While large vision-language models (VLMs) demonstrate impressive long-context understanding, their prevalent small branches fails on linguistics-photography alignment for limited window size. We discover that knowledge distillation improve students capability as compelementary to Rotary Position Embeddings (RoPE) on certain windows size (anchored from large models). Building on this insight, we propose LAid, which explicitly targets the transfer of long-range attention mechanisms through two complementary components: (1) a progressive distance-weighted attention matching that dynamically emphasizes longer position differences during training, and (2) a learnable RoPE response gain modulation that selectively amplifies position sensitivity where needed. Extensive experiments across multiple model families demonstrate that LAid-distilled models achieve up to 3.2× longer effective context windows compared to baseline small models, while maintaining or improving performance on standard VL benchmarks. Spectral analysis also suggests that LAid successfully preserves crucial low-frequency attention components that conventional methods fail to transfer. Our work not only provides practical techniques for building more efficient long-context VLMs but also offers theoretical insights into how positional understanding emerges and transfers during distillation.
论文检索
输入标题、作者或关键词，从 960 篇学术成果中精准定位
The emergence of accurate open large language models (LLMs) has sparked a push for advanced quantization techniques to enable efficient deployment on end-user devices. In this paper, we revisit the challenge of extreme LLM compression---targeting ultra-low-bit quantization for both activations and weights---from a Fourier frequency domain perspective. We propose SpecQuant, a two-stage framework that tackles activation outliers and cross-channel variance. In the first stage, activation outliers are smoothed and transferred into the weight matrix to simplify downstream quantization. In the second stage, we apply channel-wise low-frequency Fourier truncation to suppress high-frequency components while preserving essential signal energy, improving quantization robustness. Our method builds on the principle that most of the weight energy is concentrated in low-frequency components, which can be retained with minimal impact on model accuracy. To enable runtime adaptability, we introduce a lightweight truncation module during inference that adjusts truncation thresholds based on channel characteristics. On LLaMA-3 8B, SpecQuant achieves 4-bit quantization for both weights and activations, narrowing the zero-shot accuracy gap to only 1.5% compared to full precision, while delivering 2× faster inference and 3× lower memory usage.
Length-Adaptive Interest Network for Balancing Long and Short Sequence Modeling in CTR Prediction
PDF ↗User behavior sequences in modern recommendation systems exhibit significant length heterogeneity, ranging from sparse short-term interactions to rich long-term histories. While longer sequences provide more context, we observe that increasing the maximum input sequence length in existing CTR models paradoxically degrades performance for short-sequence users due to attention polarization and length imbalance in training data. To address this, we propose LAIN (Length-Adaptive Interest Network), a plug-and-play framework that explicitly incorporates sequence length as a conditioning signal to balance long- and short-sequence modeling. LAIN consists of three lightweight components: a Spectral Length Encoder that maps length into continuous representations, Length-Conditioned Prompting that injects global contextual cues into both long- and short-term behavior branches, and Length-Modulated Attention that adaptively adjusts attention sharpness based on sequence length. Extensive experiments on three real-world benchmarks across five strong CTR backbones show that LAIN consistently improves overall performance, achieving up to 1.15% AUC gain and 2.25% log loss reduction. Notably, our method significantly improves accuracy for short-sequence users without sacrificing long-sequence effectiveness. Our work offers a general, efficient, and deployable solution to mitigate length-induced bias in sequential recommendation.
