Enhancing Visual Inspection Capability of Multi-Modal Large Language Models on Medical Time Series with Supportive Conformalized and Interpretable Small Specialized Models

Large language models (LLMs) exhibit remarkable capabilities in visual inspection of medical time-series data, achieving proficiency comparable to human clinicians. However, their broad scope limits domain-specific precision, and proprietary weights hinder fine-tuning for specialized datasets. In contrast, small specialized models (SSMs) excel in targeted tasks but lack the contextual reasoning required for complex clinical decision-making. To address these challenges, we propose ConMIL (Conformalized Multiple Instance Learning), a decision-support SSM that integrates seamlessly with LLMs. By using Multiple Instance Learning (MIL) to identify clinically significant signal segments and conformal prediction for calibrated set-valued outputs, ConMIL enhances LLMs' interpretative capabilities for medical time-series analysis. Experimental results demonstrate that ConMIL significantly improves the performance of state-of-the-art LLMs, such as ChatGPT4.0 and Qwen2-VL-7B. Specifically, \ConMIL{}-supported Qwen2-VL-7B achieves 94.92% and 96.82% precision for confident samples in arrhythmia detection and sleep staging, compared to standalone LLM accuracy of 46.13% and 13.16%. These findings highlight the potential of ConMIL to bridge task-specific precision and broader contextual reasoning, enabling more reliable and interpretable AI-driven clinical decision support.

Role of Mixup in Topological Persistence Based Knowledge Distillation for Wearable Sensor Data

The analysis of wearable sensor data has enabled many successes in several applications. To represent the high-sampling rate time-series with sufficient detail, the use of topological data analysis (TDA) has been considered, and it is found that TDA can complement other time-series features. Nonetheless, due to the large time consumption and high computational resource requirements of extracting topological features through TDA, it is difficult to deploy topological knowledge in various applications. To tackle this problem, knowledge distillation (KD) can be adopted, which is a technique facilitating model compression and transfer learning to generate a smaller model by transferring knowledge from a larger network. By leveraging multiple teachers in KD, both time-series and topological features can be transferred, and finally, a superior student using only time-series data is distilled. On the other hand, mixup has been popularly used as a robust data augmentation technique to enhance model performance during training. Mixup and KD employ similar learning strategies. In KD, the student model learns from the smoothed distribution generated by the teacher model, while mixup creates smoothed labels by blending two labels. Hence, this common smoothness serves as the connecting link that establishes a connection between these two methods. In this paper, we analyze the role of mixup in KD with time-series as well as topological persistence, employing multiple teachers. We present a comprehensive analysis of various methods in KD and mixup on wearable sensor data.

Position: There are no Champions in Long-Term Time Series Forecasting

Recent advances in long-term time series forecasting have introduced numerous complex prediction models that consistently outperform previously published architectures. However, this rapid progression raises concerns regarding inconsistent benchmarking and reporting practices, which may undermine the reliability of these comparisons. Our position emphasizes the need to shift focus away from pursuing ever-more complex models and towards enhancing benchmarking practices through rigorous and standardized evaluation methods. To support our claim, we first perform a broad, thorough, and reproducible evaluation of the top-performing models on the most popular benchmark by training 3,500+ networks over 14 datasets. Then, through a comprehensive analysis, we find that slight changes to experimental setups or current evaluation metrics drastically shift the common belief that newly published results are advancing the state of the art. Our findings suggest the need for rigorous and standardized evaluation methods that enable more substantiated claims, including reproducible hyperparameter setups and statistical testing.

Calibrated Unsupervised Anomaly Detection in Multivariate Time-series using Reinforcement Learning

This paper investigates unsupervised anomaly detection in multivariate time-series data using reinforcement learning (RL) in the latent space of an autoencoder. A significant challenge is the limited availability of anomalous data, often leading to misclassifying anomalies as normal events, thus raising false negatives. RL can help overcome this limitation by promoting exploration and balancing exploitation during training, effectively preventing overfitting. Wavelet analysis is also utilized to enhance anomaly detection, enabling time-series data decomposition into both time and frequency domains. This approach captures anomalies at multiple resolutions, with wavelet coefficients extracted to detect both sudden and subtle shifts in the data, thereby refining the anomaly detection process. We calibrate the decision boundary by generating synthetic anomalies and embedding a supervised framework within the model. This supervised element aids the unsupervised learning process by fine-tuning the decision boundary and increasing the model's capacity to distinguish between normal and anomalous patterns effectively.

Unifying Prediction and Explanation in Time-Series Transformers via Shapley-based Pretraining

In this paper, we propose ShapTST, a framework that enables time-series transformers to efficiently generate Shapley-value-based explanations alongside predictions in a single forward pass. Shapley values are widely used to evaluate the contribution of different time-steps and features in a test sample, and are commonly generated through repeatedly inferring on each sample with different parts of information removed. Therefore, it requires expensive inference-time computations that occur at every request for model explanations. In contrast, our framework unifies the explanation and prediction in training through a novel Shapley-based pre-training design, which eliminates the undesirable test-time computation and replaces it with a single-time pre-training. Moreover, this specialized pre-training benefits the prediction performance by making the transformer model more effectively weigh different features and time-steps in the time-series, particularly improving the robustness against data noise that is common to raw time-series data. We experimentally validated our approach on eight public datasets, where our time-series model achieved competitive results in both classification and regression tasks, while providing Shapley-based explanations similar to those obtained with post-hoc computation. Our work offers an efficient and explainable solution for time-series analysis tasks in the safety-critical applications.

