Effective pronunciation feedback is critical in second language (L2) learning, for which computer-assisted pronunciation training (CAPT) systems often encompass two key tasks: automatic pronunciation assessment (AP A) and mispronunciation detection and diagnosis (MDD). Recent work has shown that joint modeling of these two tasks can yield mutual benefits. Our unified framework leverages Mamba, a selective state space model (SSM), while integrating phonological features and think token strategies to jointly enhance interpretability and fine-grained temporal reasoning in AP A and MDD. To our knowledge, this is the first study to combine phonological attribution, SSM-based modeling, and prompting in CAPT. A series of experiments conducted on the speechocean762 benchmark demonstrate that our model consistently outperforms prior methods, particularly on the MDD task.

Pioneered by the foundational information theory by Claude Shannon and the visionary framework of machine intelligence by Alan Turing, the convergent evolution of information and communication technologies (IT/CT) has created an unbroken wave of connectivity and computation. This synergy has sparked a technological revolution, now reaching its peak with large artificial intelligence (AI) models that are reshaping industries and redefining human-machine collaboration. However, the realization of ubiquitous intelligence faces considerable challenges due to substantial resource consumption in large models and high communication bandwidth demands. To address these challenges, AI Flow has been introduced as a multidisciplinary framework that integrates cutting-edge IT and CT advancements, with a particular emphasis on the following three key points. First, device-edge-cloud framework serves as the foundation, which integrates end devices, edge servers, and cloud clusters to optimize scalability and efficiency for low-latency model inference. Second, we introduce the concept of familial models, which refers to a series of different-sized models with aligned hidden features, enabling effective collaboration and the flexibility to adapt to varying resource constraints and dynamic scenarios. Third, connectivity- and interaction-based intelligence emergence is a novel paradigm of AI Flow. By leveraging communication networks to enhance connectivity, the collaboration among AI models across heterogeneous nodes achieves emergent intelligence that surpasses the capability of any single model. The innovations of AI Flow provide enhanced intelligence, timely responsiveness, and ubiquitous accessibility to AI services, paving the way for the tighter fusion of AI techniques and communication systems.

We propose a novel framework that harnesses the power of generative artificial intelligence and copula-based modeling to address two critical challenges in multivariate time-series analysis: delivering accurate predictions and enabling robust anomaly detection. Our method, Copula-based Conformal Anomaly Identification for Multivariate Time-Series (CoCAI), leverages a diffusion-based model to capture complex dependencies within the data, enabling high quality forecasting. The model's outputs are further calibrated using a conformal prediction technique, yielding predictive regions which are statistically valid, i.e., cover the true target values with a desired confidence level. Starting from these calibrated forecasts, robust outlier detection is performed by combining dimensionality reduction techniques with copula-based modeling, providing a statistically grounded anomaly score. CoCAI benefits from an offline calibration phase that allows for minimal overhead during deployment and delivers actionable results rooted in established theoretical foundations. Empirical tests conducted on real operational data derived from water distribution and sewerage systems confirm CoCAI's effectiveness in accurately forecasting target sequences of data and in identifying anomalous segments within them.

Canonical correlation analysis (CCA) is a technique for finding correlated sets of features between two datasets. In this paper, we propose a novel extension of CCA to the online, streaming data setting: Sliding Window Informative Canonical Correlation Analysis (SWICCA). Our method uses a streaming principal component analysis (PCA) algorithm as a backend and uses these outputs combined with a small sliding window of samples to estimate the CCA components in real time. We motivate and describe our algorithm, provide numerical simulations to characterize its performance, and provide a theoretical performance guarantee. The SWICCA method is applicable and scalable to extremely high dimensions, and we provide a real-data example that demonstrates this capability.

Many signals in the real world that evolve in time can be modeled as a stochastic process with the signal randomly jumping from one state to another as time proceeds. When the signal can only exhibit a finite number of possible states, one can interpret the evolution of the signal as a random walk on a graph with vertices representing the states of the signal and edge weights giving way to the transition probabilities from one state to another. In particular, one arrives at a Markov chain representation of the signal that can be estimated using only the signal data. However, many realistic signals can take on a continuum of values, and so the goal of this work is to present a framework for modeling continuous-space stochastic signals and to identify metastable and coherent sets via clustering techniques. We present a data-driven method to learn the discrete-time transition probabilities of stochastic signals evolving in continuous space, which can be regarded as a generalization of the discrete space case considered in [25, 22]. The underlying theory is developed by evoking the concept of a graphon, which can be defined as the limit of sequences of dense networks that grow without bound [35, 34, 21, 18]. As recently shown in [43], graphons provide a well-developed framework for extending the concepts of random walks on finite graphs to stochastic processes evolving in continuous space. For example, random walks on graphs can be used to measure the centrality of vertices, and these concepts can also be extended to graphons [4]. Our goal is to identify transition probabilities, clusters, and the graphon itself from random walk data.

We introduce the microclustering Ewens--Pitman model for random partitions, obtained by scaling the strength parameter of the Ewens--Pitman model linearly with the sample size. The resulting random partition is shown to have the microclustering property, namely: the size of the largest cluster grows sub-linearly with the sample size, while the number of clusters grows linearly. By leveraging the interplay between the Ewens--Pitman random partition with the Pitman--Yor process, we develop efficient variational inference schemes for posterior computation in entity resolution. Our approach achieves a speed-up of three orders of magnitude over existing Bayesian methods for entity resolution, while maintaining competitive empirical performance.

