Vision-language models (VLMs) are facing the challenges of understanding and following multimodal assembly instructions, particularly when fine-grained spatial reasoning and precise object state detection are required. In this work, we explore LEGO Co-builder, a hybrid benchmark combining real-world LEGO assembly logic with programmati-cally generated multimodal scenes. The dataset captures stepwise visual states and procedural instructions, allowing controlled evaluation of instruction-following, object detection, and state detection. We introduce a unified framework and assess leading VLMs such as GPT -4o, Gemini, and Qwen-VL, under zero-shot and fine-tuned settings. Our results reveal that even advanced models like GPT -4o struggle with fine-grained assembly tasks, with a maximum F1 score of just 40.54% on state detection, highlighting gaps in fine-grained visual understanding. We release the benchmark, codebase, and generation pipeline to support future research on multi-modal assembly assistants grounded in real-world workflows.

Deep learning has significantly propelled the performance of ECG arrhythmia classification, yet its clinical adoption remains hindered by challenges in interpretability and deployment on resource-constrained edge devices. To bridge this gap, we propose EXGnet, a novel and reliable ECG arrhythmia classification network tailored for single-lead signals, specifically designed to balance high accuracy, explainability, and edge compatibility. EXGnet integrates XAI supervision during training via a normalized cross-correlation based loss, directing the model's attention to clinically relevant ECG regions, similar to a cardiologist's focus. This supervision is driven by automatically generated ground truth, derived through an innovative heart rate variability-based approach, without the need for manual annotation. To enhance classification accuracy without compromising deployment simplicity, we incorporate quantitative ECG features during training. These enrich the model with multi-domain knowledge but are excluded during inference, keeping the model lightweight for edge deployment. Additionally, we introduce an innovative multiresolution block to efficiently capture both short and long-term signal features while maintaining computational efficiency. Rigorous evaluation on the Chapman and Ningbo benchmark datasets validates the supremacy of EXGnet, which achieves average five-fold accuracies of 98.762% and 96.932%, and F1-scores of 97.910% and 95.527%, respectively. Comprehensive ablation studies and both quantitative and qualitative interpretability assessment confirm that the XAI guidance is pivotal, demonstrably enhancing the model's focus and trustworthiness. Overall, EXGnet sets a new benchmark by combining high-performance arrhythmia classification with interpretability, paving the way for more trustworthy and accessible portable ECG based health monitoring systems.

Mindfulness training is widely recognized for its benefits in reducing depression, anxiety, and loneliness. With the rise of smartphone-based mindfulness apps, digital meditation has become more accessible, but sustaining long-term user engagement remains a challenge. This paper explores whether respiration biosignal feedback and mindfulness skill estimation enhance system usability and skill development. We develop a smartphone's accelerometer-based respiration tracking algorithm, eliminating the need for additional wearables. Unlike existing methods, our approach accurately captures slow breathing patterns typical of mindfulness meditation. Additionally, we introduce the first quantitative framework to estimate mindfulness skills-concentration, sensory clarity, and equanimity-based on accelerometer-derived respiration data. We develop and test our algorithms on 261 mindfulness sessions in both controlled and real-world settings. A user study comparing an experimental group receiving biosignal feedback with a control group using a standard app shows that respiration feedback enhances system usability. Our respiration tracking model achieves a mean absolute error (MAE) of 1.6 breaths per minute, closely aligning with ground truth data, while our mindfulness skill estimation attains F1 scores of 80-84% in tracking skill progression. By integrating respiration tracking and mindfulness estimation into a commercial app, we demonstrate the potential of smartphone sensors to enhance digital mindfulness training.

Despite the widespread use of Uniform Manifold Approximation and Projection (UMAP), the impact of its stochastic optimization process on the results remains underexplored. We observed that it often produces unstable results where the projections of data points are determined mostly by chance rather than reflecting neighboring structures. To address this limitation, we introduce (r,d)-stability to UMAP: a framework that analyzes the stochastic positioning of data points in the projection space. To assess how stochastic elements, specifically initial projection positions and negative sampling, impact UMAP results, we introduce "ghosts", or duplicates of data points representing potential positional variations due to stochasticity. We define a data point's projection as (r,d)-stable if its ghosts perturbed within a circle of radius r in the initial projection remain confined within a circle of radius d for their final positions. To efficiently compute the ghost projections, we develop an adaptive dropping scheme that reduces a runtime up to 60% compared to an unoptimized baseline while maintaining approximately 90% of unstable points. We also present a visualization tool that supports the interactive exploration of the (r,d)-stability of data points. Finally, we demonstrate the effectiveness of our framework by examining the stability of projections of real-world datasets and present usage guidelines for the effective use of our framework.

Food is not only essential to human health but also serves as a medium for cultural identity and emotional connection. In the context of precision nutrition, accurately identifying and classifying food images is critical for dietary monitoring, nutrient estimation, and personalized health management. However, fine-grained food classification remains challenging due to the subtle visual differences among similar dishes. To address this, we propose Feature-Enhanced TResNet (FE-TResNet), a novel deep learning model designed to improve the accuracy of food image recognition in fine-grained scenarios. Built on the TResNet architecture, FE-TResNet integrates a Style-based Recalibration Module (StyleRM) and Deep Channel-wise Attention (DCA) to enhance feature extraction and emphasize subtle distinctions between food items. Evaluated on two benchmark Chinese food datasets-ChineseFoodNet and CNFOOD-241-FE-TResNet achieved high classification accuracies of 81.37% and 80.29%, respectively. These results demonstrate its effectiveness and highlight its potential as a key enabler for intelligent dietary assessment and personalized recommendations in precision nutrition systems.

