An Analysis of Temporal Dropout in Earth Observation Time Series for Regression Tasks

Missing instances in time series data impose a significant challenge to deep learning models, particularly in regression tasks. In the Earth Observation field, satellite failure or cloud occlusion frequently results in missing time-steps, introducing uncertainties in the predicted output and causing a decline in predictive performance. While many studies address missing time-steps through data augmentation to improve model robustness, the uncertainty arising at the input level is commonly overlooked. To address this gap, we introduce Monte Carlo Temporal Dropout (MC-TD), a method that explicitly accounts for input-level uncertainty by randomly dropping time-steps during inference using a predefined dropout ratio, thereby simulating the effect of missing data. To bypass the need for costly searches for the optimal dropout ratio, we extend this approach with Monte Carlo Concrete Temporal Dropout (MC-ConcTD), a method that learns the optimal dropout distribution directly. Both MC-TD and MC-ConcTD are applied during inference, leveraging Monte Carlo sampling for uncertainty quantification. Experiments on three EO time-series datasets demonstrate that MC-ConcTD improves predictive performance and uncertainty calibration compared to existing approaches. Additionally, we highlight the advantages of adaptive dropout tuning over manual selection, making uncertainty quantification more robust and accessible for EO applications.

Learning from Peers in Reasoning Models

Large Reasoning Models (LRMs) have the ability to self-correct even when they make mistakes in their reasoning paths. However, our study reveals that when the reasoning process starts with a short but poor beginning, it becomes difficult for the model to recover. We refer to this phenomenon as the "Prefix Dominance Trap". Inspired by psychological findings that peer interaction can promote self-correction without negatively impacting already accurate individuals, we propose **Learning from Peers** (LeaP) to address this phenomenon. Specifically, every tokens, each reasoning path summarizes its intermediate reasoning and shares it with others through a routing mechanism, enabling paths to incorporate peer insights during inference. However, we observe that smaller models sometimes fail to follow summarization and reflection instructions effectively. To address this, we fine-tune them into our **LeaP-T** model series. Experiments on AIME 2024, AIME 2025, AIMO 2025, and GPQA Diamond show that LeaP provides substantial improvements. For instance, QwQ-32B with LeaP achieves nearly 5 absolute points higher than the baseline on average, and surpasses DeepSeek-R1-671B on three math benchmarks with an average gain of 3.3 points. Notably, our fine-tuned LeaP-T-7B matches the performance of DeepSeek-R1-Distill-Qwen-14B on AIME 2024. In-depth analysis reveals LeaP's robust error correction by timely peer insights, showing strong error tolerance and handling varied task difficulty. LeaP marks a milestone by enabling LRMs to collaborate during reasoning. Our code, datasets, and models are available at https://learning-from-peers.github.io/ .

LLM4FTS: Enhancing Large Language Models for Financial Time Series Prediction

Predicting financial time series presents significant challenges due to inherent low signal-to-noise ratios and intricate temporal patterns. Traditional machine learning models exhibit limitations in this forecasting task constrained by their restricted model capacity. Recent advances in large language models (LLMs), with their greatly expanded parameter spaces, demonstrate promising potential for modeling complex dependencies in temporal sequences. However, existing LLM-based approaches typically focus on fixed-length patch analysis due to the Transformer architecture, ignoring market data's multi-scale pattern characteristics. In this study, we propose $LLM4FTS$, a novel framework that enhances LLM capabilities for temporal sequence modeling through learnable patch segmentation and dynamic wavelet convolution modules. Specifically,we first employ K-means++ clustering based on DTW distance to identify scale-invariant patterns in market data. Building upon pattern recognition results, we introduce adaptive patch segmentation that partitions temporal sequences while preserving maximal pattern integrity. To accommodate time-varying frequency characteristics, we devise a dynamic wavelet convolution module that emulates discrete wavelet transformation with enhanced flexibility in capturing time-frequency features. These three modules work together to improve large language model's ability to handle scale-invariant patterns in financial time series. Extensive experiments on real-world financial datasets substantiate the framework's efficacy, demonstrating superior performance in capturing complex market patterns and achieving state-of-the-art results in stock return prediction. The successful deployment in practical trading systems confirms its real-world applicability, representing a significant advancement in LLM applications for financial forecasting.

The Multimodal Paradox: How Added and Missing Modalities Shape Bias and Performance in Multimodal AI

Multimodal learning, which integrates diverse data sources such as images, text, and structured data, has proven superior to unimodal counterparts in high-stakes decision-making. However, while performance gains remain the gold standard for evaluating multimodal systems, concerns around bias and robustness are frequently overlooked. In this context, this paper explores two key research questions (RQs): (i) RQ1 examines whether adding a modality con-sistently enhances performance and investigates its role in shaping fairness measures, assessing whether it mitigates or amplifies bias in multimodal models; (ii) RQ2 investigates the impact of missing modalities at inference time, analyzing how multimodal models generalize in terms of both performance and fairness. Our analysis reveals that incorporating new modalities during training consistently enhances the performance of multimodal models, while fairness trends exhibit variability across different evaluation measures and datasets. Additionally, the absence of modalities at inference degrades performance and fairness, raising concerns about its robustness in real-world deployment. We conduct extensive experiments using multimodal healthcare datasets containing images, time series, and structured information to validate our findings.