The widespread adoption of graph neural networks (GNNs) has brought increased attention to fairness issues related to sensitive attributes, such as gender and race, in practical scenarios. However, this concern remains largely unexplored in the context of graph clustering. Conventional fair graph clustering methods primarily depend on spectral clustering approaches. Meanwhile, we argue that existing graph learning works mainly focus on a single type of fairness, whereas graph clustering should achieve group equality-informed individual fairness. In this paper, we introduce for the first time a fairness-aware framework termed FairGC for deep graph clustering, which integrates the dual objectives of individual and group fairness while maintaining accurate clustering results. Specifically, we construct two views with distinct semantics using Siamese encoders. Then, we apply multi-step random walks on view-specific affinity graphs to capture high-order affinities of node pairs, thereby reformulating the contrastive learning with a focus on individual similarity. Besides, we utilize adversarial learning by making node representations independent of the estimated sensitive attributes to further eliminate group biases of clustering results. Extensive experiments on four benchmarks demonstrate the effectiveness and superiority of our proposed framework FairGC.
SEED: Spectral Entropy-Guided Evaluation of Spatial-Temporal Dependencies for Multivariate Time Series Forecasting
PDF ↗Effective multivariate time series forecasting often benefits from accurately modeling complex inter-variable dependencies. However, existing attention- or graph-based methods face three key issues: (a) strong temporal self-dependencies are often disrupted by irrelevant variables; (b) softmax normalization ignores and reverses negative correlations; (c) variables struggle to perceive their temporal positions. To address these, we propose **SEED**, a Spectral Entropy-guided evaluation framework for spatial-temporal dependency modeling. SEED introduces a Dependency Evaluator, a key innovation that leverages spectral entropy to dynamically provide a preliminary evaluation of the spatial and temporal dependencies of each variable, enabling the model to adaptively balance Channel Independence (CI) and Channel Dependence (CD) strategies. To account for temporal regularities originating from the influence of other variables rather than intrinsic dynamics, we propose Spectral Entropy-based Fuser to further refine the evaluated dependency weights, effectively separating this part. Moreover, to preserve negative correlations, we introduce a Signed Graph Constructor that enables signed edge weights, overcoming the limitations of softmax. Finally, to help variables perceive their temporal positions and thereby construct more comprehensive spatial features, we introduce the Context Spatial Extractor, which leverages local contextual windows to extract spatial features. Extensive experiments on 12 real-world datasets from various application domains demonstrate that SEED achieves state-of-the-art performance, validating its effectiveness and generality.
Multiphase flow simulation is critical in science and engineering but incurs high computational costs due to complex field discontinuities and the need for high-resolution numerical meshes. While Neural Operators (NOs) offer an efficient alternative for solving Partial Differential Equations (PDEs), they struggle with two core challenges unique to multiphase systems: spectral bias caused by spatial heterogeneity at phase interfaces, and the persistent scarcity of expensive, high-resolution field data. This work introduces the Interface Information Aware Neural Operator (IANO), a novel architecture that mitigates these issues by leveraging readily obtainable interface data (e.g., topology and position). Interface data inherently contains the high-frequency features not only necessary to complement the physical field data, but also help with spectral bias. IANO incorporates an interface-aware function encoding mechanism to capture dynamic coupling, and a geometry-aware positional encoding method to enhance spatial fidelity for pointwise super-resolution. Empirical results across multiple multiphase flow cases demonstrate that IANO achieves significant accuracy improvements (up to ~10%) over existing NO baselines. Furthermore, IANO exhibits superior generalization capabilities in low-data and noisy settings, confirming its utility for practical, data-efficient AI-based multiphase flow simulations.
As Large Language Models (LLMs) are increasingly integrated in diverse applications, obtaining reliable measures of their predictive uncertainty has become critically important. A precise distinction between aleatoric uncertainty, arising from inherent ambiguities within input data, and epistemic uncertainty, originating exclusively from model limitations, is essential to effectively address each uncertainty source. In this paper, we introduce Spectral Uncertainty, a novel approach to quantifying and decomposing uncertainties in LLMs. Leveraging the Von Neumann entropy from quantum information theory, Spectral Uncertainty provides a rigorous theoretical foundation for separating total uncertainty into distinct aleatoric and epistemic components. Unlike existing baseline methods, our approach incorporates a fine-grained representation of semantic similarity, enabling nuanced differentiation among various semantic interpretations in model responses. Empirical evaluations demonstrate that Spectral Uncertainty outperforms state-of-the-art methods in estimating both aleatoric and total uncertainty across diverse models and benchmark datasets.
