Data-Efficient Learning

Classical compute-optimal scaling laws assume an unbounded supply of fresh pretraining data, yet pretraining is increasingly entering a regime in which compute grows faster than the availability of high-quality data. We propose Compute-Data (CD) scaling laws, a unified framework that bridges compute-optimal scaling, where data scales freely with compute, and data-optimal scaling, where the corpus is fixed while compute can grow without bound. CD scaling extends classical scaling laws by introducing a token-effectiveness function, $η$, which quantifies the value of a derived token-produced, for example, through multi-epoch repetition or paraphrasing-relative to a fresh token, ranging from a perfect substitute to having no value. We fit $η$ for two data-expansion strategies, multi-epoch repetition and paraphrasing, across model sizes from 14M to 600M parameters using the Dolma-3 corpus. We find that token effectiveness is far from constant: it depends jointly on model size, the tokens-per-parameter ratio, and the amount of derived data, and it saturates as the corpus is expanded. The functional form of $η$ implies diminishing returns when substituting compute for data as either model size or data availability increases. It also partitions training into three operational regimes---compute-bound, data-bound, and model-bound---and shows that classical compute-optimal allocation is suboptimal across most practically relevant settings.

Data scarcity poses a fundamental challenge in training generative models to produce initial guesses for parametric optimization problems that are otherwise numerically expensive to solve. We therefore study a $k$-neighborhood data collection strategy that augments datasets of converged solutions with intermediate solver iterates, increasing the amount of training data without additional solver runs. To understand the benefits of this approach, we derive a generalization bound based on Rademacher complexity that reveals the role of the $k$-neighborhoods and related parameters. To achieve this result, we focus on one-sided box-constrained quadratic programs solved by projected gradient descent. We illustrate the behavior of this solver on two examples. The approach proposed in this paper enables a more capable DDDAS paradigm by improving the efficiency of the data-model-optimization loop. We finish by discussing two views of learning solver-iterate data and connect our analysis with GLENS, a new data-efficient global search method.

Recent visual place recognition (VPR) studies have increasingly relied on large-scale datasets to train more robust and discriminative models. Although this trend significantly improves recognition performance, it also introduces substantial storage and training costs, especially when new architectures or training strategies need to be repeatedly developed and evaluated. Dataset pruning (DP) provides a promising way to improve data efficiency by retaining only informative training data. However, conventional DP methods mainly follow the sample-wise classification paradigm, which overlooks the relation-dependent training nature of VPR, where supervision is typically formed by image pairs rather than independent images. To address this issue, we propose a place-wise dataset pruning framework tailored for VPR. Instead of pruning individual images, our method treats each place as the basic pruning unit and introduces two complementary novel metrics, i.e., intra-place diversity (IPD) and inter-place similarity (IPS), to evaluate the training value of each place. By jointly considering these two metrics, our method ranks all places and constructs a compact yet informative coreset, thereby allowing the pruned dataset to still support the training of robust and discriminative VPR models. Extensive experiments demonstrate that our method consistently outperforms state-of-the-art DP baselines under different pruning ratios while reducing selection and training costs. Moreover, by pruning a merged dataset roughly 3.5$\times$ the size of GSV-Cities to a comparable scale, our coreset maintains highly competitive performance, achieving 94.5% R@1 on MSLS-val and 97.0% R@1 on Nordland with only NetVLAD. Codes will be made publicly available.

Machine-learning force fields (MLFFs) are reliable only near their training distribution, making efficient construction of diverse training sets a major bottleneck for both train-from-scratch and foundation fine-tuning workflows. Active learning can reduce this cost, but standard model-committee uncertainty is impractical for foundation MLFFs because each committee member requires a separate fine-tuning run. We present an active-learning workflow based on last-layer-projection regression (LLPR), a forward-pass-cheap per-configuration uncertainty estimator. Across molecular, condensed-phase, and electrolyte systems, LLPR identifies compact, high-value training sets that recover full-data accuracy using only a small fraction of electronic-structure labels. In foundation-model fine-tuning, LLPR-selected configurations reach the full-pool fine-tuning ceiling with substantially fewer labels than random selection. In iterative electrolyte fine-tuning, LLPR detects unphysical local coordination before DFT labelling, provides an absolute force-error threshold, and enables automatic termination of the learning loop. The resulting models reproduce reference density and ion-coordination structure, providing a scalable uncertainty-quantification strategy across MLFF training regimes.

