Reconstructing 3D scenes from sparse viewpoints is a long-standing challenge with wide applications. Recent advances in feed-forward 3D Gaussian sparse-view reconstruction methods provide an efficient solution for real-time novel view synthesis by leveraging geometric priors learned from large-scale multi-view datasets and computing 3D Gaussian centers via back-projection. Despite offering strong geometric cues, both feed-forward multi-view depth estimation and flow-depth joint estimation face key limitations: the former suffers from mislocation and artifact issues in low-texture or repetitive regions, while the latter is prone to local noise and global inconsistency due to unreliable matches when ground-truth flow supervision is unavailable. To overcome this, we propose JointSplat, a unified framework that leverages the complementarity between optical flow and depth via a novel probabilistic optimization mechanism. Specifically, this pixel-level mechanism scales the information fusion between depth and flow based on the matching probability of optical flow during training. Building upon the above mechanism, we further propose a novel multi-view depth-consistency loss to leverage the reliability of supervision while suppressing misleading gradients in uncertain areas. Evaluated on RealEstate10K and ACID, JointSplat consistently outperforms state-of-the-art (SOTA) methods, demonstrating the effectiveness and robustness of our proposed probabilistic joint flow-depth optimization approach for high-fidelity sparse-view 3D reconstruction.

Annotating data is a time-consuming and costly task, but it is inherently required for supervised machine learning. Active Learning (AL) is an established method that minimizes human labeling effort by iteratively selecting the most informative unlabeled samples for expert annotation, thereby improving the overall classification performance. Even though AL has been known for decades, AL is still rarely used in real-world applications. As indicated in the two community web surveys among the NLP community about AL, two main reasons continue to hold practitioners back from using AL: first, the complexity of setting AL up, and second, a lack of trust in its effectiveness. We hypothesize that both reasons share the same culprit: the large hyperparameter space of AL. This mostly unexplored hyperparameter space often leads to misleading and irreproducible AL experiment results. In this study, we first compiled a large hyperparameter grid of over 4.6 million hyperparameter combinations, second, recorded the performance of all combinations in the so-far biggest conducted AL study, and third, analyzed the impact of each hyperparameter in the experiment results. In the end, we give recommendations about the influence of each hyperparameter, demonstrate the surprising influence of the concrete AL strategy implementation, and outline an experimental study design for reproducible AL experiments with minimal computational effort, thus contributing to more reproducible and trustworthy AL research in the future.

We present an empirical validation of the directional non-commutative monoidal embedding framework recently introduced in prior work~\cite{Godavarti2025monoidal}. This framework defines learnable compositional embeddings using distinct non-commutative operators per dimension (axis) that satisfy an interchange law, generalizing classical one-dimensional transforms. Our primary goal is to verify that this framework can effectively model real data by applying it to a controlled, well-understood task: image classification on the MNIST dataset~\cite{lecun1998gradient}. A central hypothesis for why the proposed monoidal embedding works well is that it generalizes the Discrete Fourier Transform (DFT)~\cite{oppenheim1999discrete} by learning task-specific frequency components instead of using fixed basis frequencies. We test this hypothesis by comparing learned monoidal embeddings against fixed DFT-based embeddings on MNIST. The results show that as the embedding dimensionality decreases (e.g., from 32 to 8 to 2), the performance gap between the learned monoidal embeddings and fixed DFT-based embeddings on MNIST grows increasingly large. This comparison is used as an analytic tool to explain why the framework performs well: the learnable embeddings can capture the most discriminative spectral components for the task. Overall, our experiments confirm that directional non-commutative monoidal embeddings are highly effective for representing image data, offering a compact learned representation that retains high task performance. The code used in this work is available at https://github.com/mahesh-godavarti/directional_composition_mnist.

