCC) verification mechanism, reducing character classes by 86.57%; (2) An augmented BiLSTM-Attention architecture with residual multi-head attention mechanisms for long-distance dependencies; (3) A linguistically-informed Conditional Random Field (CRF) optimization strategy with soft-constrained transition matrices derived from orthographic rules. Experiments demonstrate superior performance with 99.3% VCC edit distance accuracy and 98.7% character-level F1-score, representing significant improvements over conventional approaches. This framework establishes foundational infrastructure for the computational preservation of ancient Tibetan texts.

Model attribution, which assigns each input feature a value to indicate its contribution to the final predictions, has become the most widely studied paradigm towards explainable artificial intelligence. Evaluation of the existing attribution methods, however, still remains a challenge due to the unavailable ground truth. Prior human-agnostic evaluation approaches typically adopt feature ablation to test how the performance varies by dropping the features of different attribution values. However, these methods suffer from either the missingness bias incurred by the inconsistent data distribution, or the expensive computational cost caused by retraining a large number of models. In this work, we propose an embarrassingly simple yet surprisingly effective evaluation scheme, termed as Random-Ablation training for attrIbution-ablatioN test (RAIN), to balance the missingness bias and computational cost. The core idea underlying RAIN is approximating the data distribution after attribution-based feature ablation with a randomly-ablated data distribution. With the proposed RAIN, we systematically evaluate the existing attribution methods with extensive experiments. Results demonstrate that the proposed method not only significantly alleviates missingness bias issues, but also yields more consistent and reasonable attribution rankings, yet with much cheaper computational cost. Code and model will be made publicly available soon.

Geomagnetic map interpolation aims to infer unobserved geomagnetic data at spatial points, yielding critical applications in navigation and resource exploration. However, existing methods for scattered data interpolation are not specifically designed for geomagnetic maps, which inevitably leads to suboptimal performance due to detection noise and the laws of physics. Therefore, we propose a Physics-informed Diffusion Generation framework (PDG) to interpolate incomplete geomagnetic maps. First, we design a physics-informed mask strategy to guide the diffusion generation process based on a local receptive field, effectively eliminating noise interference. Second, we impose a physics-informed constraint on the diffusion generation results following the kriging principle of geomagnetic maps, ensuring strict adherence to the laws of physics. Extensive experiments and in-depth analyses on four real-world datasets demonstrate the superiority and effectiveness of each component of PDG.

To expand the applicability of decentralized online learning, previous studies have proposed several algorithms for decentralized online continuous submodular maximization (D-OCSM) – a non-convex/non-concave setting with continuous DR-submodular reward functions. However, there exist large gaps between their approximate regret bounds and the regret bounds achieved in the convex setting. Moreover, if focusing on projection-free algorithms, which can efficiently handle complex decision sets, they cannot even recover the approximate regret bounds achieved in the centralized setting. In this paper, we first demonstrate that for D-OCSM over general convex decision sets, these two issues can be addressed simultaneously. Furthermore, for D-OCSM over downward-closed decision sets, we show that the second issue can be addressed while significantly alleviating the first issue. Our key techniques are two reductions from D-OCSM to decentralized online convex optimization (D-OCO), which can exploit D-OCO algorithms to improve the approximate regret of D-OCSM in these two cases, respectively.

Deep models are vulnerable to performance degradation caused by various factors, such as imbalanced samples, inaccurate labels, and backdoor attacks. However, existing optimization methods that address these issues are typically designed in a scenario- or architecture-specific manner, and each optimization often requires costly training. To this end, inspired by image denoising, we propose parameter purification as a new paradigm for model performance optimization. Parameter purification attributes performance degradation to the contamination of model parameters and aims to recover clean parameters from corrupted ones in a manner analogous to image denoising. To purify parameters with massive scale and complex structure, we further introduce a novel parameter manifold purification method. In this framework, high-dimensional and complex parameters are first viewed as manifolds embedded in a high-dimensional space, and are then partitioned into nested local parameter-cluster manifolds via a proposed parameter clustering strategy. Meanwhile, to remove parameter redundancy while preserving global parameter information, we propose an implicit manifold auto-encoder along with a parameter-cluster discrepancy loss to learn low-dimensional representations of parameter-cluster manifolds. Finally, an implicit conditional diffusion model is applied to denoise the low-dimensional parameter manifolds, progressively restoring clean parameters. Extensive experiments under three representative scenarios that cause model performance degradation demonstrate that parameter manifold purification can accurately and completely purify corrupted parameters of unseen models, analogous to denoising unseen images, and rapidly improve model performance.