Learning from non-stationary data streams subject to concept drift requires models that can adapt on-the-fly while remaining resource-efficient. Existing adaptive ensemble methods often rely on coarse-grained adaptation mechanisms or simple voting schemes that fail to optimally leverage specialized knowledge. This paper introduces DriftMoE, an online Mixture-of-Experts (MoE) architecture that addresses these limitations through a novel co-training framework. DriftMoE features a compact neural router that is co-trained alongside a pool of incremental Hoeffding tree experts. The key innovation lies in a symbiotic learning loop that enables expert specialization: the router selects the most suitable expert for prediction, the relevant experts update incrementally with the true label, and the router refines its parameters using a multi-hot correctness mask that reinforces every accurate expert. This feedback loop provides the router with a clear training signal while accelerating expert specialization. We evaluate DriftMoE's performance across nine state-of-the-art data stream learning benchmarks spanning abrupt, gradual, and real-world drifts testing two distinct configurations: one where experts specialize on data regimes (multi-class variant), and another where they focus on single-class specialization (task-based variant). Our results demonstrate that DriftMoE achieves competitive results with state-of-the-art stream learning adaptive ensembles, offering a principled and efficient approach to concept drift adaptation.

Alice Williams Department of Computer Science Central Washington University USA 0009 - 0001 - 6154 - 2407 Boris Kovalerchuk Department of Computer Science Central Washington University USA 0000 - 0002 - 0995 - 9539 Abstract -- The v isualization of multi - dimensional data with interpretable methods remains limited by ca pabilities for both high - dimensional lossless visualizations that do not suffer from occlusion and that are computationally capable by parameterized visualization . This paper proposes a low to high dimensional data supporting framework using lossless C oncentric C oordinates that a re a more compact generalization of Parallel Coordinate s along with former C ircular C oordinates . These are forms of the General Line Coordinate visualizations that can directly support machine learning algorithm visualization and facilitate human inter action . A. Motivation In many domains, accurate and interpretable classification models can be accurately visualized. However, in many other domains, this remains a long - standing and critical roadblock to deploy artificial intelligence and machine learning (AI/ML) models. This is critica l and challenging for high - risk tasks like healthcare diagnostics. Visualization of multidimensional (n - D) data classification is critical for three major reasons: (1) to speed up analysis of prediction accuracy, (2) to interpret/explain classifier predictions, and (3) to improve/modify the prediction model. B. Overview of Existing Methods AI/ ML tasks for high multi - dimensional (n - D) data are commonly approached with black - box deep - learning (DL) methods that inherently lack in i nterpretability and decision explanation. Further relying on explainability after model design as popularly done with either LIME or SHAP [ 7 ]. Moreover, visualization methods used commonly pre process data with dimensional reduction (DR) methods like Principal Component Analysis (PCA), t - Stochastic Neighbor Embedding (t - SNE), or other similar approximations. However, s uch methods are lossy and not reversible. Therefore, these methods commonly introduce visual ly verify inaccuracies in n - D. Alternatively, lossless visualizations allow for the use of Visual Knowledge Discovery (VKD) to visually discover algorithmic adjustments that improve ML prediction models [ 5 ] .

Transformer models have emerged as fundamental tools across various scientific and engineering disciplines, owing to their outstanding performance in diverse applications. Despite this empirical success, the theoretical foundations of Transformers remain relatively underdeveloped, particularly in understanding their training dynamics. Existing research predominantly examines isolated components--such as self-attention mechanisms and feedforward networks--without thoroughly investigating the interdependencies between these components, especially when residual connections are present. In this paper, we aim to bridge this gap by analyzing the convergence behavior of a structurally complete yet single-layer Transformer, comprising self-attention, a feedforward network, and residual connections. We demonstrate that, under appropriate initialization, gradient descent exhibits a linear convergence rate, where the convergence speed is determined by the minimum and maximum singular values of the output matrix from the attention layer. Moreover, our analysis reveals that residual connections serve to ameliorate the ill-conditioning of this output matrix, an issue stemming from the low-rank structure imposed by the softmax operation, thereby promoting enhanced optimization stability. We also extend our theoretical findings to a multi-layer Transformer architecture, confirming the linear convergence rate of gradient descent under suitable initialization. Empirical results corroborate our theoretical insights, illustrating the beneficial role of residual connections in promoting convergence stability.

The volatility and unpredictability of emerging technologies, such as artificial intelligence (AI), generate significant uncertainty, which is widely discussed on social media. This study examines anticipatory discourse surrounding technological futures by analysing 1.5 million posts from 400 key opinion leaders (KOLs) published on the X platform (from 2021 to 2023). Using advanced text mining techniques, including BERTopic modelling, sentiment, emotion, and attitude analyses, the research identifies 100 distinct topics reflecting anticipated tech-driven futures. Our findings emphasize the dual role of KOLs in framing \textit{present futures} -- optimistic visions of transformative technologies like AI and IoT -- and influencing \textit{future presents}, where these projections shape contemporary societal and geopolitical debates. Positive emotions such as Hope dominate, outweighing Anxiety, particularly in topics like ``Machine Learning, Data Science, and Deep Learning,'' while discussions around ``Climate Change'' and ``War, Ukraine, and Trump People'' elicit \textit{Anxiety}. By framing technologies as solutions to societal challenges, KOLs act as mediators of societal narratives, bridging imagined futures and current realities. These insights underscore their pivotal role in directing public attention with emerging technologies during periods of heightened uncertainty, advancing our understanding of anticipatory discourse in technology-mediated contexts.