Multispectral and hyperspectral imagery are widely used in agriculture, environmental monitoring, and urban planning due to their complementary spatial and spectral characteristics. A fundamental trade-off persists: multispectral imagery offers high spatial but limited spectral resolution, while hyperspectral imagery provides rich spectra at lower spatial resolution. Prior hyperspectral generation approaches (e.g., pan-sharpening variants, matrix factorization, CNNs) often struggle to jointly preserve spatial detail and spectral fidelity. In response, we propose SpecSwin3D, a transformer-based model that generates hyperspectral imagery from multispectral inputs while preserving both spatial and spectral quality. Specifically, SpecSwin3D takes five multispectral bands as input and reconstructs 224 hyperspectral bands at the same spatial resolution. In addition, we observe that reconstruction errors grow for hyperspectral bands spectrally distant from the input bands. To address this, we introduce a cascade training strategy that progressively expands the spectral range to stabilize learning and improve fidelity. Moreover, we design an optimized band sequence that strategically repeats and orders the five selected multispectral bands to better capture pairwise relations within a 3D shifted-window transformer framework. Quantitatively, our model achieves a PSNR of 35.82 dB, SAM of 2.40°, and SSIM of 0.96, outperforming the baseline MHF-Net by +5.6 dB in PSNR and reducing ERGAS by more than half. Beyond reconstruction, we further demonstrate the practical value of SpecSwin3D on two downstream tasks, including land use classification and burnt area segmentation.

Recent advancements in deep learning models for time series forecasting have been significant. These models often leverage fundamental time series properties such as seasonality and non-stationarity, which may suggest an intrinsic link between model performance and data properties. However, existing benchmark datasets fail to offer diverse and well-defined temporal patterns, restricting the systematic evaluation of such connections. Additionally, there is no effective model recommendation approach, leading to high time and cost expenditures when testing different architectures across different downstream applications. For those reasons, we propose ARIES, a framework for assessing relation between time series properties and modeling strategies, and for recommending deep forcasting models for realistic time series. First, we construct a synthetic dataset with multiple distinct patterns, and design a comprehensive system to compute the properties of time series. Next, we conduct an extensive benchmarking of over 50 forecasting models, and establish the relationship between time series properties and modeling strategies. Our experimental results reveal a clear correlation. Based on these findings, we propose the first deep forecasting model recommender, capable of providing interpretable suggestions for real-world time series. In summary, ARIES is the first study to establish the relations between the properties of time series data and modeling strategies, while also implementing a model recommendation system. The code is available at: https://github.com/blisky-li/ARIES.

The reliable identification of magnetic ground states remains a major challenge in high-throughput materials databases, where density functional theory (DFT) workflows often converge to ferromagnetic (FM) solutions. Here, we partially address this challenge by developing machine learning classifiers trained on experimentally validated MAGNDATA magnetic materials leveraging a limited number of simple compositional, structural, and electronic descriptors sourced from the Materials Project database. Our propagation vector classifiers achieve accuracies above 92%, outperforming recent studies in reliably distinguishing zero from nonzero propagation vector structures, and exposing a systematic ferromagnetic bias inherent to the Materials Project database for more than 7,843 materials. In parallel, LightGBM and XGBoost models trained directly on the Materials Project labels achieve accuracies of 84-86% (with macro F1 average scores of 63-66%), which proves useful for large-scale screening for magnetic classes, if refined by MAGNDATA-trained classifiers. These results underscore the role of machine learning techniques as corrective and exploratory tools, enabling more trustworthy databases and accelerating progress toward the identification of materials with various properties.

While queueing network models are powerful tools for analyzing service systems, they traditionally require substantial human effort and domain expertise to construct. To make this modeling approach more scalable and accessible, we propose a data-driven framework for queueing network modeling and simulation based on autoregressive sequence models trained on event-stream data. Instead of explicitly specifying arrival processes, service mechanisms, or routing logic, our approach learns the conditional distributions of event types and event times, recasting the modeling task as a problem of sequence distribution learning. We show that Transformer-style architectures can effectively parameterize these distributions, enabling automated construction of high-fidelity simulators. As a proof of concept, we validate our framework on event tables generated from diverse queueing networks, showcasing its utility in simulation, uncertainty quantification, and counterfactual evaluation. Leveraging advances in artificial intelligence and the growing availability of data, our framework takes a step toward more automated, data-driven modeling pipelines to support broader adoption of queueing network models across service domains.

Aerial remote sensing using multispectral and RGB imagers has provided a critical impetus to precision agriculture. Analysis of the hyperspectral images with limited or no labels is challenging. This paper focuses on self-supervised learning to create neural network embeddings reflecting vegetation properties of trees from aerial hyperspectral images of crop fields. Experimental results demonstrate that a constructed tree representation, using a vegetation property-related embedding space, performs better in downstream machine learning tasks compared to the direct use of hyperspectral vegetation properties as tree representations.