--The use of machine learning (ML) techniques has allowed rapid advancements in many scientific and engineering fields. One of these problems is that of surface soil taxonomy, a research area previously hindered by the reliance on human-derived classifications, which are mostly dependent on dividing a dataset based on historical understandings of that data rather than data-driven, statistically observable similarities. Using a ML-based taxonomy allows soil researchers to move beyond the limitations of human visualization and create classifications of high-dimension datasets with a much higher level of specificity than possible with hand-drawn taxonomies. Furthermore, this pipeline allows for the possibility of producing both highly accurate and flexible soil taxonomies with classes built to fit a specific application. The machine learning pipeline outlined in this work combines product quantization with the systematic evaluation of parameters and output to get the best available results, rather than accepting sub-optimal results by using either default settings or best guess settings.

Foundation models have begun to transform image analysis by acting as pretrained generalist backbones that can be adapted to many tasks even when post-training data are limited, yet their impact on spatial proteomics, imaging that maps proteins at single-cell resolution, remains limited. Here, we introduce KRONOS, a foundation model built for spatial proteomics. KRONOS was trained in a self-supervised manner on over 47 million image patches covering 175 protein markers, 16 tissue types, and 8 fluorescence-based imaging platforms. We introduce key architectural adaptations to address the high-dimensional, multi-channel, and heterogeneous nature of multiplex imaging. We demonstrate that KRONOS learns biologically meaningful representations across multiple scales, ranging from cellular and microenvironment to tissue levels, enabling it to address diverse downstream tasks, including cell phenotyping, region classification, and patient stratification. Evaluated across 11 independent cohorts, KRONOS achieves state-of-the-art performance across cell phenotyping, treatment response prediction, and retrieval tasks, and is highly data-efficient. KRONOS also introduces the paradigm of segmentation-free patch-level processing for efficient and scalable spatial proteomics analysis, allowing cross-institutional comparisons, and as an image reverse search engine for spatial patterns.

This paper introduces a novel approach to budgeted online active learning from finite-horizon data streams with extremely limited labeling budgets. In agricultural applications, such streams might include daily weather data over a growing season, and labels require costly measurements of weather-dependent plant characteristics. Our method integrates two key sources of prior information: a collection of preexisting expert predictors and episodic behavioral knowledge of the experts based on unlabeled data streams. Unlike previous research on online active learning with experts, our work simultaneously considers query budgets, finite horizons, and episodic knowledge, enabling effective learning in applications with severely limited labeling capacity. We demonstrate the utility of our approach through experiments on various prediction problems derived from both a realistic agricultural crop simulator and real-world data from multiple grape cultivars. The results show that our method significantly outperforms baseline expert predictions, uniform query selection, and existing approaches that consider budgets and limited horizons but neglect episodic knowledge, even under highly constrained labeling budgets.

Postoperative stroke remains a critical complication in elderly surgical intensive care unit (SICU) patients, contributing to prolonged hospitalization, elevated healthcare costs, and increased mortality. Accurate early risk stratification is essential to enable timely intervention and improve clinical outcomes. We constructed a combined cohort of 19,085 elderly SICU admissions from the MIMIC-III and MIMIC-IV databases and developed an interpretable machine learning (ML) framework to predict in-hospital stroke using clinical data from the first 24 hours of Intensive Care Unit (ICU) stay. The preprocessing pipeline included removal of high-missingness features, iterative Singular Value Decomposition (SVD) imputation, z-score normalization, one-hot encoding, and class imbalance correction via the Adaptive Synthetic Sampling (ADASYN) algorithm. A two-stage feature selection process-combining Recursive Feature Elimination with Cross-Validation (RFECV) and SHapley Additive exPlanations (SHAP)-reduced the initial 80 variables to 20 clinically informative predictors. Among eight ML models evaluated, CatBoost achieved the best performance with an AUROC of 0.8868 (95% CI: 0.8802--0.8937). SHAP analysis and ablation studies identified prior cerebrovascular disease, serum creatinine, and systolic blood pressure as the most influential risk factors. Our results highlight the potential of interpretable ML approaches to support early detection of postoperative stroke and inform decision-making in perioperative critical care.

