The training dynamics of neural networks have attracted significant attention in deep learning theory. It has been suggested that the dynamics induced by training algorithms strongly influence the generalization performance of neural networks. This effect is captured in the idea of implicit bias (Neyshabur et al., 2014), in which the algorithm selects a certain solution among many induced by nonconvexity of the loss and overparametrization of networks. Accordingly, many recent works have studied the interplay between models and optimizers, aiming to characterize the resulting implicit biases (Neyshabur, 2017; Soudry et al., 2018; Arora et al., 2019; Bartlett et al., 2021). Moreover, understanding the convergence speed and timescales of the training dynamics contributes to efficient training of high-performance models in practice, especially in the context of modern large-scale neural networks in which the training is stopped at a compute-optimal point (Kaplan et al., 2020).

This paper analyzes the generalization error of minimum-norm interpolating solutions in linear regression using spiked covariance data models. The paper characterizes how varying spike strengths and target-spike alignments can affect risk, especially in overparameterized settings. The study presents an exact expression for the generalization error, leading to a comprehensive classification of benign, tempered, and catastrophic overfitting regimes based on spike strength, the aspect ratio $c=d/n$ (particularly as $c \to \infty$), and target alignment. Notably, in well-specified aligned problems, increasing spike strength can surprisingly induce catastrophic overfitting before achieving benign overfitting. The paper also reveals that target-spike alignment is not always advantageous, identifying specific, sometimes counterintuitive, conditions for its benefit or detriment. Alignment with the spike being detrimental is empirically demonstrated to persist in nonlinear models.

Standard discrete diffusion models treat all unobserved states identically by mapping them to an absorbing [MASK] token. This creates an 'information void' where semantic information that could be inferred from unmasked tokens is lost between denoising steps. We introduce Continuously Augmented Discrete Diffusion (CADD), a framework that augments the discrete state space with a paired diffusion in a continuous latent space. This yields graded, gradually corrupted states in which masked tokens are represented by noisy yet informative latent vectors rather than collapsed 'information voids'. At each reverse step, CADD may leverage the continuous latent as a semantic hint to guide discrete denoising. The design is clean and compatible with existing discrete diffusion training. At sampling time, the strength and choice of estimator for the continuous latent vector enables a controlled trade-off between mode-coverage (generating diverse outputs) and mode-seeking (generating contextually precise outputs) behaviors. Empirically, we demonstrate CADD improves generative quality over mask-based diffusion across text generation, image synthesis, and code modeling, with consistent gains on both qualitative and quantitative metrics against strong discrete baselines.

Linking textual values in tabular data to their corresponding entities in a Knowledge Base is a core task across a variety of data integration and enrichment applications. Although Large Language Models (LLMs) have shown State-of-The-Art performance in Entity Linking (EL) tasks, their deployment in real-world scenarios requires not only accurate predictions but also reliable uncertainty estimates, which require resource-demanding multi-shot inference, posing serious limits to their actual applicability. As a more efficient alternative, we investigate a self-supervised approach for estimating uncertainty from single-shot LLM outputs using token-level features, reducing the need for multiple generations. Evaluation is performed on an EL task on tabular data across multiple LLMs, showing that the resulting uncertainty estimates are highly effective in detecting low-accuracy outputs. This is achieved at a fraction of the computational cost, ultimately supporting a cost-effective integration of uncertainty measures into LLM-based EL workflows. The method offers a practical way to incorporate uncertainty estimation into EL workflows with limited computational overhead.

This work focuses on visualizing uncertainty of local divergence of two-dimensional vector fields. Divergence is one of the fundamental attributes of fluid flows, as it can help domain scientists analyze potential positions of sources (positive divergence) and sinks (negative divergence) in the flow. However, uncertainty inherent in vector field data can lead to erroneous divergence computations, adversely impacting downstream analysis. While Monte Carlo (MC) sampling is a classical approach for estimating divergence uncertainty, it suffers from slow convergence and poor scalability with increasing data size and sample counts. Thus, we present a two-fold contribution that tackles the challenges of slow convergence and limited scalability of the MC approach. (1) We derive a closed-form approach for highly efficient and accurate uncertainty visualization of local divergence, assuming independently Gaussian-distributed vector uncertainties. (2) We further integrate our approach into Viskores, a platform-portable parallel library, to accelerate uncertainty visualization. In our results, we demonstrate significantly enhanced efficiency and accuracy of our serial analytical (speed-up up to 1946X) and parallel Viskores (speed-up up to 19698X) algorithms over the classical serial MC approach. We also demonstrate qualitative improvements of our probabilistic divergence visualizations over traditional mean-field visualization, which disregards uncertainty. We validate the accuracy and efficiency of our methods on wind forecast and ocean simulation datasets.

