The performance of large language models (LLMs) is deeply influenced by the quality and composition of their training data. While much of the existing work has centered on English, there remains a gap in understanding how to construct effective training corpora for other languages. We explore scalable methods for building web-based corpora for LLMs. We apply them to build a new 120B token corpus in Portuguese that achieves competitive results to an industrial-grade corpus. Using a continual pretraining setup, we study how different data selection and preprocessing strategies affect LLM performance when transitioning a model originally trained in English to another language. Our findings demonstrate the value of language-specific filtering pipelines, including classifiers for education, science, technology, engineering, and mathematics (STEM), as well as toxic content. We show that adapting a model to the target language leads to performance improvements, reinforcing the importance of high-quality, language-specific data. While our case study focuses on Portuguese, our methods are applicable to other languages, offering insights for multilingual LLM development.

The rise of misinformation underscores the need for scalable and reliable fact-checking solutions. Large language models (LLMs) hold promise in automating fact verification, yet their effectiveness across global contexts remains uncertain. We systematically evaluate nine established LLMs across multiple categories (open/closed-source, multiple sizes, diverse architectures, reasoning-based) using 5,000 claims previously assessed by 174 professional fact-checking organizations across 47 languages. Our methodology tests model generalizability on claims postdating training cutoffs and four prompting strategies mirroring both citizen and professional fact-checker interactions, with over 240,000 human annotations as ground truth. Findings reveal a concerning pattern resembling the Dunning-Kruger effect: smaller, accessible models show high confidence despite lower accuracy, while larger models demonstrate higher accuracy but lower confidence. This risks systemic bias in information verification, as resource-constrained organizations typically use smaller models. Performance gaps are most pronounced for non-English languages and claims originating from the Global South, threatening to widen existing information inequalities. These results establish a multilingual benchmark for future research and provide an evidence base for policy aimed at ensuring equitable access to trustworthy, AI-assisted fact-checking.

Swin Transformer achieved the best performance with 86% accuracy. LIME and Grad-CAM visual explanations were utilized for model in-terpretability. External validation with unseen images demonstrated strong generalization across conditions. A web-based diagnostic tool was developed for arsenic screening in rural communities. Abstract Background: Arsenicosis is a serious public health concern in South and Southeast Asia, primarily caused by long-term consumption of arsenic-contaminated water. Its early cutaneous manifestations are clinically significant but often underdiagnosed, particularly in rural areas with limited access to dermatologists. Automated, image-based diagnostic solutions can support early detection and timely interventions. Methods: In this study, we propose an end-to-end framework for arseni-cosis diagnosis using mobile phone-captured skin images. A dataset comprising 20 classes and over 11000 images of arsenic-induced and other dermatological conditions was curated. Multiple deep learning architectures, including convolutional neural networks (CNNs) and Transformer-based models, were benchmarked for arsenicosis detection. Model interpretability was integrated via LIME and Grad-CAM, while deployment feasibility was demonstrated through a web-based diagnostic tool. Results: Transformer-based models significantly outperformed CNNs, with the Swin Transformer achieving the best results (86% accuracy). LIME and Grad-CAM visualizations confirmed that the models attended to lesion-relevant regions, increasing clinical transparency and aiding in error analysis. The framework also demonstrated strong performance on external validation samples, confirming its ability to generalize beyond the curated dataset. Conclusion: The proposed framework demonstrates the potential of deep learning for non-invasive, accessible, and explainable diagnosis of arseni-Corresponding author: Asif Newaz, Email: eee.asifnewaz@iut-dhaka.edu cosis from mobile-acquired images. By enabling reliable image-based screening, it can serve as a practical diagnostic aid in rural and resource-limited communities, where access to dermatologists is scarce, thereby supporting early detection and timely intervention. Introduction Skin diseases are among the most common health problems worldwide, impacting millions of individuals across diverse populations. Globally, skin diseases represent a massive public health burden: recent estimates indicate that in 2021 alone, approximately 4.69 billion new cases were recorded, and skin conditions remain the fourth leading cause of non-fatal disease burden and among the top causes of disability worldwide [1]. These diseases range from mild infections to chronic and life-threatening disorders.