Stock market indices serve as fundamental market measurement that quantify systematic market dynamics. However, accurate index price prediction remains challenging, primarily because existing approaches treat indices as isolated time series and frame the prediction as a simple regression task. These methods fail to capture indices' inherent nature as aggregations of constituent stocks with complex, time-varying interdependencies. To address these limitations, we propose Cubic, a novel end-to-end framework that explicitly models the adaptive fusion of constituent stocks for index price prediction. Our main contributions are threefold. i) Fusion in the latent space: we introduce the fusion mechanism over the latent embedding of the stocks to extract the information from the vast number of stocks. ii) Binary encoding classification: since regression tasks are challenging due to continuous value estimation, we reformulate the regression into the classification task, where the target value is converted to binary and we optimize the prediction of the value of each digit with cross-entropy loss. iii) Confidence-guided prediction and trading: we introduce the regularization loss to address market prediction uncertainty for the index prediction and design the rule-based trading policies based on the confidence. Extensive experiments across multiple stock markets and indices demonstrate that Cubic consistently outperforms state-of-the-art baselines in stock index prediction tasks, achieving superior performance on both forecasting accuracy metrics and downstream trading profitability.

Large language models (LLMs) have enabled agents to perform complex reasoning and decision-making through free-form language interactions. However, in open-ended language action environments (e.g., negotiation or question-asking games), the action space can be formulated as a joint distribution over tokens, resulting in an exponentially large action space. Sampling actions in such a space can lead to extreme reward sparsity, which brings large reward variance, hindering effective reinforcement learning (RL). To address this, we propose ARIA, a method that Aggregates Rewards in Intention space to enable efficient and effective language Agents training. ARIA aims to project natural language actions from the high-dimensional joint token distribution space into a low-dimensional intention space, where semantically similar actions are clustered and assigned shared rewards. This intention-aware reward aggregation reduces reward variance by densifying reward signals, fostering better policy optimization. Extensive experiments demonstrate that ARIA not only significantly reduces policy gradient variance, but also delivers substantial performance gains of an average of 9.95% across four downstream tasks, consistently outperforming offline and online RL baselines.

Missing data appears when parts of the data are not available for a given variable or a given observation. It is an ubiquitous problem in a wide range of scientific disciplines, including sensor networks, geophysical data analysis, radar and image processing, remote sensing, ecological statistics and biomedical studies, just to name a few [1]-[5]. Signal processing is no exception to the rule, where missing data mainly come from sensor malfunction, hidden or impossible measurements, human errors and natural hazards, all of which can hinder a thorough understanding, analysis, and interpretation of the signal. One of the earliest work on missing data was published in 1932 by Wilks, who mentioned the need to extract as much information as possible from fragmentary answers of questionnaires in social sciences and government statistics. Therefore, it is not surprising that the first discipline to witness this issue was mathematical statistics. This led Wilks to derive efficient estimators for the parameters of a normal bivariate distribution when the data contain missing values [6]. This work was extended to the multivariate case by Lord in 1955 [7]. Since the early 1970's, the literature in missing data has flourished with the development of computational capacity, leading to major developments in signal processing and its related fields, such as statistical inference [2], data analysis [8] and machine learning [9]. In particular, the formulation of a missing-data theory framework by Rubin in [10], which describes the relation between missingness and data values in the so-called missing-data mechanisms, has allowed tremendous advancements in statistical analysis. Therefore, a tutorial paper aiming to summarize the existing and novel strategies in the SP & ML literature addressing various problems related to missing data, such as parameter estimation, matrix completion, missing data imputation and learning with missing values, as well as showing their potential applications, is an urgent desideratum. This tutorial aims to provide practitioners with vital tools, in an accessible way, to answer the question: How to deal with missing data? There are many strategies to handle incomplete signals.