The imperative of user privacy protection and regulatory compliance necessitates sensitive data removal in model training, yet this process often induces distributional shifts that undermine model performance-particularly in out-of-distribution (OOD) scenarios. We propose a novel data removal approach that enhances deep predictive models through factor decorrelation and loss perturbation. Our approach introduces: (1) a discriminative-preserving factor decorrelation module employing dynamic adaptive weight adjustment and iterative representation updating to reduce feature redundancy and minimize inter-feature correlations. (2) a smoothed data removal mechanism with loss perturbation that creates information-theoretic safeguards against data leakage during removal operations. Extensive experiments on five benchmark datasets show that our approach outperforms other baselines and consistently achieves high predictive accuracy and robustness even under significant distribution shifts. The results highlight its superior efficiency and adaptability in both in-distribution and out-of-distribution scenarios.

Transformers have proven highly effective across a wide range of modalities. However, the quadratic complexity of the standard softmax attention mechanism poses a fundamental barrier to scaling them to long context windows. A large body of work addresses this with linear attention, which reformulates attention as a kernel function and approximates it with finite feature maps to achieve linear-time computation. Orthogonal to computational scaling, most attention mechanisms -- both quadratic and linear -- produce row-normalized maps that can over-focus on a few tokens, degrading robustness and information flow. Enforcing doubly-stochastic attention alleviates this by balancing token participation across rows and columns, but existing doubly-stochastic attention mechanisms typically introduce substantial overhead, undermining scalability. We propose LOTFormer, a principled attention mechanism that is simultaneously linear-time and doubly-stochastic. Our approach exploits the connection between attention maps and transportation plans between query and key measures. The central idea is to constrain the transport plan to be low-rank by conditioning it on a learnable pivot measure with small support. Concretely, we solve two entropic optimal transport problems (queries $\to$ pivot and pivot $\to$ keys) and compose them into a conditional (glued) coupling. This yields an attention matrix that is provably doubly-stochastic, has rank at most $r \ll n$, and applies to values in $O(nr)$ time without forming the full $n \times n$ map. The pivot locations and masses are learned end-to-end. Empirically, LOTFormer achieves state-of-the-art results on the Long Range Arena benchmark, surpassing prior linear and transport-based attention methods in both accuracy and efficiency.

This paper proposes a novel community detection method that integrates the Louvain algorithm with Graph Neural Networks (GNNs), enabling the discovery of communities without prior knowledge. Compared to most existing solutions, the proposed method does not require prior knowledge of the number of communities. It enhances the Louvain algorithm using node embeddings generated by a GNN to capture richer structural and feature information. Furthermore, it introduces a merging algorithm to refine the results of the enhanced Louvain algorithm, reducing the number of detected communities. To the best of our knowledge, this work is the first one that improves the Louvain algorithm using GNNs for community detection. The improvement of the proposed method was empirically confirmed through an evaluation on real-world datasets. The results demonstrate its ability to dynamically adjust the number of detected communities and increase the detection accuracy in comparison with the benchmark solutions.

The Entropic Optimal Transport (EOT) problem and its dynamic counterpart, the Schrödinger bridge (SB) problem, play an important role in modern machine learning, linking generative modeling with optimal transport theory. While recent advances in discrete diffusion and flow models have sparked growing interest in applying SB methods to discrete domains, there is still no reliable way to evaluate how well these methods actually solve the underlying problem. We address this challenge by introducing a benchmark for SB on discrete spaces. Our construction yields pairs of probability distributions with analytically known SB solutions, enabling rigorous evaluation. As a byproduct of building this benchmark, we obtain two new SB algorithms, DLightSB and DLightSB-M, and additionally extend prior related work to construct the $α$-CSBM algorithm. We demonstrate the utility of our benchmark by evaluating both existing and new solvers in high-dimensional discrete settings. This work provides the first step toward proper evaluation of SB methods on discrete spaces, paving the way for more reproducible future studies.

We investigate the recovery dynamics of healthy cardiac activity after physical exertion using multimodal biosignals recorded with a polycardiograph. Multifractal features derived from the singularity spectrum capture the scale-invariant properties of cardiovascular regulation. Five supervised classification algorithms - Logistic Regression (LogReg), Suport Vector Machine with RBF kernel (SVM-RBF), k-Nearest Neighbors (kNN), Decision Tree (DT), and Random Forest (RF) - were evaluated to distinguish recovery states in a small, imbalanced dataset. Our results show that multifractal analysis, combined with multimodal sensing, yields reliable features for characterizing recovery and points toward nonlinear diagnostic methods for heart conditions.