Despite the remarkable generative capabilities of Large Language Models (LLMs), existing long-form document generation methods frequently suffer from structural collapse and logical drift as the document length increases.We identify the root cause as a persistent structural retrieval gap, where traditional Retrieval-Augmented Generation (RAG) paradigms focus almost exclusively on fine-grained factual snippets while neglecting the macro-level organizational logic required for coherent narratives. To bridge this gap, we propose a pioneering hierarchical structure-retrieved generation framework (HS-RAG) that reconceptualizes the generation task as a systematic retrieval-alignment-fusion process from template to text, marking a fundamental paradigm shift from spontaneous generation to grounded structural anchoring. The proposed framework introduces three core methodological innovations: (1) A novel dual-stream structural indexing mechanism that extracts retrievable prototypes from historical templates, effectively closing the structural retrieval gap; (2) An adaptive query-guided alignment algorithm that maps unstructured user intents into explicit hierarchical logical constraints; (3) A reinforcement learning (RL)-driven hierarchical relevance feedback optimization strategy designed to dynamically maximize the alignment between generated content, retrieved structures, and external knowledge. Extensive experiments across four diverse datasets demonstrate that our approach significantly outperforms state-of-the-art baselines, including GPT-5.2 and advanced RAG variants. Specifically, our framework achieves an exceptional Structure Match Rate (SMR) of 0.951 and a semantic fidelity score (BERTScore) of 0.921 on AcademicPapers dataset, outperforming the strongest SOTA baseline by 5.43% and 4.19%, respectively. These compelling quantitative indicators validate that explicit structural priors are essential for mitigating long-range incoherence in controllable document generation.

To address the issues of the disconnection between static and dynamic data in existing temporal graph data models and the insufficient usability of temporal graph query languages, this paper proposes the temporal property graph model compatible with static graphs (TPGMSG), a temporal property graph model compatible with static graphs, along with its query language the temporal graph query language compatible with static graphs (TGQLSG). The model distinguishes between dynamic and static elements, supports the temporal evolution of nodes, edges, and attributes. TGQLSG, as a temporal extension of GQL (the graph query language standard), offers a declarative syntax and comprehensive temporal query capabilities. Furthermore, a Neo4j-based implementation scheme is proposed, where a converter transforms TGQLSG queries into GQL queries. Experimental results show that this model achieves 20.7% and 40.3% improvements in time performance compared to traditional property graphs and static-incompatible models, respectively, while reducing storage space by 79.7%.

Link prediction is a foundational task in temporal graphs. While temporal graph neural networks exhibit commendable performance, they are often criticized for providing inadequate representations, especially under limited data. Contrastive learning has been introduced as a solution for graph pre-training to mitigate data scarcity. However, the data augmentation techniques on which they depend frequently lead to suboptimal augmentations, manifesting either as over-augmentation or under-augmentation. In light of these challenges, we explore the under-explored domain of contrastive learning of temporal graph transformers and propose a novel model, \model, which employs a dual-view graph transformer. This transformer is fine-tuned to extract sequences tailored for specific target nodes, encapsulating both spatial and temporal perspectives. To optimize the contrastive learning of this dual-view transformer, we put forth an innovative, learnable data augmentation method. This technique, which involves selective masking of elements within dual-view sequences, generates superior augmentations, thereby amplifying the potency of the contrastive learning approach. Extensive experiments on five public temporal network datasets demonstrate that our model can consistently outperform all baselines, especially in small training set conditions.