Temporal graph classification plays a critical role in applications such as cybersecurity, brain connectivity analysis, social dynamics, and traffic monitoring. Despite its significance, this problem remains underexplored compared to temporal link prediction or node forecasting. Existing methods often rely on snapshot-based or recurrent architectures that either lose fine-grained temporal information or struggle with long-range dependencies. Moreover, local message-passing approaches suffer from oversmoothing and oversquashing, limiting their ability to capture complex temporal structures. We introduce T3FORMER, a novel Topological Temporal Transformer that leverages sliding-window topological and spectral descriptors as first-class tokens, integrated via a specialized Descriptor-Attention mechanism. This design preserves temporal fidelity, enhances robustness, and enables principled cross-modal fusion without rigid discretization. T3former achieves state-of-the-art performance across multiple benchmarks, including dynamic social networks, brain functional connectivity datasets, and traffic networks. It also offers theoretical guarantees of stability under temporal and structural perturbations. Our results highlight the power of combining topological and spectral insights for advancing the frontier of temporal graph learning.
Multivariable time series forecasting methods can integrate information from exogenous variables, leading to significant prediction accuracy gains. The transformer architecture has been widely applied in various time series forecasting models due to its ability to capture long-range sequential dependencies. However, a naïve application of transformers often struggles to effectively model complex relationships among variables over time. To mitigate against this, we propose a novel architecture, termed Spectral Operator Neural Network (Sonnet). Sonnet applies learnable wavelet transformations to the input and incorporates spectral analysis using the Koopman operator. Its predictive skill relies on the Multivariable Coherence Attention (MVCA), an operation that leverages spectral coherence to model variable dependencies. Our empirical analysis shows that Sonnet yields the best performance on 34 out of 47 forecasting tasks with an average mean absolute error (MAE) reduction of 2.2% against the most competitive baseline. We further show that MVCA can remedy the deficiencies of naïve attention in various deep learning models, reducing MAE by 10.7% on average in the most challenging forecasting tasks.
Beyond Missing Data Imputation: Information-Theoretic Coupling of Missingness and Class Imbalance for Optimal Irregular Time Series Classification
PDF ↗Irregular time series (IRTS) are prevalent in real-world applications, where uneven sampling and missing data pose fundamental challenges to deep learning-based feature modeling. Although existing methods attempt to retain timestamp information, they often overlook the structured patterns embedded within the missingness itself, and tend to perform poorly when confronted with class imbalance exacerbated by data incompleteness. Specifically, temporal irregularity hinders the modeling of long-range dependencies and local patterns, while sparse observations limit representational capacity, disproportionately impairing minority classes and leading to severe classification bias. To address these deeply coupled challenges, we propose SPECTRA (Structured Pattern and Enriched Context-aware Temporal Representation Architecture), a unified framework for robust IRTS classification. SPECTRA introduces a frequency-guided observation encoder that reconstructs temporal dependencies in a stable manner, mitigating spectral distortion and information corruption. Complementarily, a missingness pattern encoder explicitly captures the dynamic evolution of missing data and leverages it as a discriminative signal. In addition, a prototype-constrained classification paradigm directly optimizes the geometric structure of the feature space, enhancing intra-class compactness and alleviating generalization bottlenecks caused by class imbalance. Extensive experiments on three public IRTS datasets—P12, P19, and PAM—demonstrate the superior performance of SPECTRA under both missing and imbalanced conditions.