Learning effectively from limited data is critical in domains like security where labeled examples are scarce. Large language models (LLMs) have demonstrated some capabilities for data-efficient learning, especially through parameter-efficient adaptation methods, but continue to struggle when faced with few samples for difficult tasks. To meet this challenge, we propose Attention Head Reweighting (AHR), a data-efficient method that adapts LLMs to new text-classification tasks by learning only a single scalar per attention head. This drastically reduces the number of parameters that need to be learned by making use of the functional specialization of individual attention heads. Experiments on diverse open-source text classification datasets show that AHR can outperform standard baselines like LoRA when learning from limited samples, despite having 200-1000x fewer trainable parameters, as our AHR only modifies ~0.0001% of the model's parameters. In addition, our learned weights are easy to interpret and can be analyzed to better understand the mechanisms and attention heads responsible for in-context learning abilities in LLMs.

Deep learning models dependency on large-scale inertial datasets presents a significant bottleneck in inertial sensor-based classification tasks, such as human activity recognition and smartphone location recognition. In these domains, data collection requires massive recording campaigns that are complex, time-consuming, and difficult to scale. Currently, data-driven guidelines for determining the minimum sample size required to reach a desired accuracy level do not exist. To address this gap, this study presents a systematic empirical evaluation of learning curve convergence rates in inertial classification. We introduce a unified framework that analyzes classification performance under both binary and multi-class scenarios, and derive an empirical formula to estimate performance relative to dataset size. Testing across six diverse, real-world datasets totaling 102.7 hours of inertial measurements demonstrates that accuracy follows a consistent logarithmic growth pattern, regardless of task complexity. Leveraging this finding, we propose a quantitative stability point metric, defined as the sample size required for the learning curve to stabilize within a predefined mean absolute percentage deviation of its asymptotic maximum. Our analysis reveals that models often reach practical stability with substantially fewer samples than traditional heuristics suggest. Ultimately, we offer a generalizable framework to extrapolate total data requirements from small-scale pilot studies, optimizing the tradeoff between recording effort and model reliability. These findings shift the prevailing paradigm from maximizing data volume toward optimizing data efficiency, offering concrete, data-backed guidelines for planning recording campaigns in inertial sensing applications.

The rapid expansion of large-scale AI models has led to significant performance breakthroughs across diverse domains, yet it has also raised critical concerns regarding computational costs, energy consumption, and environmental sustainability. This survey provides a comprehensive overview of the green development of large models, emphasizing resource-efficient architectures and full-stack hardware-software co-design. We systematically review recent advances in efficient model construction, including attention operator optimization, linear-complexity architectures, and model sparsification and merging, as well as training and deployment strategies such as data-efficient learning, parameter-efficient fine-tuning, and computational compression. Beyond algorithmic improvements, we explore energy-efficient AI hardware, including mainstream AI chips, memory optimization, cross-platform deployment, and sustainable infrastructure. Furthermore, we examine how large models are being applied to sustainability-critical domains such as DeepSeek, remote sensing interpretation, national-scale infrastructure, and global initiatives. Finally, we discuss key challenges and future directions, highlighting the need for continual learning paradigms, memory-centric hardware, and standardized evaluation protocols. This survey aims to offer a holistic roadmap toward sustainable, scalable, and socially responsible development of large models. Paper homepage: https://cje.ejournal.org.cn/article/doi/10.23919/cje.2025.00.438