Post-training language models (LMs) with reinforcement learning (RL) can enhance their complex reasoning capabilities without supervised fine-tuning, as demonstrated by DeepSeek-R1-Zero. However, effectively utilizing RL for LMs requires significant parallelization to scale-up inference, which introduces non-trivial technical challenges (e.g. latency, memory, and reliability) alongside ever-growing financial costs. We present Swarm sAmpling Policy Optimization (SAPO), a fully decentralized and asynchronous RL post-training algorithm. SAPO is designed for decentralized networks of heterogenous compute nodes, where each node manages its own policy model(s) while "sharing" rollouts with others in the network; no explicit assumptions about latency, model homogeneity, or hardware are required and nodes can operate in silo if desired. As a result, the algorithm avoids common bottlenecks in scaling RL post-training while also allowing (and even encouraging) new possibilities. By sampling rollouts "shared" across the network, it enables "Aha moments" to propagate, thereby bootstrapping the learning process. In this paper we show SAPO achieved cumulative reward gains of up to 94% in controlled experiments. We also share insights from tests on a network with thousands of nodes contributed by Gensyn community members running the algorithm on diverse hardware and models during an open-source demo.

Event-based cameras are bio-inspired sensors with pixels that independently and asynchronously respond to brightness changes at microsecond resolution, offering the potential to handle state estimation tasks involving motion blur and high dynamic range (HDR) illumination conditions. However, the versatility of event-based visual odometry (VO) relying on handcrafted data association (either direct or indirect methods) is still unreliable, especially in field robot applications under low-light HDR conditions, where the dynamic range can be enormous and the signal-to-noise ratio is spatially-and-temporally varying. Leveraging deep neural networks offers new possibilities for overcoming these challenges. In this paper, we propose a learning-based stereo event visual odometry. Building upon Deep Event Visual Odometry (DEVO), our system (called Stereo-DEVO) introduces a novel and efficient static-stereo association strategy for sparse depth estimation with almost no additional computational burden. By integrating it into a tightly coupled bundle adjustment (BA) optimization scheme, and benefiting from the recurrent network's ability to perform accurate optical flow estimation through voxel-based event representations to establish reliable patch associations, our system achieves high-precision pose estimation in metric scale. In contrast to the offline performance of DEVO, our system can process event data of \zs{Video Graphics Array} (VGA) resolution in real time. Extensive evaluations on multiple public real-world datasets and self-collected data justify our system's versatility, demonstrating superior performance compared to state-of-the-art event-based VO methods. More importantly, our system achieves stable pose estimation even in large-scale nighttime HDR scenarios.

Human Activity Recognition (HAR) has seen significant advancements with the adoption of deep learning techniques, yet challenges remain in terms of data requirements, reliability and robustness. This paper explores a novel application of Ensemble Distribution Distillation (EDD) within a self-supervised learning framework for HAR aimed at overcoming these challenges. By leveraging unlabeled data and a partially supervised training strategy, our approach yields an increase in predictive accuracy, robust estimates of uncertainty, and substantial increases in robustness against adversarial perturbation; thereby significantly improving reliability in real-world scenarios without increasing computational complexity at inference. We demonstrate this with an evaluation on several publicly available datasets. The contributions of this work include the development of a self-supervised EDD framework, an innovative data augmentation technique designed for HAR, and empirical validation of the proposed method's effectiveness in increasing robustness and reliability.