Towards Non-Stationary Time Series Forecasting with Temporal Stabilization and Frequency Differencing
PDF ↗Time series forecasting is critical for decision making across dynamic domains such as energy, finance, transportation, and cloud computing. However, real-world time series often exhibit non-stationarity, including temporal distribution shifts and spectral variability, which poses significant challenges for existing long-term time series forecasting methods. In this paper, we propose DTAF, a dual-branch framework that addresses non-stationarity in both the temporal and frequency domains. For the temporal domain, the Temporal Stabilizing Fusion (TFS) module employs a non-stationary mix of experts (MOE) filter to disentangle and suppress temporal non-stationary patterns while preserving long-term dependencies. For the frequency domain, the Frequency Wave Modeling (FWM) module applies frequency differencing to dynamically highlight components with significant spectral shifts. By fusing the complementary outputs of TFS and FWM, DTAF generates robust forecasts that adapt to both temporal and frequency domain non-stationarity. Extensive experiments on multiple real-world benchmarks demonstrate that DTAF outperforms state-of-the-art baselines, yielding significant improvements in forecasting accuracy under non-stationary conditions.
SVGL: Scale-Variable Graph Learning in Model Space for Multivariate Time Series Classification
PDF ↗Multivariate time series classification (MTSC) has broad applications in numerous domains. Existing MTSC methods typically focus on either temporal dynamics or variable interactions of the data, often overlooking cross-scale couplings among different variables. To bridge this gap, we propose Scale-Variable Graph Learning (SVGL), a novel framework that effectively captures data-inherent scale-variable interactions for MTSC. SVGL begins with spectral analysis to adaptively identify key periodic scales for each variable. A period-aware reservoir computing network is then incorporated to fit the variable at these scales, encoding the sequential and periodic dynamics into multi-scale dynamic representations. Subsequently, we construct a scale-variable graph to model interactions of the encoded temporal dynamics, where nodes represent scale-variable pairs and edges denote their correlations. After sparsely initializing the graph via nearest neighbors, a parallel graph learning architecture is integrated in SVGL, combining global graph convolutional and sample-specific graph attention to aggregate effective features for classification. Extensive experiments on 30 UEA datasets demonstrate that SVGL outperforms state-of-the-art baselines in accuracy and maintains low training overhead.
Graph Neural Networks (GNNs) have demonstrated strong performance across various tasks by leveraging the structural information inherent in graph-structured data. To address the challenge of edge heterophily, where connected nodes may have dissimilar labels or features, two main families of GNNs have emerged: Mixture-of-Experts (MoE) based spatial GNNs and frequency filtering based spectral GNNs. While MoE-based spatial GNNs intuitively assign experts to different hops without solid theoretical grounding, spectral GNNs are based on principled insights from graph signal processing but often rely on manually designed filters and global operators, limiting their scalability and adaptability. In this work, we identify an inherent connection between these two families by showing that the eigengraph components in spectral methods can be treated as experts within an MoE framework. Building on this insight, we propose MORGAN, a novel spectral GNN that integrates Mixture-of-Experts into the spectral domain. MORGAN performs eigen-decomposition of the graph Laplacian, partitions the spectrum into multiple frequency bands, and assigns a dedicated expert network to each band. A learnable gating function dynamically combines these experts based on the spectral characteristics of the input. To support scalable and inductive learning, we further develop MORGAN(L), which incorporates subgraph sampling to enable localized spectral filtering without requiring full access to the graph Laplacian. Extensive experiments on 16 real-world benchmark datasets show that MORGAN achieves competitive or superior performance compared to state-of-the-art baselines, particularly in inductive node classification under heterophilic settings.