Recent advances in Large Language Models (LLMs) have underscored the potential of Reinforcement Learning (RL) to facilitate the emergence of reasoning capabilities. Despite the encouraging results, a fundamental dilemma persists as RL improvement relies on learning from high-quality samples, yet the exploration for such samples remains bounded by the inherent limitations of LLMs. This, in effect, creates an undesirable cycle in which what cannot be explored cannot be learned. In this work, we propose Rubric-Scaffolded Reinforcement Learning (RuscaRL), a novel instructional scaffolding framework designed to break the exploration bottleneck for general LLM reasoning. Specifically, RuscaRL introduces checklist-style rubrics as (1) explicit scaffolding for exploration during rollout generation, where different rubrics are provided as external guidance within task instructions to steer diverse high-quality responses. This guidance is gradually decayed over time, encouraging the model to internalize the underlying reasoning patterns; (2) verifiable rewards for exploitation during model training, where we can obtain robust LLM-as-a-Judge scores using rubrics as references, enabling effective RL on general reasoning tasks. Extensive experiments demonstrate the superiority of the proposed RuscaRL across various benchmarks, effectively expanding reasoning boundaries under the Best-of-N evaluation.

Decentralized online convex optimization (D-OCO) is a popular framework for distributed applications with streaming data. To tackle the communication bottleneck, previous studies have investigated D-OCO with compressed communication and proposed several algorithms that are variants of online gradient descent (OGD). However, for D-OCO with exact communication, the best existing algorithms are variants of follow-the-regularized-leader (FTRL). In this paper, for the first time, we propose two FTRL-type algorithms for D-OCO with compressed communication. Compared with OGD-type algorithms, our algorithms are more elegant in both algorithmic design and theoretical analysis. The key insight is that the dual update mechanism of FTRL allows us to make a simple application of the technique for average consensus with communication compression. More specifically, our first algorithm considers the full-information setting, and can match the existing regret bounds. Our second algorithm is designed for the bandit setting, and can significantly improve both the regret bounds and communication costs of existing algorithms.

Audio-driven emotional talking face generation aims to synthesize realistic videos with expressive facial dynamics. However, existing methods struggle to balance controllability and visual fidelity. Although implicit representations capture rich semantics, they lack structural guidance, often resulting in averaged emotional expressions. In contrast, explicit geometric methods offer better control over facial expressions but tend to sacrifice high-frequency texture details. To address it, we propose GemTalk, a diffusion-based framework that combines the semantic richness of implicit representations with the structural precision of explicit geometric priors. We introduce a Vision-guided Audio Emotion Projection (V-AEP) module to extract implicit emotional lip and expression features. At the same time, a Diffusion-based Geometric Priors Generator (D-GPG) generates identity-aware blendshape coefficients as explicit structural priors. Crucially, our Geometry-guided Emotion Modulation (GEM) module leverages these geometric priors to recalibrate the magnitude of implicit features, enabling precise, continuous control over emotional expressions, especially emotion intensity, without sacrificing visual quality. Extensive experiments show GemTalk achieves superior performance in photo-realism, and facial emotional dynamics.

Pathology images are crucial for cancer diagnosis and treatment. Although artificial intelligence has driven rapid advancements in pathology image analysis, the interpretation of ultra-large and multi-scale pathology images in clinical practice still heavily relies on physicians' experience. Clinicians need to repeatedly zoom in and out on individual slides to compare and assess pathological details - a process that is both time-consuming and prone to visual fatigue. The system first employs a diffusion model to perform tissue segmentation on pathology images, then calculates pathological tissue proportions and morphological metrics. Finally, through multi-scale dynamic comparison and multi-level visual evaluation, the system facilitates comprehensive and precise analysis of pathology images. The system provides clinicians with an intelligent and interactive tool for pathology image interpretation, enabling efficient visualization and precise analysis of pathological details, thereby reducing the effort require for detailed analysis.

Human mobility prediction is crucial for applications ranging from location-based recommendations to urban planning, which aims to forecast users' next location visits based on historical trajectories. While existing mobility prediction models excel at capturing sequential patterns through diverse architectures for different scenarios, they are hindered by the long-tailed distribution of location visits, leading to biased predictions and limited applicability. This highlights the need for a solution that enhances the long-tailed prediction capabilities of these models with broad compatibility and efficiency across diverse architectures. To address this need, we propose the first architecture-agnostic plugin for long-tailed human mobility prediction, named Adaptive LOcation HierArchy learning (ALOHA). Inspired by Maslow's theory of human motivation, we exploit and explore common mobility knowledge of head and tail locations derived from human mobility trajectories to effectively mitigate long-tailed bias. Specifically, we introduce an automatic pipeline to construct city-tailored location hierarchies based on Large Language Models (LLMs) and Chain-of-Thought (CoT) prompts, capturing high-level mobility semantics with minimal human verification. We further design an Adaptive Hierarchical Loss (AHL) that rebalances learning through Gumbel disturbance and node-wise adaptive weighting, enabling both exploitation of multi-level signals and exploration within semantically related groups. Extensive experiments across multiple state-of-the-art models demonstrate that ALOHA consistently improves long-tailed mobility prediction performance by up to 16.59% while maintaining efficiency and robustness. Our code is at https://github.com/Star607/ALOHA.