In physically dominated machining processes, experimental datasets are small, expensive, and material-specific; in this regime, data curation, evaluation design, and the form of physics integration can matter as much as the learning algorithm. Using an abrasive waterjet milling dataset ($n{=}155$, Inconel,718), we make three methodological contributions. First, we separate physics-based data \emph{cleaning} from statistical \emph{curation} and treat the latter as competing modelling hypotheses rather than silent preprocessing. Second, we find that model rankings from a 15-point hold-out set can be unstable: the single-split winner drops from rank1 to rank7 under 10-fold cross-validation, while Gaussian Process (GP) variants occupy the top ranks. Third, we study a spectrum of physics integration levels and find that residual learning on a compact physics baseline is competitive for GP, yielding lower variance and an interpretable decomposition, but degrades tree-based models. Bayesian hyper parameter tuning improves parameter-sensitive baselines such as gradient boosting and SVR, yet harms multi-stage hybrid pipelines at this sample size. GP uncertainty intervals are approximately calibrated ($86\%$ empirical coverage at nominal $90\%$). The resulting picture is methodological: for small, expensive process datasets, our results suggest that, in this setting, reliable model comparison benefits from explicit curation hypotheses, robust evaluation, and careful choices about how physics enters the model.

Vision-Language-Action (VLA) models are typically trained by imitation learning on large-scale robot demonstration datasets, but more data does not necessarily yield better policies due to redundancy, noise, and uneven coverage. Existing data selection methods often assess demonstrations at either the trajectory or state-action level, missing the reusable structures that compose long-horizon behaviors. In this paper, we propose SIEVE, a structure-aware data selection method for VLA imitation learning. SIEVE views demonstrations as compositions of reusable primitives and transition interfaces. It first discovers visuo-motor primitives from segmented trajectories, then allocates selection budgets to composition patterns by maximizing reuse-aware structural exposure under diminishing returns. Finally, it selects medoid trajectories within each composition-pattern bucket to retain central, stable, and imitation-friendly demonstrations. Experiments across multiple datasets, benchmarks, and VLA models show that SIEVE consistently outperforms competitive data selection baselines. Notably, SIEVE can surpass full-data training while using only 50% of demonstrations and 50% of training steps, suggesting that reusable structure, captured through primitives and transitions, is an important signal for efficient VLA imitation learning.

Automatic sleep staging is a key technology for precise diagnosis and treatment of sleep disorders as well as long-term home sleep monitoring. Portable electroencephalogram (EEG) devices have become the focus of research due to their convenience in data collection. However, current methods still face three major challenges: large parameter sizes that easily lead to overfitting on small datasets, low accuracy in classifying difficult stages such as N1 and REM, unclear optimal training dataset size, and difficulty in deployment. This paper proposes GamSleepNet, a lightweight and low-latency automatic sleep staging framework for single-channel EEG. The framework features the FEB module, which combines improved Gabor kernels with learnable filters for feature extraction, uses the Mamba architecture to build a temporal classification network, introduces a novel contrastive loss and a two-stage training strategy, and experimentally validates the optimal dataset size for single-channel EEG sleep staging models. On the Sleepedf dataset, this model achieves an overall accuracy of 87.86 percent with only 30.86 thousand parameters, with all metrics reaching SOTA levels and significantly improving the identification accuracy of challenging sleep stages.

Modern machine learning systems demand extensive datasets for visual recognition. Conversely, humans learn with high efficiency despite severe data limitations, often by acquiring broad categorical structures before refining finer distinctions. Inspired by this contrast, we introduce SCALA (Scaffolded Cognitive Architecture for Learning under limited dAta), a hierarchical learning framework grounded in cognitive psychology that guides models from coarse conceptual structures to fine-grained recognition. Our model exhibits human-like cognitive selectivity by effectively prioritizing task-relevant features while suppressing background distractors, a mechanism that induces a fundamental shift in representation learning. This shift is characterized by accelerated cluster formation, reduced intra-class dispersion, and enhanced semantic separability. Empirically, SCALA achieves significant accuracy improvements under severe data scarcity. Furthermore, this hierarchical scaffolding promotes robust generalization to unseen classes and accelerates the acquisition of novel categories. Collectively, our results establish SCALA as a powerful framework for achieving human-level sample efficiency and resilient category generalization in data-constrained environments.