Qwen2.5-VL Technical Report

We introduce Qwen2.5-VL, the latest flagship model of Qwen vision-language series, which demonstrates significant advancements in both foundational capabilities and innovative functionalities. Qwen2.5-VL achieves a major leap forward in understanding and interacting with the world through enhanced visual recognition, precise object localization, robust document parsing, and long-video comprehension. A standout feature of Qwen2.5-VL is its ability to localize objects using bounding boxes or points accurately. It provides robust structured data extraction from invoices, forms, and tables, as well as detailed analysis of charts, diagrams, and layouts. To handle complex inputs, Qwen2.5-VL introduces dynamic resolution processing and absolute time encoding, enabling it to process images of varying sizes and videos of extended durations (up to hours) with second-level event localization. This allows the model to natively perceive spatial scales and temporal dynamics without relying on traditional normalization techniques. By training a native dynamic-resolution Vision Transformer (ViT) from scratch and incorporating Window Attention, we reduce computational overhead while maintaining native resolution. As a result, Qwen2.5-VL excels not only in static image and document understanding but also as an interactive visual agent capable of reasoning, tool usage, and task execution in real-world scenarios such as operating computers and mobile devices. Qwen2.5-VL is available in three sizes, addressing diverse use cases from edge AI to high-performance computing. The flagship Qwen2.5-VL-72B model matches state-of-the-art models like GPT-4o and Claude 3.5 Sonnet, particularly excelling in document and diagram understanding. Additionally, Qwen2.5-VL maintains robust linguistic performance, preserving the core language competencies of the Qwen2.5 LLM.

Explaining the Success of Nearest Neighbor Methods in Prediction

Many modern methods for prediction leverage nearest neighbor search to find past training examples most similar to a test example, an idea that dates back in text to at least the 11th century and has stood the test of time. This monograph aims to explain the success of these methods, both in theory, for which we cover foundational nonasymptotic statistical guarantees on nearest-neighbor-based regression and classification, and in practice, for which we gather prominent methods for approximate nearest neighbor search that have been essential to scaling prediction systems reliant on nearest neighbor analysis to handle massive datasets. Furthermore, we discuss connections to learning distances for use with nearest neighbor methods, including how random decision trees and ensemble methods learn nearest neighbor structure, as well as recent developments in crowdsourcing and graphons. In terms of theory, our focus is on nonasymptotic statistical guarantees, which we state in the form of how many training data and what algorithm parameters ensure that a nearest neighbor prediction method achieves a user-specified error tolerance. We begin with the most general of such results for nearest neighbor and related kernel regression and classification in general metric spaces. In such settings in which we assume very little structure, what enables successful prediction is smoothness in the function being estimated for regression, and a low probability of landing near the decision boundary for classification. In practice, these conditions could be difficult to verify for a real dataset. We then cover recent guarantees on nearest neighbor prediction in the three case studies of time series forecasting, recommending products to people over time, and delineating human organs in medical images by looking at image patches. In these case studies, clustering structure enables successful prediction.

An accuracy-runtime trade-off comparison of scalable Gaussian process approximations for spatial data

Gaussian processes (GPs) are flexible, probabilistic, non-parametric models widely employed in various fields such as spatial statistics, time series analysis, and machine learning. A drawback of Gaussian processes is their computational cost having $\mathcal{O}(N^3)$ time and $\mathcal{O}(N^2)$ memory complexity which makes them prohibitive for large datasets. Numerous approximation techniques have been proposed to address this limitation. In this work, we systematically compare the accuracy of different Gaussian process approximations concerning marginal likelihood evaluation, parameter estimation, and prediction taking into account the time required to achieve a certain accuracy. We analyze this trade-off between accuracy and runtime on multiple simulated and large-scale real-world datasets and find that Vecchia approximations consistently emerge as the most accurate in almost all experiments. However, for certain real-world data sets, low-rank inducing point-based methods, i.e., full-scale and modified predictive process approximations, can provide more accurate predictive distributions for extrapolation.

A spectral clustering-type algorithm for the consistent estimation of the Hurst distribution in moderately high dimensions

Scale invariance (fractality) is a prominent feature of the large-scale behavior of many stochastic systems. In this work, we construct an algorithm for the statistical identification of the Hurst distribution (in particular, the scaling exponents) undergirding a high-dimensional fractal system. The algorithm is based on wavelet random matrices, modified spectral clustering and a model selection step for picking the value of the clustering precision hyperparameter. In a moderately high-dimensional regime where the dimension, the sample size and the scale go to infinity, we show that the algorithm consistently estimates the Hurst distribution. Monte Carlo simulations show that the proposed methodology is efficient for realistic sample sizes and outperforms another popular clustering method based on mixed-Gaussian modeling. We apply the algorithm in the analysis of real-world macroeconomic time series to unveil evidence for cointegration.

Two-Stage Representation Learning for Analyzing Movement Behavior Dynamics in People Living with Dementia

In remote healthcare monitoring, time series representation learning reveals critical patient behavior patterns from high-frequency data. This study analyzes home activity data from individuals living with dementia by proposing a two-stage, self-supervised learning approach tailored to uncover low-rank structures. The first stage converts time-series activities into text sequences encoded by a pre-trained language model, providing a rich, high-dimensional latent state space using a PageRank-based method. This PageRank vector captures latent state transitions, effectively compressing complex behaviour data into a succinct form that enhances interpretability. This low-rank representation not only enhances model interpretability but also facilitates clustering and transition analysis, revealing key behavioral patterns correlated with clinicalmetrics such as MMSE and ADAS-COG scores. Our findings demonstrate the framework's potential in supporting cognitive status prediction, personalized care interventions, and large-scale health monitoring.