Deep learning has shown strong potential for massive multiple-input multiple-output (Massive MIMO) physical-layer tasks, including channel state information (CSI) feedback and channel estimation. However, environmental heterogeneity can severely degrade CSI models in unseen scenarios, while conventional adaptation requires target-domain data and substantial computation. This paper proposes Channel Conditional Parameter Generation (CCPG), an end-to-end pipeline for rapid deployment of CSI models in dynamic wireless environments. CCPG identifies scene-sensitive adaptation bottlenecks through component-freezing experiments and generates only lightweight LoRA weights instead of full model parameters. It compresses high-dimensional channel features into compact latent conditions using cascaded SVD and a Perceiver Resampler. An energy-based canonicalization mechanism mitigates permutation and sign ambiguities in LoRA weights, while a diffusion-based generator incorporates structural information and an asymmetric size-aware loss for topology-aware parameter generation. Experiments on DeepMIMO and WAIR-D for CSI feedback and channel estimation show that CCPG adapts to new scenarios in about 3 seconds with a single forward pass, without target-scenario training or fine-tuning, and achieves cross-domain recovery performance comparable to costly online adaptation. These results demonstrate that CCPG enables efficient deployment of CSI models in large-scale dynamic wireless scenarios for intelligent 6G communications.

Real-time, high-fidelity monocular depth estimation from remote sensing imagery is crucial for numerous applications, yet existing methods face a stark trade-off between accuracy and efficiency. Although using Vision Transformer (ViT) backbones for dense prediction is fast, they often exhibit poor perceptual quality. Conversely, diffusion models offer high fidelity but at a prohibitive computational cost. To overcome these limitations, we propose Depth Detail Diffusion for Remote Sensing Monocular Depth Estimation (D³-RSMDE), an efficient framework designed to achieve an optimal balance between speed and quality. Our framework first leverages a ViT-based module to rapidly generate a high-quality preliminary depth map construction, which serves as a structural prior, effectively replacing the time-consuming initial structure generation stage of diffusion models. Based on this prior, we propose a Progressive Linear Blending Refinement (PLBR) strategy, which uses a lightweight U-Net to refine the details in only a few iterations. The entire refinement step operates efficiently in a compact latent space supported by a Variational Autoencoder (VAE). Extensive experiments demonstrate that D³-RSMDE achieves a notable 11.85% reduction in the Learned Perceptual Image Patch Similarity (LPIPS) perceptual metric over leading models like Marigold, while also achieving over a 40× speedup in inference and maintaining VRAM usage comparable to lightweight ViT models.

Unsupervised action segmentation (UAS) aims to identify action boundaries in long, untrimmed videos without the use of annotations. This involves learning discriminative frame features and applying a segmentation mechanism to organize frames into coherent action segments. However, most of the common approaches ignore the importance of multi-scale temporal interactions within the video sequence, resulting in a limited frame representation capability and inaccurate action boundary detection. In this paper, we propose MulSclTE, a novel UAS framework that incorporates multi-scale temporal interactions across global, clip, and frame levels to enhance the overall performance. To address the limited representation capability, we first present global-level interaction enhancement by implementing a bi-directional temporal encoding mechanism, designed to capture comprehensive information across the entire sequence. Then, we devise a hierarchical self-supervised loss function equipped with a clip-level interaction constraint that aims to bring temporally adjacent clips closer while separating non-adjacent ones. To precisely identify action boundaries, we provide comprehensive information by integrating frame-level prediction errors and similarity scores to alleviate the under-segmentation issue, and present a refinement mechanism to mitigate the over-segmentation issue. Extensive experiments on Breakfast, YouTube Instructions, 50Salads, and EPIC-KITCHENS show that MulSclTE attains leading or second-best performance across all datasets, and even exceeds some supervised methods in MoF and F1 metrics, underscoring its robustness and effectiveness.