Autonomous-driving research has recently embraced deep Reinforcement Learning (RL) as a promising framework for data-driven decision making, yet a clear picture of how these algorithms are currently employed, benchmarked and evaluated is still missing. This survey fills that gap by systematically analysing around 100 peer-reviewed papers that train, test or validate RL policies inside the open-source CARLA simulator. We first categorize the literature by algorithmic family model-free, model-based, hierarchical, and hybrid and quantify their prevalence, highlighting that more than 80% of existing studies still rely on model-free methods such as DQN, PPO and SAC. Next, we explain the diverse state, action and reward formulations adopted across works, illustrating how choices of sensor modality (RGB, LiDAR, BEV, semantic maps, and carla kinematics states), control abstraction (discrete vs. continuous) and reward shaping are used across various literature. We also consolidate the evaluation landscape by listing the most common metrics (success rate, collision rate, lane deviation, driving score) and the towns, scenarios and traffic configurations used in CARLA benchmarks. Persistent challenges including sparse rewards, sim-to-real transfer, safety guarantees and limited behaviour diversity are distilled into a set of open research questions, and promising directions such as model-based RL, meta-learning and richer multi-agent simulations are outlined. By providing a unified taxonomy, quantitative statistics and a critical discussion of limitations, this review aims to serve both as a reference for newcomers and as a roadmap for advancing RL-based autonomous driving toward real-world deployment.

Fairness-aware classification requires balancing performance and fairness, often intensified by intersectional biases. Conflicting fairness definitions further complicate the task, making it difficult to identify universally fair solutions. Despite growing regulatory and societal demands for equitable AI, popular toolkits offer limited support for exploring multi-dimensional fairness and related trade-offs. To address this, we present mmm-fair, an open-source toolkit leveraging boosting-based ensemble approaches that dynamically optimizes model weights to jointly minimize classification errors and diverse fairness violations, enabling flexible multi-objective optimization. The system empowers users to deploy models that align with their context-specific needs while reliably uncovering intersectional biases often missed by state-of-the-art methods. In a nutshell, mmm-fair uniquely combines in-depth multi-attribute fairness, multi-objective optimization, a no-code, chat-based interface, LLM-powered explanations, interactive Pareto exploration for model selection, custom fairness constraint definition, and deployment-ready models in a single open-source toolkit, a combination rarely found in existing fairness tools. Demo walkthrough available at: https://youtu.be/_rcpjlXFqkw.

Multiple Instance Learning (MIL) is a powerful framework for weakly supervised learning, particularly useful when fine-grained annotations are unavailable. Despite growing interest in deep MIL methods, the field lacks standardized tools for model development, evaluation, and comparison, which hinders reproducibility and accessibility. To address this, we present torchmil, an open-source Python library built on PyTorch. torchmil offers a unified, modular, and extensible framework, featuring basic building blocks for MIL models, a standardized data format, and a curated collection of benchmark datasets and models. The library includes comprehensive documentation and tutorials to support both practitioners and researchers. torchmil aims to accelerate progress in MIL and lower the entry barrier for new users. Available at https://torchmil.readthedocs.io.

Abstract--Objective: Electrocardiograms (ECGs) play a crucial role in diagnosing heart conditions; however, the effectiveness of artificial intelligence (AI)-based ECG analysis is often hindered by the limited availability of labeled data. Self-supervised learning (SSL) can address this by leveraging large-scale unlabeled data. We introduce PhysioCLR (Physiology-aware Contrastive Learning Representation for ECG), a physiology-aware contrastive learning framework that incorporates domain-specific priors to enhance the generalizability and clinical relevance of ECG-based arrhythmia classification. Methods: During pre-training, PhysioCLR learns to bring together embeddings of samples that share similar clinically relevant features while pushing apart those that are dissimilar . Additionally, we introduce ECGspecific augmentations that preserve the ECG category post-augmentation and propose a hybrid loss function to further refine the quality of learned representations. Results: We evaluate PhysioCLR on two public ECG datasets, Chapman and Georgia, for multilabel ECG diagnoses, as well as a private ICU dataset labeled for binary classification. Across the Chapman, Georgia, and private cohorts, PhysioCLR boosts the mean AUROC by 12% relative to the strongest baseline, underscoring its robust cross-dataset generalization. This work was supported in part by the Natural Sciences and Engineering Research Council of Canada (NSERC); the New Frontiers in Research Fund (NFRF) through the Social Sciences and Humanities Research Council (SSHRC); and the V ector Institute. Sophia Mannina is supported in part by the Social Sciences and Humanities Research Council. Stephanie Sibley is supported in part by the Canadian Institutes of Health Research (CIHR). David Maslove is supported in part by the Southeastern Ontario Academic Medical Association (SEAMO).