Forecasting from Clinical Textual Time Series: Adaptations of the Encoder and Decoder Language Model Families

Clinical case reports encode rich, temporal patient trajectories that are often underexploited by traditional machine learning methods relying on structured data. In this work, we introduce the forecasting problem from textual time series, where timestamped clinical findings--extracted via an LLM-assisted annotation pipeline--serve as the primary input for prediction. We systematically evaluate a diverse suite of models, including fine-tuned decoder-based large language models and encoder-based transformers, on tasks of event occurrence prediction, temporal ordering, and survival analysis. Our experiments reveal that encoder-based models consistently achieve higher F1 scores and superior temporal concordance for short- and long-horizon event forecasting, while fine-tuned masking approaches enhance ranking performance. In contrast, instruction-tuned decoder models demonstrate a relative advantage in survival analysis, especially in early prognosis settings. Our sensitivity analyses further demonstrate the importance of time ordering, which requires clinical time series construction, as compared to text ordering, the format of the text inputs that LLMs are classically trained on. This highlights the additional benefit that can be ascertained from time-ordered corpora, with implications for temporal tasks in the era of widespread LLM use.

Sparseformer: a Transferable Transformer with Multi-granularity Token Sparsification for Medical Time Series Classification

Medical time series (MedTS) classification is crucial for improved diagnosis in healthcare, and yet it is challenging due to the varying granularity of patterns, intricate inter-channel correlation, information redundancy, and label scarcity. While existing transformer-based models have shown promise in time series analysis, they mainly focus on forecasting and fail to fully exploit the distinctive characteristics of MedTS data. In this paper, we introduce Sparseformer, a transformer specifically designed for MedTS classification. We propose a sparse token-based dual-attention mechanism that enables global modeling and token compression, allowing dynamic focus on the most informative tokens while distilling redundant features. This mechanism is then applied to the multi-granularity, cross-channel encoding of medical signals, capturing intra- and inter-granularity correlations and inter-channel connections. The sparsification design allows our model to handle heterogeneous inputs of varying lengths and channels directly. Further, we introduce an adaptive label encoder to address label space misalignment across datasets, equipping our model with cross-dataset transferability to alleviate the medical label scarcity issue. Our model outperforms 12 baselines across seven medical datasets under supervised learning. In the few-shot learning experiments, our model also achieves superior average results. In addition, the in-domain and cross-domain experiments among three diagnostic scenarios demonstrate our model's zero-shot learning capability. Collectively, these findings underscore the robustness and transferability of our model in various medical applications.

Explainability by design: an experimental analysis of the legal coding process

Behind a set of rules in Deontic Defeasible Logic, there is a mapping process of normative background fragments. This process goes from text to rules and implicitly encompasses an explanation of the coded fragments. In this paper we deliver a methodology for \textit{legal coding} that starts with a fragment and goes onto a set of Deontic Defeasible Logic rules, involving a set of \textit{scenarios} to test the correctness of the coded fragments. The methodology is illustrated by the coding process of an example text. We then show the results of a series of experiments conducted with humans encoding a variety of normative backgrounds and corresponding cases in which we have measured the efforts made in the coding process, as related to some measurable features. To process these examples, a recently developed technology, Houdini, that allows reasoning in Deontic Defeasible Logic, has been employed. Finally we provide a technique to forecast time required in coding, that depends on factors such as knowledge of the legal domain, knowledge of the coding processes, length of the text, and a measure of \textit{depth} that refers to the length of the paths of legal references.

Waymo Driverless Car Data Analysis and Driving Modeling using CNN and LSTM

Self driving cars has been the biggest innovation in the automotive industry, but to achieve human level accuracy or near human level accuracy is the biggest challenge that research scientists are facing today. Unlike humans autonomous vehicles do not work on instincts rather they make a decision based on the training data that has been fed to them using machine learning models using which they can make decisions in different conditions they face in the real world. With the advancements in machine learning especially deep learning the self driving car research skyrocketed. In this project we have presented multiple ways to predict acceleration of the autonomous vehicle using Waymo's open dataset. Our main approach was to using CNN to mimic human action and LSTM to treat this as a time series problem.

Retrieving Time-Series Differences Using Natural Language Queries

Effectively searching time-series data is essential for system analysis; however, traditional methods often require domain expertise to define search criteria. Recent advancements have enabled natural language-based search, but these methods struggle to handle differences between time-series data. To address this limitation, we propose a natural language query-based approach for retrieving pairs of time-series data based on differences specified in the query. Specifically, we define six key characteristics of differences, construct a corresponding dataset, and develop a contrastive learning-based model to align differences between time-series data with query texts. Experimental results demonstrate that our model achieves an overall mAP score of 0.994 in retrieving time-series pairs.