Dynamic Semantic Tokenization for Time Series via Elastic Sampling on Physics-aware Perception
PDF ↗Despite the remarkable success of semantic token learning in NLP and vision domains, token-level representation mechanisms face fundamental challenges when extended to continuous time series analysis. We identify a core limitation lies in the intrinsic absence of semantically meaningful tokenization boundaries within time-series, which differs substantially from discrete text tokens and presents unique complexities compared to spatially coherent image patches. While existing works mechanically apply fixed-length partitioning, recent evidence from time series foundation models reveals performance ceilings in prediction tasks under such paradigms. This paper introduces a novel tokenization framework known as physics-aware tokenization (PATK), designed to implement adaptive time-frequency tokenization via distribution-sensitive sampling strategies. Key innovations include: 1) A Rate-of-Variation (RoV) distribution is meticulously structured to encompass multi-scale temporal dynamics in the time domain, alongside a Spectral Energy Intensity (SEI) distribution devised to reveal global seasonal patterns within the frequency domain; 2) A physics-aware hidden Markov modeling (PA-HMM) is then established to adaptively breaks down continuous time-series into distinct tokens with elastic lengths, responding to physics-aware probabilities sampled from RoV and SEI distributions. The proposed PATK allows steady integration with both conventional Transformers and advanced large-scale time series models (including LLM-transferred methods and pretrained time series foundation models). Simulations across various datasets demonstrate that PATK excels in classification and forecasting tasks, showing notable adaptability to model long-term dependencies, strengthening resilience against disturbances, and robustness to missing data events.
Cross-Domain Few-Shot Learning (CD-FSL) remains a significant challenge due to substantial distribution shifts between source and target domains. While prior approaches primarily focus on spatial alignment, they often overlook discrepancies in the frequency domain. In this paper, we reveal frequency band discretization as a key phenomenon, characterized by intra-domain low-frequency dominance, inter-domain amplitude divergence, and limited high-frequency variation. This spectral disharmony biases models toward low-frequency components, leading to spectral collapse. We quantify spectral collapse via the effective rank, a principled measure of spectral diversity. To mitigate spectral collapse, we propose Harmonized Amplitude Perturbation (HAP), a frequency-domain augmentation strategy that perturbs the amplitude spectrum via frequency-aware gains sampled from Harmonized Distributions, while fixing the phase spectrum to maintain semantic integrity. Extensive experiments on both Cross-Domain Few-Shot Image Classification and Object Detection benchmarks demonstrate that HAP effectively increases spectral diversity and consistently improves generalization, outperforming state-of-the-art methods without introducing extra model complexity.
High-Pass Matters: Theoretical Insights and Sheaflet-Based Design for Hypergraph Neural Networks
PDF ↗Hypergraph neural networks (HGNNs) have shown great potential in modeling higher-order relationships among multiple entities. However, most existing HGNNs primarily emphasize low-pass filtering while neglecting the role of high-frequency information. In this work, we present a theoretical investigation into the spectral behavior of HGNNs and prove that combining both low-pass and high-pass components leads to more expressive and effective models. Notably, our analysis highlights that high-pass signals play a crucial role in capturing local discriminative structures within hypergraphs. Guided by these insights, we propose a novel sheaflet-based HNNs that integrates cellular sheaf theory and framelet transforms to preserve higher-order dependencies while enabling multi-scale spectral decomposition. This framework explicitly emphasizes high-pass components, aligning with our theoretical findings. Extensive experiments on benchmark datasets demonstrate the superiority of our approach over existing methods, validating the importance of high-frequency information in hypergraph learning.
M2FMoE: Multi-Resolution Multi-View Frequency Mixture-of-Experts for Extreme-Adaptive Time Series Forecasting
PDF ↗Forecasting time series with extreme events is critical yet challenging due to their high variance, irregular dynamics, and sparse but high-impact nature. While existing methods excel in modeling dominant regular patterns, their performance degrades significantly during extreme events, constituting the primary source of forecasting errors in real-world applications. Although some approaches incorporate auxiliary signals to improve performance, they still fail to capture extreme events' complex temporal dynamics. To address these limitations, we propose M²FMoE, an extreme-adaptive forecasting model that learns both regular and extreme patterns through multi-resolution and multi-view frequency modeling. It comprises three modules: (1) a multi-view frequency mixture-of-experts module assigns experts to distinct spectral bands in Fourier and Wavelet domains, with cross-view shared band splitter aligning frequency partitions and enabling inter-expert collaboration to capture both dominant and rare fluctuations; (2) a multi-resolution adaptive fusion module that hierarchically aggregates frequency features from coarse to fine resolutions, enhancing sensitivity to both short-term variations and sudden changes; (3) a temporal gating integration module that dynamically balances long-term trends and short-term frequency-aware features, improving adaptability to both regular and extreme temporal patterns. Experiments on real-world hydrological datasets with extreme patterns demonstrate that M²FMoE outperforms state-of-the-art baselines without requiring extreme-event labels.
