A fundamental challenge in robust visual-inertial odometry (VIO) is to dynamically assess the reliability of sensor measurements. This assessment is crucial for properly weighting the contribution of each measurement to the state estimate. Conventional methods often simplify this by assuming a static, uniform uncertainty for all measurements. This heuristic, however, may be limited in its ability to capture the dynamic error characteristics inherent in real-world data. To improve this limitation, we present a statistical framework that learns measurement reliability assessment online, directly from sensor data and optimization results. Our approach leverages multi-view geometric consistency as a form of self-supervision. This enables the system to infer landmark uncertainty and adaptively weight visual measurements during optimization. We evaluated our method on the public EuRoC dataset, demonstrating improvements in tracking accuracy with average reductions of approximately 24\% in translation error and 42\% in rotation error compared to baseline methods with fixed uncertainty parameters. The resulting framework operates in real time while showing enhanced accuracy and robustness. To facilitate reproducibility and encourage further research, the source code will be made publicly available.

Recent advances in computer vision have made training object detectors more efficient and effective; however, assessing their performance in real-world applications still relies on costly manual annotation. To address this limitation, we develop an automated model evaluation (AutoEval) framework for object detection. We propose Prediction Consistency and Reliability (PCR), which leverages the multiple candidate bounding boxes that conventional detectors generate before non-maximum suppression (NMS). PCR estimates detection performance without ground-truth labels by jointly measuring 1) the spatial consistency between boxes before and after NMS, and 2) the reliability of the retained boxes via the confidence scores of overlapping boxes. For a more realistic and scalable evaluation, we construct a meta-dataset by applying image corruptions of varying severity. Experimental results demonstrate that PCR yields more accurate performance estimates than existing AutoEval methods, and the proposed meta-dataset covers a wider range of detection performance. The code is available at https://github.com/YonseiML/autoeval-det.

Reliable risk identification based on driver behavior data underpins real-time safety feedback, fleet risk management, and evaluation of driver-assist systems. While naturalistic driving studies have become foundational for providing real-world driver behavior data, the existing frameworks for identifying risk based on such data have two fundamental limitations: (i) they rely on predefined time windows and fixed thresholds to disentangle risky and normal driving behavior, and (ii) they assume behavior is stationary across drivers and time, ignoring heterogeneity and temporal drift. In practice, these limitations can lead to timing errors and miscalibration in alerts, weak generalization to new drivers/routes/conditions, and higher false-alarm and miss rates, undermining driver trust and reducing safety intervention effectiveness. To address this gap, we propose a unified, context-aware framework that adapts labels and models over time and across drivers via rolling windows, joint optimization, dynamic calibration, and model fusion, tailored for time-stamped kinematic data. The framework is tested using two safety indicators, speed-weighted headway and harsh driving events, and three models: Random Forest, XGBoost, and Deep Neural Network (DNN). Speed-weighted headway yielded more stable and context-sensitive classifications than harsh-event counts. XGBoost maintained consistent performance under changing thresholds, whereas DNN achieved higher recall at lower thresholds but with greater variability across trials. The ensemble aggregated signals from multiple models into a single risk decision, balancing responsiveness to risky behavior with control of false alerts. Overall, the framework shows promise for adaptive, context-aware risk detection that can enhance real-time safety feedback and support driver-focused interventions in intelligent transportation systems.

Understanding and quantifying chaos from data remains challenging. We present a data-driven method for estimating the largest Lyapunov exponent (LLE) from one-dimensional chaotic time series using machine learning. A predictor is trained to produce out-of-sample, multi-horizon forecasts; the LLE is then inferred from the exponential growth of the geometrically averaged forecast error (GMAE) across the horizon, which serves as a proxy for trajectory divergence. We validate the approach on four canonical 1D maps-logistic, sine, cubic, and Chebyshev-achieving R2pos > 0.99 against reference LLE curves with series as short as M = 450. Among baselines, KNN yields the closest fits (KNN-R comparable; RF larger deviations). By design the estimator targets positive exponents: in periodic/stable regimes it returns values indistinguishable from zero. Noise robustness is assessed by adding zero-mean white measurement noise and summarizing performance versus the average SNR over parameter sweeps: accuracy saturates for SNRm > 30 dB and collapses below 27 dB, a conservative sensor-level benchmark. The method is simple, computationally efficient, and model-agnostic, requiring only stationarity and the presence of a dominant positive exponent. It offers a practical route to LLE estimation in experimental settings where only scalar time-series measurements are available, with extensions to higher-dimensional and irregularly sampled data left for future work.