Inverse design of mechanical metamaterials seeks a periodic unit cell whose homogenized elastic properties meet a prescribed target, but current learning-based methods are data-hungry, mostly interpolative, and provide no guarantee that the generated design satisfies the specification. We introduce CertMix, a data-efficient framework that represents each exemplar unit cell as a small periodic neural implicit field, specifically a SIREN signed-distance decoder overfit from a shared anchor, so that exemplar weight vectors become aligned and directly comparable. The key observation is that, in this aligned weight space, the homogenized elasticity tensor is approximately linear in the mixing coefficients. Targeted design therefore reduces to a small constrained affine-mixing problem solved with a differentiable periodic homogenizer in the loop. Negative coefficients enable extrapolation beyond the exemplar range, a linearity-mismatch trust region keeps blends valid, and split-conformal calibration converts the mismatch signal into a distribution-free certificate on achieved-property error. From as few as 50 exemplars, CertMix attains a scaled property error of $10^{-4}$, roughly two to three orders of magnitude below conditional generative baselines trained on 1000 cells. It remains accurate far outside the exemplar range, is $57\times$ faster than per-target topology optimization while avoiding checkerboards and enclosed voids, and extends to spatially graded fields, 3D triply periodic surfaces, and a certified running-shoe midsole application.

Learning from few labeled examples is a central challenge in tabular machine learning, and it becomes the binding constraint in domains where labeling is costly, such as crowd monitoring during Hajj and Umrah. Tabular foundation models, which predict from only a handful of examples without task-specific training, were recently introduced to address this very-few-label regime. In this study we test them on crowd-state classification to assess how much they help when labels are scarce, and we compare them against standard machine learning methods to characterize the accuracy and efficiency trade-offs between the two approaches. Using three real datasets we evaluate different machine learning models, in untuned and tuned forms, against three foundation models. Results show that no single family is best everywhere. The right choice depends on the label budget. When labels are very few, foundation models lead. As labels grow, tuned conventional models catch up and significantly surpass the foundation models on the more structural geometry target. Efficiency separates them further where tuned machine learning models incur a large tuning cost that foundation models avoid, although foundation models reprocess their context at every prediction. We summarize these results as a practical map of which approach to prefer under a given label budget and computational budget.

Active learning reduces labeling cost by querying the most informative unlabeled samples, but standard coreset methods ignore known data symmetries and can waste budget on transformed versions of the same instance. We propose GRINCO, a group-invariant coreset framework that performs acquisition in the quotient space induced by a transformation group, so that selection operates on orbits rather than raw samples. The method uses either canonical representatives or learned orbit-separating invariant embeddings to define practical quotient metrics, and combines quotient-space k-center selection with invariant training through an orbit-averaged loss. We further derive a generalization bound that relates excess orbit-averaged risk to quotient-space coverage, label uncertainty, and intra-orbit variability. Experiments on synthetic scale-invariant data and image benchmarks with rotation-induced redundancy show that GRINCO improves orbit coverage and achieves stronger label efficiency than conventional coreset baselines, especially when group-induced redundancy is substantial.

Recent advancements in scaling dataset distillation rely heavily on decoupled information extraction pipelines, comprising SQUEEZE, RECOVER, and RELABEL stages. Despite their scalability to large-scale datasets, these methods suffer from prohibitive computational overhead and poor cross-architecture generalization. In this paper, we reveal the root cause of these bottlenecks: the implicit dual-compression process, from data to model and back to images, inherently induces severe information loss. Crucially, we empirically and theoretically demonstrate that this loss creates a distribution shift that fundamentally compromises the widely adopted RELABEL strategy, transforming the pre-trained model into an unreliable labeler that yields sub-optimal labels. To overcome these critical flaws, we propose CIM, a novel, metric-driven framework that abandons the flawed dual-compression paradigm. Instead, CIM explicitly quantifies and minimizes the information gap between the original and synthetic datasets. By directly aligning the data distributions, our approach ensures high-fidelity information condensation and inherently satisfies the prerequisites for effective relabeling. Extensive experiments demonstrate that CIM establishes a new state-of-the-art. Notably, it distills ImageNet-1K at an IPC=10 in merely 80 minutes on a single RTX-4090 GPU, achieving an unprecedented 48.7% Top-1 accuracy on ResNet-18 and significantly outperforming previous SOTA approaches, such as NRR-DD and DELT, by 2.6% and 2.9%, respectively. Our code is available at https://github.com/LINs-lab/CIM.

