Weak-to-strong generalization, where a student model trained on imperfect labels generated by a weaker teacher nonetheless surpasses that teacher, has been widely observed but the mechanisms that enable it have remained poorly understood. In this paper, through a theoretical analysis of simple models, we uncover three core mechanisms that can drive this phenomenon. First, by analyzing ridge regression, we study the interplay between the teacher and student regularization and prove that a student can compensate for a teacher's under-regularization and achieve lower test error. We also analyze the role of the parameterization regime of the models. Second, by analyzing weighted ridge regression, we show that a student model with a regularization structure more aligned to the target, can outperform its teacher. Third, in a nonlinear multi-index setting, we demonstrate that a student can learn easy, task-specific features from the teacher while leveraging its own broader pre-training to learn hard-to-learn features that the teacher cannot capture.

Perovskite solar cells (PSCs) without a hole transport layer (HTL) offer a cost-effective and stable alternative to conventional architectures, utilizing only an absorber layer and an electron transport layer (ETL). This study presents a machine learning (ML)-driven framework to optimize the efficiency and stability of HTL-free PSCs by integrating experimental validation with numerical simulations. Excellent agreement is achieved between a fabricated device and its simulated counterpart at a molar fraction \( x = 68.7\% \) in \(\mathrm{MAPb}_{1-x}\mathrm{Sb}_{2x/3}\mathrm{I}_3\), where MA is methylammonium. A dataset of 1650 samples is generated by varying molar fraction, absorber defect density, thickness, and ETL doping, with corresponding efficiency and 50-hour degradation as targets. A fourth-degree polynomial regressor (PR-4) shows the best performance, achieving RMSEs of 0.0179 and 0.0117, and \( R^2 \) scores of 1 and 0.999 for efficiency and degradation, respectively. The derived model generalizes beyond the training range and is used in an L-BFGS-B optimization algorithm with a weighted objective function to maximize efficiency and minimize degradation. This improves device efficiency from 13.7\% to 16.84\% and reduces degradation from 6.61\% to 2.39\% over 1000 hours. Finally, the dataset is labeled into superior and inferior classes, and a multilayer perceptron (MLP) classifier achieves 100\% accuracy, successfully identifying optimal configurations.

This paper considers a challenging problem of identifying a causal graphical model under the presence of latent variables. While various identifiability conditions have been proposed in the literature, they often require multiple pure children per latent variable or restrictions on the latent causal graph. Furthermore, it is common for all observed variables to exhibit the same modality. Consequently, the existing identifiability conditions are often too stringent for complex real-world data. We consider a general nonparametric measurement model with arbitrary observed variable types and binary latent variables, and propose a double triangular graphical condition that guarantees identifiability of the entire causal graphical model. The proposed condition significantly relaxes the popular pure children condition. We also establish necessary conditions for identifiability and provide valuable insights into fundamental limits of identifiability. Simulation studies verify that latent structures satisfying our conditions can be accurately estimated from data.

Future link prediction on temporal graphs is a fundamental task with wide applicability in real-world dynamic systems. These scenarios often involve both recurring (seen) and novel (unseen) interactions, requiring models to generalize effectively across both types of edges. However, existing methods typically rely on complex memory and aggregation modules, yet struggle to handle unseen edges. In this paper, we revisit the architecture of existing temporal graph models and identify two essential but overlooked modeling requirements for future link prediction: representing nodes with unique identifiers and performing target-aware matching between source and destination nodes. To this end, we propose Cross-Attention based Future Link Predictor on Temporal Graphs (CRAFT), a simple yet effective architecture that discards memory and aggregation modules and instead builds on two components: learnable node embeddings and cross-attention between the destination and the source's recent interactions. This design provides strong expressive power and enables target-aware modeling of the compatibility between candidate destinations and the source's interaction patterns. Extensive experiments on diverse datasets demonstrate that CRAFT consistently achieves superior performance with high efficiency, making it well-suited for large-scale real-world applications.

In this paper, we introduce the first publicly available English-Kpelle dataset for machine translation, comprising over 2000 sentence pairs drawn from everyday communication, religious texts, and educational materials. By fine-tuning Meta's No Language Left Behind(NLLB) model on two versions of the dataset, we achieved BLEU scores of up to 30 in the Kpelle-to-English direction, demonstrating the benefits of data augmentation. Our findings align with NLLB-200 benchmarks on other African languages, underscoring Kpelle's potential for competitive performance despite its low-resource status. Beyond machine translation, this dataset enables broader NLP tasks, including speech recognition and language modelling. We conclude with a roadmap for future dataset expansion, emphasizing orthographic consistency, community-driven validation, and interdisciplinary collaboration to advance inclusive language technology development for Kpelle and other low-resourced Mande languages.