Autonomous technology, which has become widespread today, appears in many different configurations such as mobile robots, manipulators, and drones. One of the most important tasks of these vehicles during autonomous operations is path planning. In the literature, path planners are generally divided into two categories: probabilistic and deterministic methods. In the analysis of probabilistic methods, the common problem of almost all methods is observed in narrow passage environments. In this paper, a novel sampler is proposed that deterministically identifies narrow passage environments using occupancy grid maps and accordingly increases the amount of sampling in these regions. The codes of the algorithm is provided as open source. To evaluate the performance of the algorithm, benchmark studies are conducted in three distinct categories: specific and random simulation environments, and a real-world environment. As a result, it is observed that our algorithm provides higher performance in planning time and number of milestones compared to the baseline samplers.

In many real-world regression tasks, the data distribution is heavily skewed, and models learn predominantly from abundant majority samples while failing to predict minority labels accurately. While imbalanced classification has been extensively studied, imbalanced regression remains relatively unexplored. Deep imbalanced regression (DIR) represents cases where the input data are high-dimensional and unstructured. Although several data-level approaches for tabular imbalanced regression exist, deep imbalanced regression currently lacks dedicated data-level solutions suitable for high-dimensional data and relies primarily on algorithmic modifications. To fill this gap, we propose LatentDiff, a novel framework that uses conditional diffusion models with priority-based generation to synthesize high-quality features in the latent representation space. LatentDiff is computationally efficient and applicable across diverse data modalities, including images, text, and other high-dimensional inputs. Experiments on three DIR benchmarks demonstrate substantial improvements in minority regions while maintaining overall accuracy.

Code switching, particularly between Korean and English, has become a defining feature of modern K-pop, reflecting both aesthetic choices and global market strategies. This paper is a primary investigation into the linguistic strategies employed in K-pop songs that achieve global chart success, with a focus on the role of code-switching and English lyric usage. A dataset of K-pop songs that appeared on the Billboard Hot 100 and Global 200 charts from 2017 to 2025, spanning 14 groups and 8 solo artists, was compiled. Using this dataset, the proportion of English and Korean lyrics, the frequency of code-switching, and other stylistic features were analysed. It was found that English dominates the linguistic landscape of globally charting K-pop songs, with both male and female performers exhibiting high degrees of code-switching and English usage. Statistical tests indicated no significant gender-based differences, although female solo artists tend to favour English more consistently. A classification task was also performed to predict performer gender from lyrics, achieving macro F1 scores up to 0.76 using multilingual embeddings and handcrafted features. Finally, differences between songs charting on the Hot 100 versus the Global 200 were examined, suggesting that, while there is no significant gender difference in English, higher English usage may be more critical for success in the US-focused Hot 100. The findings highlight how linguistic choices in K-pop lyrics are shaped by global market pressures and reveal stylistic patterns that reflect performer identity and chart context.

Test-time entropy minimization helps adapt a model to novel environments and incentivize its reasoning capability, unleashing the model's potential during inference by allowing it to evolve and improve in real-time using its own predictions, achieving promising performance. However, pure entropy minimization can favor non-generalizable shortcuts, such as inflating the logit norm and driving all predictions to a dominant class to reduce entropy, risking collapsed solutions (e.g., constant one-hot outputs) that trivially minimize the objective without meaningful learning. In this paper, we introduce ZeroSiam, an efficient asymmetric Siamese architecture tailored for test-time entropy minimization. ZeroSiam prevents collapse through asymmetric divergence alignment, which is efficiently achieved by a learnable predictor and a stop-gradient operator before the classifier. We provide empirical and theoretical evidence that ZeroSiam not only prevents collapse solutions, but also absorbs and regularizes biased learning signals, enhancing performance even when no collapse occurs. Despite its simplicity, extensive results show that ZeroSiam performs more stably over prior methods using negligible overhead, demonstrating efficacy on both vision adaptation and large language model reasoning tasks across challenging test scenarios and diverse models, including tiny models that are particularly collapse-prone.

Tabular data are central to many applications, especially longitudinal data in healthcare, where missing values are common, undermining model fidelity and reliability. Prior imputation methods either impose restrictive assumptions or struggle with complex cross-feature structure, while recent generative approaches suffer from instability and costly inference. We propose Impute-MACFM, a mask-aware conditional flow matching framework for tabular imputation that addresses missingness mechanisms, missing completely at random, missing at random, and missing not at random. Its mask-aware objective builds trajectories only on missing entries while constraining predicted velocity to remain near zero on observed entries, using flexible nonlinear schedules. Impute-MACFM combines: (i) stability penalties on observed positions, (ii) consistency regularization enforcing local invariance, and (iii) time-decayed noise injection for numeric features. Inference uses constraint-preserving ordinary differential equation integration with per-step projection to fix observed values, optionally aggregating multiple trajectories for robustness. Across diverse benchmarks, Impute-MACFM achieves state-of-the-art results while delivering more robust, efficient, and higher-quality imputation than competing approaches, establishing flow matching as a promising direction for tabular missing-data problems, including longitudinal data.