Unsupervised Reinforcement Learning (URL) aims to pre-train scalable, skill-conditioned policies without extrinsic rewards, serving as a foundation for downstream control tasks. Despite recent progress, we argue that current off-policy URL methods are limited by two critical, overlooked bottlenecks: (1) non-stationary skill semantics and (2) brittle generalization. To address these challenges, we propose GenDa (Generalizable Data-efficient Agent), a unified framework for robust unsupervised reinforcement learning. First, we introduce a skill relabeling mechanism to mitigate non-stationarity and significantly improve data efficiency for pre-training. Second, we propose a Complementary Information Bottleneck (CIB), encouraging the learned skill policy to focus on ego-centric features and become robust to distribution shifts for downstream tasks. Through various experiments, we demonstrate that GenDa significantly enhances the scalability of URL with superior generalizability and data efficiency. Our code and videos are available at https://ihatebroccoli.github.io/official-GenDa.

High-fidelity molecular docking simulations can produce biologically relevant estimates of epitope-receptor binding affinity but are computationally expensive and therefore limit the number of candidates that can be screened for vaccine design. In this work, we evaluate machine learning (ML) approaches where variants of active learning are used to classify instances of high binding affinity between 9-mer epitopes and a well-conserved swine leukocyte antigen (SLA) receptor in the context of Porcine Reproductive and Respiratory Syndrome (PRRS). We use an internally generated dataset of 80 epitope-SLA docking affinities, each requiring more than 48 hours of high-performance computing (HPC). Multiple model families (linear, MLP, CNN, and a small transformer) are trained under strict low-data conditions within a pool-based active learning loop. In each case, optimal model configurations are identified by conducting large-scale hyperparameter optimization over the combined space of model architecture, training configuration, acquisition policy, and ensemble decision rules. To mitigate the effects of data subsample selection, each candidate configuration is evaluated by averaging performance over many randomized and balanced training and validation data subsets. Across experiments, transformer-based sequence models consistently emerged as the best-performing architecture, with active incremental learning yielding significant improvement over a baseline random sample acquisition strategy. Under moderate training data availability (N=30), the optimized ML-model configuration outperforms a standard baseline trained on twice the amount of data. Under higher training data availability (N=60), the same configuration achieves a peak accuracy of 86.8%, consistent with an upper bound of 85% classification accuracy based on two independent estimates of conformational noise.

Deep learning models for surface electromyography (sEMG) can benefit substantially from subject-specific (re-)calibration, since no sufficiently large and diverse datasets are available to train fully generic decoders. However, for user acceptance, the number of repetitions that can realistically be collected during calibration is severely limited, which increases the risk of overfitting and, in extreme cases, can even degrade performance compared to the uncalibrated model. Classical overfitting indicators such as validation performance and regularization with early stopping are difficult to apply in this low-sample regime, as they require additional held-out data that is rarely available in practical calibration scenarios. In this work, we investigate a recently proposed class of memorization indicators based solely on the activation statistics of rectified linear units (ReLU) in deep neural networks, which can be computed directly from training data without any extra validation set. We conduct a transferlearning experiment on a benchmark sEMG dataset, where a convolutional neural network is first pre-trained on multiple subjects and subsequently fine-tuned on individual users using only a small number of repetitions. During calibration, we monitor both decoding performance and the activation behaviour of the last hidden layer. Our results provide first evidence that decreases in test accuracy during fine-tuning are ac companied by characteristic changes in activation rates, indicating that activation-based memorization indicators are a promising tool for early spotting of unsuccessful learning in low-sample sEMG calibration settings.

