Transformers have revolutionized natural language processing, but their quadratic complexity with respect to sequence length remains a fundamental bottleneck for long-range modeling. While sparse attention mechanisms like RingAttention reduce computational costs by restricting attention to local neighborhoods, they suffer from limited receptive fields and lack of adaptability. We present \PiAttention, a periodic sparse Transformer that factorizes attention into ring-local neighborhoods, deterministic $π$-stride skips, and an adaptive fusion gate. The periodic structure provides predictable coverage of distant tokens, while the sparse footprint keeps the per-layer complexity linear in context length. We prove that \PiAttention achieves $\mathcal{O}(kL + π\log L)$ receptive field growth compared to $\mathcal{O}(kL)$ for RingAttention, where $k$ is the local window size, $π$ is the skip period, and $L$ is the sequence length. Extensive experiments on language modeling, retrieval, and vision-language tasks demonstrate that \PiAttention matches or surpasses dense attention quality with 8.3\% lower perplexity than RingAttention while using 50\% fewer GPUs for the same context length. Our detailed ablations and visualizations reveal the importance of periodic skips, adaptive fusion, and head-level sparsity coordination for efficient long-context modeling.

Haixu Ma Department of Statistics and Operations Research University of North Carolina at Chapel Hill Chapel Hill, NC 27516 haixuma@live.unc.edu A.1 Estimation of the main effect We briefly discuss how to obtain the estimation of the main effect function M For nonparametric regression, we follow [ 3 ] to divide the training data into M folds based on the assigned treatment. Then p E r Y |Z,A " a s is obtained from the regression forest [ 4 ] on Y Z with the dataset tp y We refer to [ 3 ] for more discussions about the case of misspecifying the main effect, and the corresponding robust and efficient method to solve the misspecification problem. A.2 Implementation details for the adaptive proximal gradient algorithm Recall that U " diag pX The main steps of the proposed algorithm for SCAF are summarized as below. In particular, the experiments were run on a Linux-based computing server.

While LLMs have demonstrated remarkable potential in time series forecasting, their practical deployment remains constrained by excessive computational demands and memory footprints. Existing LLM-based approaches typically suffer from three critical limitations: Inefficient parameter utilization in handling numerical time series patterns; Modality misalignment between continuous temporal signals and discrete text embeddings; and Inflexibility for real-time expert knowledge integration. We present SMETimes, the first systematic investigation of sub-3B parameter SLMs for efficient and accurate time series forecasting. Our approach centers on three key innovations: A statistically-enhanced prompting mechanism that bridges numerical time series with textual semantics through descriptive statistical features; A adaptive fusion embedding architecture that aligns temporal patterns with language model token spaces through learnable parameters; And a dynamic mixture-of-experts framework enabled by SLMs' computational efficiency, adaptively combining base predictions with domain-specific models. Extensive evaluations across seven benchmark datasets demonstrate that our 3B-parameter SLM achieves state-of-the-art performance on five primary datasets while maintaining 3.8x faster training and 5.2x lower memory consumption compared to 7B-parameter LLM baselines. Notably, the proposed model exhibits better learning capabilities, achieving 12.3% lower MSE than conventional LLM. Ablation studies validate that our statistical prompting and cross-modal fusion modules respectively contribute 15.7% and 18.2% error reduction in long-horizon forecasting tasks. By redefining the efficiency-accuracy trade-off landscape, this work establishes SLMs as viable alternatives to resource-intensive LLMs for practical time series forecasting. Code and models are available at https://github.com/xiyan1234567/SMETimes.

An important paradigm in 3D object detection is the use of multiple modalities to enhance accuracy in both normal and challenging conditions, particularly for long-tail scenarios. To address this, recent studies have explored two directions of adaptive approaches: MoE-based adaptive fusion, which struggles with uncertainties arising from distinct object configurations, and late fusion for output-level adaptive fusion, which relies on separate detection pipelines and limits comprehensive understanding. In this work, we introduce Cocoon, an object- and feature-level uncertainty-aware fusion framework. The key innovation lies in uncertainty quantification for heterogeneous representations, enabling fair comparison across modalities through the introduction of a feature aligner and a learnable surrogate ground truth, termed feature impression. We also define a training objective to ensure that their relationship provides a valid metric for uncertainty quantification. Cocoon consistently outperforms existing static and adaptive methods in both normal and challenging conditions, including those with natural and artificial corruptions. Furthermore, we show the validity and efficacy of our uncertainty metric across diverse datasets.

Accurate crop yield prediction is of utmost importance for informed decision-making in agriculture, aiding farmers, and industry stakeholders. However, this task is complex and depends on multiple factors, such as environmental conditions, soil properties, and management practices. Combining heterogeneous data views poses a fusion challenge, like identifying the view-specific contribution to the predictive task. We present a novel multi-view learning approach to predict crop yield for different crops (soybean, wheat, rapeseed) and regions (Argentina, Uruguay, and Germany). Our multi-view input data includes multi-spectral optical images from Sentinel-2 satellites and weather data as dynamic features during the crop growing season, complemented by static features like soil properties and topographic information. To effectively fuse the data, we introduce a Multi-view Gated Fusion (MVGF) model, comprising dedicated view-encoders and a Gated Unit (GU) module. The view-encoders handle the heterogeneity of data sources with varying temporal resolutions by learning a view-specific representation. These representations are adaptively fused via a weighted sum. The fusion weights are computed for each sample by the GU using a concatenation of the view-representations. The MVGF model is trained at sub-field level with 10 m resolution pixels. Our evaluations show that the MVGF outperforms conventional models on the same task, achieving the best results by incorporating all the data sources, unlike the usual fusion results in the literature. For Argentina, the MVGF model achieves an R2 value of 0.68 at sub-field yield prediction, while at field level evaluation (comparing field averages), it reaches around 0.80 across different countries. The GU module learned different weights based on the country and crop-type, aligning with the variable significance of each data source to the prediction task.

The imbalance problem is widespread in real-world applications. When training a classifier on the imbalance datasets, the classifier is hard to learn an appropriate decision boundary, which causes unsatisfying classification performance. To deal with the imbalance problem, various ensemble algorithms are proposed. However, conventional ensemble algorithms do not consider exploring an effective feature subspace to further improve the performance. In addition, they treat the base classifiers equally, and ignore the different contribution of each base classifier to the ensemble result. In order to address these problems, we propose a novel ensemble algorithm that combines effective data transform and adaptive fusion scheme. First, we utilize modified metric learning to obtain an effective feature space based on imbalanced data. Next, the base classifiers are assigned different weights adaptively. The experiments on multiple imbalanced datasets, including images and biomedical dataset, verify the superiority of our proposed ensemble algorithm.

A simple yet effective architectural design of radial basis function neural networks (RBFNN) makes them amongst the most popular conventional neural networks. The current generation of radial basis function neural network is equipped with multiple kernels which provide significant performance benefits compared to the previous generation using only a single kernel. In existing multi-kernel RBF algorithms, multi-kernel is formed by the convex combination of the base/primary kernels. In this paper, we propose a novel multi-kernel RBFNN in which every base kernel has its own (local) weight. This novel flexibility in the network provides better performance such as faster convergence rate, better local minima and resilience against stucking in poor local minima. These performance gains are achieved at a competitive computational complexity compared to the contemporary multi-kernel RBF algorithms. The proposed algorithm is thoroughly analysed for performance gain using mathematical and graphical illustrations and also evaluated on three different types of problems namely: (i) pattern classification, (ii) system identification and (iii) function approximation. Empirical results clearly show the superiority of the proposed algorithm compared to the existing state-of-the-art multi-kernel approaches.