ABSTRACT Research on long-term time series prediction has primarily relied on Transformer and MLP models, while the potential of convolutional networks in this domain remains under-explored. To address this, we propose a novel multi-scale time series reshape module that effectively captures cross-period patch interactions and variable dependencies. Building on this, we develop MS-DFTVNet, the multi-scale 3D deformable convolutional framework tailored for long-term forecasting. Moreover, to handle the inherently uneven distribution of temporal features, we introduce a context-aware dynamic deformable convolution mechanism, which further enhances the model's ability to capture complex temporal patterns. Extensive experiments demonstrate that MS-DFTVNet not only significantly outperforms strong baselines but also achieves an average improvement of about 7.5% across six public datasets, setting new state-of-the-art results.

We study gradient-based data attribution, aiming to identify which training examples most influence a given output. Existing methods for this task either treat network parameters uniformly or rely on implicit weighting derived from Hessian approximations, which do not fully model functional heterogeneity of network parameters. To address this, we propose a method to explicitly learn parameter importance weights directly from data, without requiring annotated labels. Our approach improves attribution accuracy across diverse tasks, including image classification, language modeling, and diffusion, and enables fine-grained attribution for concepts like subject and style.

Forest fire prediction involves estimating the likelihood of fire ignition or related risk levels in a specific area over a defined time period. With climate change intensifying fire behavior and frequency, accurate prediction has become one of the most pressing challenges in Artificial Intelligence (AI). Traditionally, fire ignition is approached as a binary classification task in the literature. However, this formulation oversimplifies the problem, especially from the perspective of end-users such as firefighters. In general, as is the case in France, firefighting units are organized by department, each with its terrain, climate conditions, and historical experience with fire events. Consequently, fire risk should be modeled in a way that is sensitive to local conditions and does not assume uniform risk across all regions. This paper proposes a new approach that tailors fire risk assessment to departmental contexts, offering more actionable and region-specific predictions for operational use. With this, we present the first national-scale AI benchmark for metropolitan France using state-of-the-art AI models on a relatively unexplored dataset. Finally, we offer a summary of important future works that should be taken into account. Supplementary materials are available on GitHub.

Recently, a trend has emerged that favors shifting away from designing constrained equivariant architectures for data in geometric domains and instead (1) modifying the training protocol, e.g., with a specific loss and data augmentations (soft equivariance), or (2) ignoring equivariance and inferring it only implicitly. However, both options have limitations, e.g., soft equivariance still requires a priori knowledge about the underlying symmetries, while implicitly learning equivariance from data lacks interpretability. To address these limitations, we propose SEMoLA, an end-to-end approach that jointly (1) discovers a priori unknown symmetries in the data via learnable data augmentations, and uses them to (2) encode the respective approximate equivariance into arbitrary unconstrained models. Hence, it enables learning equivariant models that do not need prior knowledge about symmetries, offer interpretability, and maintain robustness to distribution shifts. Empirically, we demonstrate the ability of SEMoLA to robustly discover relevant symmetries while achieving high prediction performance across various datasets, encompassing multiple data modalities and underlying symmetry groups.

We present BiasLab, a dataset of 300 political news articles annotated for perceived ideological bias. These articles were selected from a curated 900-document pool covering diverse political events and source biases. Each article is labeled by crowdworkers along two independent scales, assessing sentiment toward the Democratic and Republican parties, and enriched with rationale indicators. The annotation pipeline incorporates targeted worker qualification and was refined through pilot-phase analysis. We quantify inter-annotator agreement, analyze misalignment with source-level outlet bias, and organize the resulting labels into interpretable subsets. Additionally, we simulate annotation using schema-constrained GPT-4o, enabling direct comparison to human labels and revealing mirrored asymmetries, especially in misclassifying subtly right-leaning content. We define two modeling tasks: perception drift prediction and rationale type classification, and report baseline performance to illustrate the challenge of explainable bias detection. BiasLab's rich rationale annotations provide actionable interpretations that facilitate explainable modeling of political bias, supporting the development of transparent, socially aware NLP systems. We release the dataset, annotation schema, and modeling code to encourage research on human-in-the-loop interpretability and the evaluation of explanation effectiveness in real-world settings.

Black-box optimization (BBO) aims to find the solution of an optimization problem where the objective function is unknown or lacks an explicit mathematical formulation. Instead, the function can only be evaluated through queries, such as physical experiments or simulations through complex computational models. However, in many real-world scenarios, these evaluations are expensive, noisy, or time-consuming. Therefore, a key goal of black-box optimization is to find near-optimal solutions while limiting the number of costly function evaluations. Due to these challenges, BBO relies on sample-efficient strategies that select query points to balance exploration (searching unexplored regions) and exploitation (refining promising solutions).