Generative Artificial Intelligence (AI) systems currently contribute negatively to the production of digital waste, via the associated energy consumption and the related CO2 emissions. At this moment, a discussion is urgently needed on the replication of harmful consumer behavior, such as overconsumption, in the digital space. We outline our previous work on the climate implications of commercially available generative AI systems and the sentiment of generative AI users when confronted with AI-related climate research. We expand on this work via a discussion of digital overconsumption and waste, other related societal impacts, and a possible solution pathway

Climate policy scenario generation and evaluation have traditionally relied on integrated assessment models (IAMs) and expert-driven qualitative analysis. These methods enable stakeholders, such as policymakers and researchers, to anticipate impacts, plan governance strategies, and develop mitigation measures. However, traditional methods are often time-intensive, reliant on simple extrapolations of past trends, and limited in capturing the complex and interconnected nature of energy and climate issues. With the advent of artificial intelligence (AI), particularly generative AI models trained on vast datasets, these limitations can be addressed, ensuring robustness even under limited data conditions. In this work, we explore the novel method that employs generative AI, specifically large language models (LLMs), to simulate climate policy scenarios for Sub-Saharan Africa. These scenarios focus on energy transition themes derived from the historical United Nations Climate Change Conference (COP) documents. By leveraging generative models, the project aims to create plausible and diverse policy scenarios that align with regional climate goals and energy challenges. Given limited access to human evaluators, automated techniques were employed for scenario evaluation. We generated policy scenarios using the llama3.2-3B model. Of the 34 generated responses, 30 (88%) passed expert validation, accurately reflecting the intended impacts provided in the corresponding prompts. We compared these validated responses against assessments from a human climate expert and two additional LLMs (gemma2-2B and mistral-7B). Our structured, embedding-based evaluation framework shows that generative AI effectively generate scenarios that are coherent, relevant, plausible, and diverse. This approach offers a transformative tool for climate policy planning in data-constrained regions.

Detecting anomalies in radio astronomy is challenging due to the vast amounts of data and the rarity of labeled anomalous examples. Addressing this challenge requires efficient methods capable of identifying unusual radio galaxy morphologies without relying on extensive supervision. This work introduces an innovative approach to anomaly detection based on morphological characteristics of the radio sources using trainable COSFIRE (Combination of Shifted Filter Responses) filters as an efficient alternative to complex deep learning methods. The framework integrates COSFIRE descriptors with an unsupervised Local Outlier Factor (LOF) algorithm to identify unusual radio galaxy morphologies. Evaluations on a radio galaxy benchmark data set demonstrate strong performance, with the COSFIRE-based approach achieving a geometric mean (G-Mean) score of 79%, surpassing the 77% achieved by a computationally intensive deep learning autoencoder. By characterizing normal patterns and detecting deviations, this semi-supervised methodology overcomes the need for anomalous examples in the training set, a major limitation of traditional supervised methods. This approach shows promise for next-generation radio telescopes, where fast processing and the ability to discover unknown phenomena are crucial.

Researchers working on low-resource languages face persistent challenges due to limited data availability and restricted access to computational resources. Although most large language models (LLMs) are predominantly trained in high-resource languages, adapting them to low-resource contexts, particularly African languages, requires specialized techniques. Several strategies have emerged for adapting models to low-resource languages in todays LLM landscape, defined by multi-stage pre-training and post-training paradigms. However, the most effective approaches remain uncertain. This work systematically investigates which adaptation strategies yield the best performance when extending existing LLMs to African languages. We conduct extensive experiments and ablation studies to evaluate different combinations of data types (translated versus synthetically generated), training stages (pre-training versus post-training), and other model adaptation configurations. Our experiments focuses on mathematical reasoning tasks, using the Llama 3.1 model family as our base model.

Large Language Models (LLMs) have the potential to transform humanities and social science research, yet their history knowledge and comprehension at a graduate level remains untested. Benchmarking LLMs in history is particularly challenging, given that human knowledge of history is inherently unbalanced, with more information available on Western history and recent periods. We introduce the History Seshat Test for LLMs (HiST-LLM), based on a subset of the Seshat Global History Databank, which provides a structured representation of human historical knowledge, containing 36,000 data points across 600 historical societies and over 2,700 scholarly references. This dataset covers every major world region from the Neolithic period to the Industrial Revolution and includes information reviewed and assembled by history experts and graduate research assistants. We find that, in a four-choice format, LLMs have a balanced accuracy ranging from 33.6% (Llama-3.1-8B)