With over 2,000 languages and potentially millions of speakers, Africa represents one of the richest linguistic regions in the world. Yet, this diversity is scarcely reflected in state-of-the-art natural language processing (NLP) systems and large language models (LLMs), which predominantly support a narrow set of high-resource languages. This exclusion not only limits the reach and utility of modern NLP technologies but also risks widening the digital divide across linguistic communities. Nevertheless, NLP research on African languages is active and growing. In recent years, there has been a surge of interest in this area, driven by several factors-including the creation of multilingual language resources, the rise of community-led initiatives, and increased support through funding programs. In this survey, we analyze 884 research papers on NLP for African languages published over the past five years, offering a comprehensive overview of recent progress across core tasks. We identify key trends shaping the field and conclude by outlining promising directions to foster more inclusive and sustainable NLP research for African languages.

While recent years have seen remarkable progress in music generation models, research on their biases across countries, languages, cultures, and musical genres remains underexplored. This gap is compounded by the lack of datasets and benchmarks that capture the global diversity of music. To address these challenges, we introduce GlobalDISCO, a large-scale dataset consisting of 73k music tracks generated by state-of-the-art commercial generative music models, along with paired links to 93k reference tracks in LAION-DISCO-12M. The dataset spans 147 languages and includes musical style prompts extracted from MusicBrainz and Wikipedia. The dataset is globally balanced, representing musical styles from artists across 79 countries and five continents. Our evaluation reveals large disparities in music quality and alignment with reference music between high-resource and low-resource regions. Furthermore, we find marked differences in model performance between mainstream and geographically niche genres, including cases where models generate music for regional genres that more closely align with the distribution of mainstream styles.

Malaria remains a major public health concern in Ethiopia, particularly in the Amhara Region, where seasonal and unpredictable transmission patterns make prevention and control challenging. Accurately forecasting malaria outbreaks is essential for effective resource allocation and timely interventions. This study proposes a hybrid predictive modeling framework that combines time-series forecasting, multi-output regression, and conventional regression-based prediction to forecast the incidence of malaria. Environmental variables, past malaria case data, and demographic information from Amhara Region health centers were used to train and validate the models. The multi-output regression approach enables the simultaneous prediction of multiple outcomes, including Plasmodium species-specific cases, temporal trends, and spatial variations, whereas the hybrid framework captures both seasonal patterns and correlations among predictors. The proposed model exhibits higher prediction accuracy than single-method approaches, exposing hidden patterns and providing valuable information to public health authorities. This study provides a valid and repeatable malaria incidence prediction framework that can support evidence-based decision-making, targeted interventions, and resource optimization in endemic areas.

Large Language Models (LLMs) powered with argentic capabilities are able to do knowledge-intensive tasks without human involvement. A prime example of this tool is Deep research with the capability to browse the web, extract information and generate multi-page reports. In this work, we introduce an evaluation sheet that can be used for assessing the capability of Deep Research tools. In addition, we selected academic survey writing as a use case task and evaluated output reports based on the evaluation sheet we introduced. Our findings show the need to have carefully crafted evaluation standards. The evaluation done on OpenAI`s Deep Search and Google's Deep Search in generating an academic survey showed the huge gap between search engines and standalone Deep Research tools, the shortcoming in representing the targeted area.

In response to the recent safety probing for OpenAI's GPT-OSS-20b model, we present a summary of a set of vulnerabilities uncovered in the model, focusing on its performance and safety alignment in a low-resource language setting. The core motivation for our work is to question the model's reliability for users from underrepresented communities. Using Hausa, a major African language, we uncover biases, inaccuracies, and cultural insensitivities in the model's behaviour. With a minimal prompting, our red-teaming efforts reveal that the model can be induced to generate harmful, culturally insensitive, and factually inaccurate content in the language. As a form of reward hacking, we note how the model's safety protocols appear to relax when prompted with polite or grateful language, leading to outputs that could facilitate misinformation and amplify hate speech. For instance, the model operates on the false assumption that common insecticide locally known as Fiya-Fiya (Cyphermethrin) and rodenticide like Shinkafar Bera (a form of Aluminium Phosphide) are safe for human consumption. To contextualise the severity of this error and popularity of the substances, we conducted a survey (n=61) in which 98% of participants identified them as toxic. Additional failures include an inability to distinguish between raw and processed foods and the incorporation of demeaning cultural proverbs to build inaccurate arguments. We surmise that these issues manifest through a form of linguistic reward hacking, where the model prioritises fluent, plausible-sounding output in the target language over safety and truthfulness. We attribute the uncovered flaws primarily to insufficient safety tuning in low-resource linguistic contexts. By concentrating on a low-resource setting, our approach highlights a significant gap in current red-teaming effort and offer some recommendations.