Implicit Neural Representations (INRs) have become a powerful paradigm for modeling continuous signals in computer vision, graphics, and scientific computing. However, multilayer perceptrons (MLPs) generally suffer from severe spectral bias, which limits their ability to accurately model high-frequency details and multi-scale structures. To address this challenge, we propose a novel Multi-Scale Sine Activation (MSA), which explicitly introduces multi-scale frequency responses by incorporating multiple sets of sine activations with logarithmically spaced frequencies in parallel at each layer. MSA is further combined with an amplitude modulation mechanism to ensure numerical stability and robust optimization across different frequency channels. We conduct extensive experiments on a series of challenging tasks, including 1D multi-scale function fitting, image representation, video representation, 3D shape representation, and PDEs solving. Experimental results show that MSA outperforms existing state-of-the-art methods in terms of reconstruction accuracy, detail preservation, and training stability.
T3Time: Tri-Modal Time Series Forecasting via Adaptive Multi-Head Alignment and Residual Fusion
PDF ↗Multivariate time series forecasting (MTSF) seeks to model temporal dynamics among variables to predict future trends. Transformer-based models and large language models (LLMs) have shown promise due to their ability to capture long-range dependencies and patterns. However, current methods often rely on rigid inductive biases, ignore intervariable interactions, or apply static fusion strategies that limit adaptability across forecast horizons. These limitations create bottlenecks in capturing nuanced, horizon-specific relationships in time-series data. To solve this problem, we propose T3Time, a novel trimodal framework consisting of time, spectral, and prompt branches, where the dedicated frequency encoding branch captures the periodic structures along with a gating mechanism that learns prioritization between temporal and spectral features based on the prediction horizon. We also proposed a mechanism which adaptively aggregates multiple cross-modal alignment heads by dynamically weighting the importance of each head based on the features. Extensive experiments on benchmark datasets demonstrate that our model consistently outperforms state-of-the-art baselines, achieving an average reduction of 3.28% in MSE and 2.29% in MAE. Furthermore, it shows strong generalization in few-shot learning settings: with 5% training data, we see a reduction in MSE and MAE by 4.13% and 1.91%, respectively; and with 10% data, by 3.62% and 1.98% on average. Code will be released upon publication.
SchellingFormer: Laplacian Matrix-guided Geometric Transformer for Robust Schelling Point Detection
PDF ↗Detecting Schelling Points—salient 3D mesh landmarks that serve as natural reference points for shape analysis—is a challenging problem in geometry processing. While existing CNN-based methods struggle with limited receptive fields and poor geometric context modeling, this paper proposes {\em SchellingFormer}, a novel Laplacian matrix-guided Geometric Transformer that effectively captures long-range dependencies and discriminative geometric features for robust Schelling point prediction. Our framework consists of two key components: (i) a hybrid geometric feature embedding module that integrates handcrafted descriptors (coordinates, Gaussian curvature, and curvature differences) to encode local geometry, and (ii) a Laplacian-driven vector attention mechanism, where spatial relationships encoded by the Laplacian matrix guide feature aggregation with the Transformer. This approach enables adaptive, geometry-aware message passing and contextual representation learning. Extensive experiments demonstrate that SchellingFormer outperforms state-of-the-art methods across multiple evaluation metrics. Our work bridges the gap between spectral mesh analysis and Transformer-based learning, offering a powerful tool for 3D shape understanding tasks such as shape matching and saliency detection.