Compositional generalization, the ability to solve complex problems by combining solutions to simpler sub-problems, is a fundamental capability of both natural and artificial intelligence, and a key mechanism underlying chain-of-thought reasoning. However, the theoretical underpinnings of compositional generalization remain poorly understood: when and why does decomposing a problem into parts yield more efficient learning than solving it directly? We study this question through the canonical problem of learning to simulate semiautomata (predicting the outcome of $T$ steps of sequential computation), a model that captures state tracking, regular language recognition, and modular arithmetic. We show that an autocurriculum-based approach building on Part I of this series, recursively decomposing longer sequences into shorter sub-problems, learning to solve them, and composing the solutions, achieves dramatically better statistical complexity than direct methods. (i) For a setting inspired by supervised fine-tuning (SFT) where the learner receives interactive feedback on intermediate states of the computation, curriculum facilitates learning from only $2^{\mathcal{O}(\sqrt{\log T})}$ tokens of supervision; i.e., subpolynomial in the sequence length $T$, overcoming the $Ω(T)$ token barrier required by direct simulation. (ii) For a setting inspired by reinforcement learning with verifiable rewards (RLVR), where the learner improves a pre-trained reference model using an outcome verifier, we show that curriculum reduces the requirement on the reference model from coverage at the full sequence length $T$ to coverage at a shorter block length $B \ll T$, an exponentially weaker condition.

To address data overload and inefficient shape-level annotation in robotic visual inspection, this paper proposes a hardware-software integrated optoelectronic architecture. A non-imaging, low-data paradigm is established to minimize annotation dependency. First, a sensor-in-the-loop strategy reconfigures a Digital Micromirror Device (DMD) as a physical optical convolutional layer, enabling photonic-domain feature extraction that unifies sensing hardware and processing software. To suppress data volume at the source, a block-based compressed sensing strategy encodes spatial information into low-dimensional temporal signals, drastically reducing redundancy. Subsequently, to bypass laborious manual defect shape annotation, natural language descriptions guide the network to align with highly generalizable features from Contrastive Language-Image Pre-training (CLIP), steering the attention maps of the optoelectronic neural network toward defect shapes. Furthermore, a Localization Accuracy for Attention (LAA) metric is proposed to quantify shape-level defect localization performance. Experiments on transparent material defect detection validate the system's effectiveness. Parametric analysis reveals how measurement matrices, compression ratios, and block sizes affect accuracy. Results show that, compared to traditional imaging, the proposed architecture maintains equivalent accuracy while reducing data volume by 90% for Vision Transformers and computational workload by 60% for Convolutional Neural Networks. This low-data paradigm offers an efficient solution for industrial automation scenarios involving massive data streams, high acquisition costs, or constrained edge resources.

Estimating parameters of dynamical systems from sparse, noisy, and irregularly sampled data is often severely ill-conditioned. When multiple related datasets are available, they provide additional information if the shared structure and variability are properly modeled. We propose a hierarchical Bayesian framework for probabilistic meta-learning in dynamical systems, modeling dataset-specific parameters as draws from a shared population distribution. A numerical ODE solver is embedded within gradient-based MCMC to enable efficient posterior inference of the shared population and dataset-specific parameter distribution. Experiments show improved predictive performance over unpooled methods, highlighting the potential for data-efficient system identification in settings with sparse data.

While point cloud foundation models have significantly advanced point cloud video understanding, existing parameter-efficient fine-tuning (PEFT) methods still suffer from two critical limitations: prohibitive annotation costs for large-scale point cloud datasets and severe memory bottlenecks. In this paper, we aim to mine richer supervision signals from existing data rather than blindly scaling datasets. A further key principle is that the memory footprint of fine-tuning must be drastically reduced compared to full fine-tuning, which remains elusive for current PEFT techniques. Driven by these challenges, we identify three core desiderata: data-, parameter-, and memory efficiency, and present PoinTriE, a unified framework that excels along all three dimensions. For pre-training, pseudo-motion trajectories are synthesized via rigid transformations, paired with text corpora and 2D projections derived from raw point clouds. We then propose a Geometric-Motion Duality Network optimized via multimodal contrastive learning, rigid rotation prediction, and motion distribution divergence to produce dense self-supervision. During fine-tuning, we freeze the pretrained backbone and only update a lightweight Spatio-temporal Side Network built with LoRA units. Equipped with a gradient flow masking strategy, PoinTriE simultaneously reduces memory consumption and parameter overhead. Extensive experiments confirm that PoinTriE establishes new state-of-the-art results on action recognition and semantic segmentation tasks.