Subgraph matching, a cornerstone of relational pattern detection in domains ranging from biochemical systems to social network analysis, faces significant computational challenges due to the dramatically growing search space. Existing methods address this problem within a filtering-ordering-enumeration framework, in which the enumeration stage recursively matches the query graph against the candidate subgraphs of the data graph. However, the lack of awareness of subgraph structural patterns leads to a costly brute-force enumeration, thereby critically motivating the need for intelligent navigation in subgraph matching. To address this challenge, we propose Neural Graph Navigation (NeuGN), a neuro-heuristic framework that transforms brute-force enumeration into neural-guided search by integrating neural navigation mechanisms into the core enumeration process. By preserving heuristic-based completeness guarantees while incorporating neural intelligence, NeuGN significantly reduces the First Match Steps by up to 98.2% compared to state-of-the-art methods across six real-world datasets.

Merging multiple Low-Rank Adaptation (LoRA) experts into a single backbone is a promising approach for efficient multi-task deployment. While existing methods strive to alleviate interference via weight interpolation or subspace alignment, they rest upon the implicit assumption that all LoRA matrices contribute constructively to the merged model. In this paper, we uncover a critical bottleneck in current merging paradigms: the existence of negative modules —specific LoRA layers that inherently degrade global performance upon merging. We propose E volutionary N egative M odule P runing ( ENMP ), a plug-and-play LoRA pruning method to locate and exclude these detrimental modules prior to merging. By leveraging an evolutionary search strategy, ENMP effectively navigates the discrete, non-differentiable landscape of module selection to identify optimal pruning configurations. Extensive evaluations demonstrate that ENMP consistently boosts the performance of existing merging algorithms, achieving a new state-of-the-art across both language and vision domains. Code is available at https://github.com/CaoAnda/ENMP-LoRAMerging.

Computational pathology has made progress in diagnosis and prognosis prediction from whole slide images (WSIs), yet pipelines still rely on patch-level feature extraction and aggregation, departing from the cell-centric reasoning used by pathologists. This gap limits sensitivity to micro-lesions and subtle changes, and current methods rarely provide a unified solution that supports both local and global tasks with trustworthy evidence. We propose Cello, a universal cell-wise feature aggregation framework for reliable pathology image analysis. Cello integrates cell-level representations into WSI modeling via protein-signal–supervised cell-wise learning, preserving fine-grained cellular cues under gigapixel constraints. For local tasks, Cello introduces a flexible prototype-based contrastive module for scalable, task-adaptive representation learning. For global tasks, Cello adopts a weakly supervised gated aggregation that can widely leverage WSI labels. Finally, a cell–local–global decision-route consistency objective dynamically aggregates cellular evidence and aligns local predictions with global outcomes, improving reliability and faithfulness. Trained with only hundreds to thousands of samples, Cello achieves performance gains of 3.0%~7.6% and outperforms SOTA pathology foundation models pretrained on tens of thousands of samples. Code is available at https://anonymous.4open.science/r/Cello.

Answer-only reinforcement learning (RL) trains reasoning models to solve fully specified problems, but many realistic queries omit a premise needed for a unique answer. In this setting, the useful response is not always refusal: the model should ask for the missing premise, condition its answer on the unknown quantity, or abstain when no informative conditional response is available. We present Ask-Condition-Abstain Reinforcement Learning (ACA-RL), a data-augmented RL framework for this setting. Its reasoning-graph-guided pipeline converts well-posed problems into missing-premise training instances with localized gap annotations; ACA-RL then trains on these instances with a structured reward over five observable response behaviors. We also introduce the Missing-Premise Benchmark (MPB), a 274-instance human-verified benchmark spanning mathematical, logical, and real-world word problems. Across Qwen3 and Llama models, ACA-RL consistently improves on MPB while preserving competitive performance on well-posed reasoning tasks. Together with the released code, MPB, and training data, this work supports a new mission for NLP evaluation: measuring whether models can recognize when a task is underdetermined and handle uncertainty, not only whether they can answer fully specified questions.