Medical multimodal representation learning aims to integrate heterogeneous clinical data into unified patient representations to support predictive modeling, which remains an essential yet challenging task in the medical data mining community. However, real-world medical datasets often suffer from missing modalities due to cost, protocol, or patient-specific constraints. Existing methods primarily address this issue by learning from the available observations in either the raw data space or feature space, but typically neglect the underlying bias introduced by the data acquisition process itself. In this work, we identify two types of biases that hinder model generalization: missingness bias, which results from non-random patterns in modality availability, and distribution bias, which arises from latent confounders that influence both observed features and outcomes. To address these challenges, we perform a structural causal analysis of the data-generating process and propose a unified framework that is compatible with existing direct prediction-based multimodal learning methods. Our method consists of two key components: (1) a missingness deconfounding module that approximates causal intervention based on backdoor adjustment and (2) a dual-branch neural network that explicitly disentangles causal features from spurious correlations. We evaluated our method in real-world public and in-hospital datasets, demonstrating its effectiveness and causal insights.

The You Only Look Once (YOLO) architecture is crucial for real-time object detection. However, deploying it in resource-constrained environments such as unmanned aerial vehicles (UAVs) requires efficient transfer learning. Although layer freezing is a common technique, the specific impact of various freezing configurations on contemporary YOLOv8 and YOLOv10 architectures remains unexplored, particularly with regard to the interplay between freezing depth, dataset characteristics, and training dynamics. This research addresses this gap by presenting a detailed analysis of layer-freezing strategies. We systematically investigate multiple freezing configurations across YOLOv8 and YOLOv10 variants using four challenging datasets that represent critical infrastructure monitoring. Our methodology integrates a gradient behavior analysis (L2 norm) and visual explanations (Grad-CAM) to provide deeper insights into training dynamics under different freezing strategies. Our results reveal that there is no universal optimal freezing strategy but, rather, one that depends on the properties of the data. For example, freezing the backbone is effective for preserving general-purpose features, while a shallower freeze is better suited to handling extreme class imbalance. These configurations reduce graphics processing unit (GPU) memory consumption by up to 28% compared to full fine-tuning and, in some cases, achieve mean average precision (mAP@50) scores that surpass those of full fine-tuning. Gradient analysis corroborates these findings, showing distinct convergence patterns for moderately frozen models. Ultimately, this work provides empirical findings and practical guidelines for selecting freezing strategies. It offers a practical, evidence-based approach to balanced transfer learning for object detection in scenarios with limited resources.

Multivariate time series (MTS) are ubiquitous in domains such as healthcare, climate science, and industrial monitoring, but their high dimensionality, limited labeled data, and non-stationary nature pose significant challenges for conventional machine learning methods. While recent self-supervised learning (SSL) approaches mitigate label scarcity by data augmentations or time point-based contrastive strategy, they neglect the intrinsic periodic structure of MTS and fail to capture the dynamic evolution of latent states. We propose PLanTS, a periodicity-aware self-supervised learning framework that explicitly models irregular latent states and their transitions. We first designed a period-aware multi-granularity patching mechanism and a generalized contrastive loss to preserve both instance-level and state-level similarities across multiple temporal resolutions. To further capture temporal dynamics, we design a next-transition prediction pretext task that encourages representations to encode predictive information about future state evolution. We evaluate PLanTS across a wide range of downstream tasks-including multi-class and multi-label classification, forecasting, trajectory tracking and anomaly detection. PLanTS consistently improves the representation quality over existing SSL methods and demonstrates superior runtime efficiency compared to DTW-based methods.

We show that translation quality can be predicted with surprising accuracy \textit{without ever running the translation system itself}. Using only a handful of features, token fertility ratios, token counts, and basic linguistic metadata (language family, script, and region), we can forecast ChrF scores for GPT-4o translations across 203 languages in the FLORES-200 benchmark. Gradient boosting models achieve favorable performance ($R^{2}=0.66$ for XX$\rightarrow$English and $R^{2}=0.72$ for English$\rightarrow$XX). Feature importance analyses reveal that typological factors dominate predictions into English, while fertility plays a larger role for translations into diverse target languages. These findings suggest that translation quality is shaped by both token-level fertility and broader linguistic typology, offering new insights for multilingual evaluation and quality estimation.

Large language models (LLMs) are unable to continuously adapt and learn from new data during reasoning at inference time. To address this limitation, we propose that complex reasoning tasks be decomposed into atomic subtasks and introduce SAGE, a trigger-guided dynamic fine-tuning framework that enables adaptive updates during reasoning at inference time. SAGE consists of three key components: (1) a Trigger module that detects reasoning failures through multiple evaluation metrics in real time; (2) a Trigger Buffer module that clusters anomaly samples using a streaming clustering process with HDBSCAN, followed by stability checks and similarity-based merging; and (3) a Lora Store module that dynamically optimizes parameter updates with an adapter pool for knowledge retention. Evaluation results show that SAGE demonstrates excellent accuracy, robustness, and stability on the atomic reasoning subtask through dynamic knowledge updating during test time.