Learning Stabilizing Policies via an Unstable Subspace Representation

We study the problem of learning to stabilize (LTS) a linear time-invariant (LTI) system. Policy gradient (PG) methods for control assume access to an initial stabilizing policy. However, designing such a policy for an unknown system is one of the most fundamental problems in control, and it may be as hard as learning the optimal policy itself. Existing work on the LTS problem requires large data as it scales quadratically with the ambient dimension. We propose a two-phase approach that first learns the left unstable subspace of the system and then solves a series of discounted linear quadratic regulator (LQR) problems on the learned unstable subspace, targeting to stabilize only the system's unstable dynamics and reduce the effective dimension of the control space. We provide non-asymptotic guarantees for both phases and demonstrate that operating on the unstable subspace reduces sample complexity. In particular, when the number of unstable modes is much smaller than the state dimension, our analysis reveals that LTS on the unstable subspace substantially speeds up the stabilization process. Numerical experiments are provided to support this sample complexity reduction achieved by our approach.

Time-Series Forecasting via Topological Information Supervised Framework with Efficient Topological Feature Learning

Topological Data Analysis (TDA) has emerged as a powerful tool for extracting meaningful features from complex data structures, driving significant advancements in fields such as neuroscience, biology, machine learning, and financial modeling. Despite its success, the integration of TDA with time-series prediction remains underexplored due to three primary challenges: the limited utilization of temporal dependencies within topological features, computational bottlenecks associated with persistent homology, and the deterministic nature of TDA pipelines restricting generalized feature learning. This study addresses these challenges by proposing the Topological Information Supervised (TIS) Prediction framework, which leverages neural networks and Conditional Generative Adversarial Networks (CGANs) to generate synthetic topological features, preserving their distribution while significantly reducing computational time. We propose a novel training strategy that integrates topological consistency loss to improve the predictive accuracy of deep learning models. Specifically, we introduce two state-of-the-art models, TIS-BiGRU and TIS-Informer, designed to capture short-term and long-term temporal dependencies, respectively. Comparative experimental results demonstrate the superior performance of TIS models over conventional predictors, validating the effectiveness of integrating topological information. This work not only advances TDA-based time-series prediction but also opens new avenues for utilizing topological features in deep learning architectures.

Wavelet Policy: Imitation Policy Learning in Frequency Domain with Wavelet Transforms

Recent imitation learning policies, often framed as time series prediction tasks, directly map robotic observations-such as high-dimensional visual data and proprioception-into the action space. While time series prediction primarily relies on spatial domain modeling, the underutilization of frequency domain analysis in robotic manipulation trajectory prediction may lead to neglecting the inherent temporal information embedded within action sequences. To address this, we reframe imitation learning policies through the lens of the frequency domain and introduce the Wavelet Policy. This novel approach employs wavelet transforms (WT) for feature preprocessing and extracts multi-scale features from the frequency domain using the SE2MD (Single Encoder to Multiple Decoder) architecture. Furthermore, to enhance feature mapping in the frequency domain and increase model capacity, we introduce a Learnable Frequency-Domain Filter (LFDF) after each frequency decoder, improving adaptability under different visual conditions. Our results show that the Wavelet Policy outperforms state-of-the-art (SOTA) end-to-end methods by over 10% on four challenging robotic arm tasks, while maintaining a comparable parameter count. In long-range settings, its performance declines more slowly as task volume increases. The code will be publicly available.

Inference of hidden common driver dynamics by anisotropic self-organizing neural networks

We are introducing a novel approach to infer the underlying dynamics of hidden common drivers, based on analyzing time series data from two driven dynamical systems. The inference relies on time-delay embedding, estimation of the intrinsic dimension of the observed systems, and their mutual dimension. A key component of our approach is a new anisotropic training technique applied to Kohonen's self-organizing map, which effectively learns the attractor of the driven system and separates it into submanifolds corresponding to the self-dynamics and shared dynamics. To demonstrate the effectiveness of our method, we conducted simulated experiments using different chaotic maps in a setup, where two chaotic maps were driven by a third map with nonlinear coupling. The inferred time series exhibited high correlation with the time series of the actual hidden common driver, in contrast to the observed systems. The quality of our reconstruction were compared and shown to be superior to several other methods that are intended to find the common features behind the observed time series, including linear methods like PCA and ICA as well as nonlinear methods like dynamical component analysis, canonical correlation analysis and even deep canonical correlation analysis.

Quantum Adaptive Self-Attention for Quantum Transformer Models

Transformer models have revolutionized sequential learning across various domains, yet their self-attention mechanism incurs quadratic computational cost, posing limitations for real-time and resource-constrained tasks. To address this, we propose Quantum Adaptive Self-Attention (QASA), a novel hybrid architecture that enhances classical Transformer models with a quantum attention mechanism. QASA replaces dot-product attention with a parameterized quantum circuit (PQC) that adaptively captures inter-token relationships in the quantum Hilbert space. Additionally, a residual quantum projection module is introduced before the feedforward network to further refine temporal features. Our design retains classical efficiency in earlier layers while injecting quantum expressiveness in the final encoder block, ensuring compatibility with current NISQ hardware. Experiments on synthetic time-series tasks demonstrate that QASA achieves faster convergence and superior generalization compared to both standard Transformers and reduced classical variants. Preliminary complexity analysis suggests potential quantum advantages in gradient computation, opening new avenues for efficient quantum deep learning models.