Electroencephalogram (EEG) analysis remains the clinical gold standard for epilepsy diagnosis and seizure detection. While Deep Learning (DL) has significantly advanced automated EEG interpretation, its transition from controlled experimental settings to routine clinical deployment is severely bottlenecked by fundamental architectural flaws. Standard DL models operate as opaque black-boxes lacking clinical interpretability, demand massive amounts of balanced annotated data, and incur steep computational costs incompatible with resource-constrained wearable or implantable neuromodulation devices. This paper presents a comprehensive review of these prevailing limitations and explores Kolmogorov-Arnold Networks (KANs) as a emerging paradigm for EEG-based seizure detection. By replacing the fixed activation functions of traditional neurons with flexible, learnable functions along the network's connections, KANs bridge the critical gap between predictive accuracy and mathematical transparency. We systematically analyze how KAN architectures resolve the shortcomings of traditional DL-based models by offering exceptional parameter efficiency, inherent interpretability for physician trust, and robust performance under data scarcity. Ultimately, this review establishes KANs not merely as an incremental algorithmic update, but as a fundamental paradigm shift necessary to actualize next-generation, patient-specific, and thoroughly transparent clinical EEG monitoring systems.

Deep Transfer Learning (DTL) allows for the efficient building of Intelligent Fault Diagnosis Systems (IFDS). On the other hand, DTL methods still heavily rely on large amounts of labelled data. Obtaining such an amount of data can be challenging when dealing with machines or structures faults. This document proposes a novel approach to the design of vibration-based IFDS using DTL in condition of strong data scarcity. A periodic multi-excitation level procedure leveraging intrinsic non-linearities of real-world systems is used to produce images that can be conveniently analysed by pre-trained Convolutional Neural Networks (CNNs) to diagnose faults. A new data visualization method and its augmentation technique are proposed in this paper to tackle the typical lack of data encountered during the design of IFDS. Experimental validation on a railway pantograph structure provides effective support for the proposed method.

Curriculum learning couples two design choices, how samples are scored by difficulty and how harder samples are paced into training, making it difficult to attribute observed gains to either component. We disentangle these factors with two evaluation protocols: stage-wise test subsets that validate scoring functions independently of curriculum training, and a baseline that applies the same pacing schedule to randomly ordered data. Within the Transfer Teacher framework (TTF), we use these protocols to evaluate a confusion-aware difficulty score that considers both correct-class confidence and the probability distribution over incorrect classes. On CIFAR-10 with ResNet-18 and VGG-16, the proposed score produces model-interpretable difficulty rankings that align with human intuition. However, at full data, neither curriculum nor anti-curriculum ordering improves accuracy over standard training, indicating that improving the scoring function alone is insufficient to overcome the known failure modes of curriculum learning in TTF. In contrast, We find that confusion-aware curriculum ordering result in consistent data-efficiency benefits, outperforming random ordering by up to 8.7% points at the 20% data regime, suggesting the potential of TTF as a data-efficient training method.

Real-time reconstruction of magnetohydrodynamic equilibria is essential for plasma shaping, stability assessment and feedback control in magnetic confinement fusion. However, Grad-Shafranov equilibrium calculations remain largely device-specific and iterative, limiting their use in latency-constrained control settings. Existing neural approaches can accelerate individual equilibrium predictions, but they do not generally provide reusable models across changing plasma boundaries or tokamak geometries. Here we show that equilibrium reconstruction can be recast as a cross-device operator learning problem. We develop a domain-specific neural operator framework that maps geometry and profile parameters directly to the poloidal flux field, replacing repeated solve-on-demand computation with amortized operator inference. Using the analytically tractable Solov'ev family as a controlled Grad-Shafranov testbed, we generate equilibria across eight geometrically distinct tokamak-like configurations and benchmark five neural operator architectures under four transfer-learning strategies. Single-geometry pretraining gives poor transfer to unseen devices, whereas multi-geometry pretraining enables data-efficient adaptation. The Wavelet Neural Operator gives the strongest cross-geometry performance, reaching mean relative L2 errors below 4% with 100 labelled target equilibria and below 2% with full fine-tuning. The predicted magnetic fields satisfy the divergence-free constraint to numerical precision, and four architectures achieve millisecond or sub-millisecond inference. These results identify neural operator pretraining as a route towards reusable, real-time equilibrium inference across fusion device configurations.