Monitoring for changes in a predictive relationship represented by a fitted supervised learning model (aka concept drift detection) is a widespread problem, e.g., for retrospective analysis to determine whether the predictive relationship was stable over the training data, for prospective analysis to determine when it is time to update the predictive model, for quality control of processes whose behavior can be characterized by a predictive relationship, etc. A general and powerful Fisher score-based concept drift approach has recently been proposed, in which concept drift detection reduces to detecting changes in the mean of the model's score vector using a multivariate exponentially weighted moving average (MEWMA). To implement the approach, the initial data must be split into two subsets. The first subset serves as the training sample to which the model is fit, and the second subset serves as an out-of-sample test set from which the MEWMA control limit (CL) is determined. In this paper, we develop a novel bootstrap procedure for computing the CL. Our bootstrap CL provides much more accurate control of false-alarm rate, especially when the sample size and/or false-alarm rate is small. It also allows the entire initial sample to be used for training, resulting in a more accurate fitted supervised learning model. We show that a standard nested bootstrap (inner loop accounting for future data variability and outer loop accounting for training sample variability) substantially underestimates variability and develop a 632-like correction that appropriately accounts for this. We demonstrate the advantages with numerical examples.

Regularized linear discriminant analysis (RLDA) is a widely used tool for classification and dimensionality reduction, but its performance in high-dimensional scenarios is inconsistent. Existing theoretical analyses of RLDA often lack clear insight into how data structure affects classification performance. To address this issue, we derive a non-asymptotic approximation of the misclassification rate and thus analyze the structural effect and structural adjustment strategies of RLDA. Based on this, we propose the Spectral Enhanced Discriminant Analysis (SEDA) algorithm, which optimizes the data structure by adjusting the spiked eigenvalues of the population covariance matrix. By developing a new theoretical result on eigenvectors in random matrix theory, we derive an asymptotic approximation on the misclassification rate of SEDA. The bias correction algorithm and parameter selection strategy are then obtained. Experiments on synthetic and real datasets show that SEDA achieves higher classification accuracy and dimensionality reduction compared to existing LDA methods.

Language models for program synthesis are usually trained and evaluated on programming competition datasets (MBPP, APPS). However, these datasets are limited in size and quality, while these language models are extremely data hungry. Additionally, the language models have a misaligned program synthesis process compared to humans. While humans iteratively develop code with the help of a compiler, most program synthesis models currently produce code in one go. To solve these issues, we introduce a bootstrapping algorithm for program synthesis, that supports teaching models how to repair. We show that bootstrapping consistently outperforms regular fine-tuning. Compared to other work, our bootstrapped model performs on par with fine-tuned models that are 68\% larger. Notably, bootstrapping with repairing also improves non-repairing performance compared to regular bootstrapping during inference. However, on our models, repairing during inference is likely inferior to simply sampling the same number of solutions. Furthermore, we find that there are issues with the example test cases in the training portion of the APPS dataset that are valuable to the community, as many repairing and reinforcement learning methods rely on them.

Desktop accessibility metadata enables AI agents to interpret screens and supports users who depend on tools like screen readers. Yet, many applications remain largely inaccessible due to incomplete or missing metadata provided by developers - our investigation shows that only 33% of applications on macOS offer full accessibility support. While recent work on structured screen representation has primarily addressed specific challenges, such as UI element detection or captioning, none has attempted to capture the full complexity of desktop interfaces by replicating their entire hierarchical structure. To bridge this gap, we introduce Screen2AX, the first framework to automatically create real-time, tree-structured accessibility metadata from a single screenshot. Our method uses vision-language and object detection models to detect, describe, and organize UI elements hierarchically, mirroring macOS's system-level accessibility structure. To tackle the limited availability of data for macOS desktop applications, we compiled and publicly released three datasets encompassing 112 macOS applications, each annotated for UI element detection, grouping, and hierarchical accessibility metadata alongside corresponding screenshots. Screen2AX accurately infers hierarchy trees, achieving a 77% F1 score in reconstructing a complete accessibility tree. Crucially, these hierarchy trees improve the ability of autonomous agents to interpret and interact with complex desktop interfaces. We introduce Screen2AX-Task, a benchmark specifically designed for evaluating autonomous agent task execution in macOS desktop environments. Using this benchmark, we demonstrate that Screen2AX delivers a 2.2x performance improvement over native accessibility representations and surpasses the state-of-the-art OmniParser V2 system on the ScreenSpot benchmark.

The performance of large language models (LLMs) is closely tied to their training data, which can include copyrighted material or private information, raising legal and ethical concerns. Additionally, LLMs face criticism for dataset contamination and internalizing biases. To address these issues, the Pre-Training Data Detection (PDD) task was proposed to identify if specific data was included in an LLM's pre-training corpus. However, existing PDD methods often rely on superficial features like prediction confidence and loss, resulting in mediocre performance. To improve this, we introduce NA-PDD, a novel algorithm analyzing differential neuron activation patterns between training and non-training data in LLMs. This is based on the observation that these data types activate different neurons during LLM inference. We also introduce CCNewsPDD, a temporally unbiased benchmark employing rigorous data transformations to ensure consistent time distributions between training and non-training data. Our experiments demonstrate that NA-PDD significantly outperforms existing methods across three benchmarks and multiple LLMs.