TSP-OCS: A Time-Series Prediction for Optimal Camera Selection in Multi-Viewpoint Surgical Video Analysis

Recording the open surgery process is essential for educational and medical evaluation purposes; however, traditional single-camera methods often face challenges such as occlusions caused by the surgeon's head and body, as well as limitations due to fixed camera angles, which reduce comprehensibility of the video content. This study addresses these limitations by employing a multi-viewpoint camera recording system, capturing the surgical procedure from six different angles to mitigate occlusions. We propose a fully supervised learning-based time series prediction method to choose the best shot sequences from multiple simultaneously recorded video streams, ensuring optimal viewpoints at each moment. Our time series prediction model forecasts future camera selections by extracting and fusing visual and semantic features from surgical videos using pre-trained models. These features are processed by a temporal prediction network with TimeBlocks to capture sequential dependencies. A linear embedding layer reduces dimensionality, and a Softmax classifier selects the optimal camera view based on the highest probability. In our experiments, we created five groups of open thyroidectomy videos, each with simultaneous recordings from six different angles. The results demonstrate that our method achieves competitive accuracy compared to traditional supervised methods, even when predicting over longer time horizons. Furthermore, our approach outperforms state-of-the-art time series prediction techniques on our dataset. This manuscript makes a unique contribution by presenting an innovative framework that advances surgical video analysis techniques, with significant implications for improving surgical education and patient safety.

AI-assisted Automatic Jump Detection and Height Estimation in Volleyball Using a Waist-worn IMU

The physical load of jumps plays a critical role in injury prevention for volleyball players. However, manual video analysis of jump activities is time-intensive and costly, requiring significant effort and expensive hardware setups. The advent of the inertial measurement unit (IMU) and machine learning algorithms offers a convenient and efficient alternative. Despite this, previous research has largely focused on either jump classification or physical load estimation, leaving a gap in integrated solutions. This study aims to present a pipeline to automatically detect jumps and predict heights using data from a waist-worn IMU. The pipeline leverages a Multi-Stage Temporal Convolutional Network (MS-TCN) to detect jump segments in time-series data and classify the specific jump category. Subsequently, jump heights are estimated using three downstream regression machine learning models based on the identified segments. Our method is verified on a dataset comprising 10 players and 337 jumps. Compared to the result of VERT in height estimation (R-squared=-1.53), a commercial device commonly used in jump landing tasks, our method not only accurately identifies jump activities and their specific types (F1-score=0.90) but also demonstrates superior performance in height prediction (R-squared=0.50). This integrated solution offers a promising tool for monitoring physical load and mitigating injury risk in volleyball players.

HQNN-FSP: A Hybrid Classical-Quantum Neural Network for Regression-Based Financial Stock Market Prediction

Financial time-series forecasting remains a challenging task due to complex temporal dependencies and market fluctuations. This study explores the potential of hybrid quantum-classical approaches to assist in financial trend prediction by leveraging quantum resources for improved feature representation and learning. A custom Quantum Neural Network (QNN) regressor is introduced, designed with a novel ansatz tailored for financial applications. Two hybrid optimization strategies are proposed: (1) a sequential approach where classical recurrent models (RNN/LSTM) extract temporal dependencies before quantum processing, and (2) a joint learning framework that optimizes classical and quantum parameters simultaneously. Systematic evaluation using TimeSeriesSplit, k-fold cross-validation, and predictive error analysis highlights the ability of these hybrid models to integrate quantum computing into financial forecasting workflows. The findings demonstrate how quantum-assisted learning can contribute to financial modeling, offering insights into the practical role of quantum resources in time-series analysis.

FreCT: Frequency-augmented Convolutional Transformer for Robust Time Series Anomaly Detection

Time series anomaly detection is critical for system monitoring and risk identification, across various domains, such as finance and healthcare. However, for most reconstruction-based approaches, detecting anomalies remains a challenge due to the complexity of sequential patterns in time series data. On the one hand, reconstruction-based techniques are susceptible to computational deviation stemming from anomalies, which can lead to impure representations of normal sequence patterns. On the other hand, they often focus on the time-domain dependencies of time series, while ignoring the alignment of frequency information beyond the time domain. To address these challenges, we propose a novel Frequency-augmented Convolutional Transformer (FreCT). FreCT utilizes patch operations to generate contrastive views and employs an improved Transformer architecture integrated with a convolution module to capture long-term dependencies while preserving local topology information. The introduced frequency analysis based on Fourier transformation could enhance the model's ability to capture crucial characteristics beyond the time domain. To protect the training quality from anomalies and improve the robustness, FreCT deploys stop-gradient Kullback-Leibler (KL) divergence and absolute error to optimize consistency information in both time and frequency domains. Extensive experiments on four public datasets demonstrate that FreCT outperforms existing methods in identifying anomalies.

A Physically Driven Long Short Term Memory Model for Estimating Snow Water Equivalent over the Continental United States

Snow is an essential input for various land surface models. Seasonal snow estimates are available as snow water equivalent (SWE) from process-based reanalysis products or locally from in situ measurements. While the reanalysis products are computationally expensive and available at only fixed spatial and temporal resolutions, the in situ measurements are highly localized and sparse. To address these issues and enable the analysis of the effect of a large suite of physical, morphological, and geological conditions on the presence and amount of snow, we build a Long Short-Term Memory (LSTM) network, which is able to estimate the SWE based on time series input of the various physical/meteorological factors as well static spatial/morphological factors. Specifically, this model breaks down the SWE estimation into two separate tasks: (i) a classification task that indicates the presence/absence of snow on a specific day and (ii) a regression task that indicates the height of the SWE on a specific day in the case of snow presence. The model is trained using physical/in situ SWE measurements from the SNOw TELemetry (SNOTEL) snow pillows in the western United States. We will show that trained LSTM models have a classification accuracy of $\geq 93\%$ for the presence of snow and a coefficient of correlation of $\sim 0.9$ concerning their SWE estimates. We will also demonstrate that the models can generalize both spatially and temporally to previously unseen data.

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.