Large-scale learner-task interaction data are crucial for intelligent educational systems but are costly to collect and constrained by privacy and learner engagement. Learner simulators play a critical role in simulating scalable learner behavior without the need for continuous involvement of real learners. However, existing methods are predominantly \textbf{individual-centric}, pairing a simulator with each learner to iteratively infer latent knowledge states from dense interaction histories, which is both data- and computation-intensive, and fragile in cold-start scenarios. We propose a \textbf{cohort-aware roll-call simulation paradigm} that first constructs cohort-level proficiency priors and refines individual learner states through a small number of targeted diagnostic queries. Based on this paradigm, we introduce \textbf{Edu-Theater}, an LLM-powered agent system that performs cohort-aware learner simulation via a teacher agent and retrospective roll-call probing over learner logs. Edu-Theater enables scalable future behavior simulation without the need for dense per-learner histories. Experiments on two real-world datasets demonstrate that Edu-Theater achieves higher simulation accuracy with significantly fewer LLM calls, producing synthetic data that enhances downstream applications such as adaptive testing.

Jet tagging at the Large Hadron Collider increasingly relies on deep learning models trained on massive simulated datasets, leading to high computational costs and limited robustness to detector mismodeling. We introduce JetParticle-JEPA (JP-JEPA), a self-supervised Joint-Embedding Predictive Architecture that learns physically meaningful jet representations directly from continuous particle clouds without tokenization or reconstruction of raw inputs. Built on a Particle Transformer backbone, JP-JEPA predicts latent representations of masked particles while preserving fine-grained kinematic correlations. On the JetClass benchmark, JP-JEPA achieves performance comparable to fully supervised state-of-the-art methods on the full dataset, surpasses supervised baselines in low-label regimes, and significantly outperforms existing SSL approaches. On Top Quark and Quark-Gluon Tagging benchmarks, it remains on par with supervised methods. The learned representations also exhibit strong robustness to missing detector information and improved uncertainty behavior, highlighting JP-JEPA as a promising foundation-model framework for robust and data-efficient jet physics at the LHC.

Training deep neural networks for clinical time-series analysis is computationally demanding, yet many healthcare settings lack the resources required for repeated model development and deployment. This challenge is particularly evident in electrocardiogram classification, where large datasets and long training schedules make efficiency practically important. Progressive Data Dropout reduces training cost by excluding samples from gradient updates once they are learned, but it relies on model confidence and may retain samples that are difficult due to noise or ambiguity rather than useful signal. In this work, we introduce ERTS, an explainability-based reliability training signal for efficient ECG classification. ERTS uses explanation quality during training to distinguish between informative and unreliable uncertainty. Building on progressive data selection, we compute Grad-CAM attention maps for candidate samples and derive a focus score that measures whether model predictions are supported by coherent and localised patterns. Samples with low focus are filtered out, while those with meaningful attention are prioritised for gradient updates. We evaluate ERTS across three ECG datasets and multiple backbone architectures, showing consistent improvements in macro-F1 alongside reduced effective training cost. These results suggest that explanation quality can serve as a practical signal for improving both efficiency and reliability in clinical time-series learning. Code will be released.

Identifying the governing equations of complex dynamical systems remains a fundamental challenge across science and engineering. While early approaches relied on empirical data and heuristics, modern data-driven methods offer greater flexibility and fewer assumptions. However, data acquisition in real-world settings is often expensive. This work addresses this challenge by introducing an active learning strategy for dynamics discovery in the ultra-low data limit. Rather than sampling randomly, our method iteratively prioritizes regions that are most informative for model identification. This approach builds on Sparse Identification of Nonlinear Dynamics (SINDy), and utilizes an ensemble extension, E-SINDy, to estimate epistemic uncertainty and guide the sampling for both ordinary and partial differential equations (ODEs/PDEs). For ODEs, an exhaustive analysis is conducted on the Lorenz system across varying data budgets and noise levels. For PDEs, two systems with contrasting dynamical characteristics are examined: the Burgers' equation, where a sharp shock front creates a distinction between informative and uninformative regions, and the Kuramoto-Sivashinsky equation, which presents a more spatially complex sampling landscape. Across all scenarios, the proposed method accurately identifies the governing dynamics with significantly fewer data samples than random sampling.