Scores are calculated by giving a weight of 1 for applicable, 0.5 for conditionally applicable, and 0 for incorrect responses. The values are presented as percentages, calculated by the number of responses that satisfy the criteria divided by the total number of responses. The country with the highest percentage is marked in bold, and the second highest is underlined.

Accurate and contextually faithful responses are critical when applying large language models (LLMs) to sensitive and domain-specific tasks, such as answering queries related to quranic studies. General-purpose LLMs often struggle with hallucinations, where generated responses deviate from authoritative sources, raising concerns about their reliability in religious contexts. This challenge highlights the need for systems that can integrate domain-specific knowledge while maintaining response accuracy, relevance, and faithfulness. In this study, we investigate 13 open-source LLMs categorized into large (e.g., Llama3:70b, Gemma2:27b, QwQ:32b), medium (e.g., Gemma2:9b, Llama3:8b), and small (e.g., Llama3.2:3b, Phi3:3.8b). A Retrieval-Augmented Generation (RAG) is used to make up for the problems that come with using separate models. This research utilizes a descriptive dataset of Quranic surahs including the meanings, historical context, and qualities of the 114 surahs, allowing the model to gather relevant knowledge before responding. The models are evaluated using three key metrics set by human evaluators: context relevance, answer faithfulness, and answer relevance. The findings reveal that large models consistently outperform smaller models in capturing query semantics and producing accurate, contextually grounded responses. The Llama3.2:3b model, even though it is considered small, does very well on faithfulness (4.619) and relevance (4.857), showing the promise of smaller architectures that have been well optimized. This article examines the trade-offs between model size, computational efficiency, and response quality while using LLMs in domain-specific applications.

For what purpose was this dataset created? Was there a specific task in mind? Was there a specific gap that needed to be filled? Who created the dataset (e.g., which team, research group) and on behalf of which entity CVQA is a collaborative movement involving many people from different institutions and communities. The CVQA is led by a team of researchers from MBZUAI. Who funded the creation of the dataset?

Visual Question Answering (VQA) is an important task in multimodal AI, and it is often used to test the ability of vision-language models to understand and reason on knowledge present in both visual and textual data. However, most of the current VQA models use datasets that are primarily focused on English and a few major world languages, with images that are typically Western-centric.

As large language models (LLMs) rapidly advance, evaluating their performance is critical. LLMs are trained on multilingual data, but their reasoning abilities are mainly evaluated using English datasets. Hence, robust evaluation frameworks are needed using high-quality non-English datasets, especially low-resource languages (LRLs). This study evaluates eight state-of-the-art (SOTA) LLMs on Latvian and Giriama using a Massive Multitask Language Understanding (MMLU) subset curated with native speakers for linguistic and cultural relevance. Giriama is benchmarked for the first time. Our evaluation shows that OpenAI's o1 model outperforms others across all languages, scoring 92.8% in English, 88.8% in Latvian, and 70.8% in Giriama on 0-shot tasks. Mistral-large (35.6%) and Llama-70B IT (41%) have weak performance, on both Latvian and Giriama. Our results underscore the need for localized benchmarks and human evaluations in advancing cultural AI contextualization.

Transfer Learning (TL) is a powerful tool that enables robots to transfer learned policies across different environments, tasks, or embodiments. To further facilitate this process, efforts have been made to combine it with Learning from Demonstrations (LfD) for more flexible and efficient policy transfer. However, these approaches are almost exclusively limited to offline demonstrations collected before policy transfer starts, which may suffer from the intrinsic issue of covariance shift brought by LfD and harm the performance of policy transfer. Meanwhile, extensive work in the learning-from-scratch setting has shown that online demonstrations can effectively alleviate covariance shift and lead to better policy performance with improved sample efficiency. This work combines these insights to introduce online demonstrations into a policy transfer setting. We present Policy Transfer with Online Demonstrations, an active LfD algorithm for policy transfer that can optimize the timing and content of queries for online episodic expert demonstrations under a limited demonstration budget. We evaluate our method in eight robotic scenarios, involving policy transfer across diverse environment characteristics, task objectives, and robotic embodiments, with the aim to transfer a trained policy from a source task to a related but different target task. The results show that our method significantly outperforms all baselines in terms of average success rate and sample efficiency, compared to two canonical LfD methods with offline demonstrations and one active LfD method with online demonstrations. Additionally, we conduct preliminary sim-to-real tests of the transferred policy on three transfer scenarios in the real-world environment, demonstrating the policy effectiveness on a real robot manipulator.

This study leverages spatial machine learning (SML) to enhance the accuracy of Proxy Means Testing (PMT) for poverty targeting in Indonesia. Conventional PMT methodologies are prone to exclusion and inclusion errors due to their inability to account for spatial dependencies and regional heterogeneity. By integrating spatial contiguity matrices, SML models mitigate these limitations, facilitating a more precise identification and comparison of geographical poverty clusters. Utilizing household survey data from the Social Welfare Integrated Data Survey (DTKS) for the periods 2016 to 2020 and 2016 to 2021, this study examines spatial patterns in income distribution and delineates poverty clusters at both provincial and district levels. Empirical findings indicate that the proposed SML approach reduces exclusion errors from 28% to 20% compared to standard machine learning models, underscoring the critical role of spatial analysis in refining machine learning-based poverty targeting. These results highlight the potential of SML to inform the design of more equitable and effective social protection policies, particularly in geographically diverse contexts. Future research can explore the applicability of spatiotemporal models and assess the generalizability of SML approaches across varying socio-economic settings.

Detecting gender-based hate speech in Indonesian social media remains challenging due to limited labeled datasets. While binary hate speech classification has advanced, a more granular category like gender-targeted hate speech is understudied because of class imbalance issues. This paper addresses this gap by comparing three data augmentation techniques for Indonesian gender-based hate speech detection. We evaluate backtranslation, single-class prompt generation (using only hate speech examples), and our proposed dual-class prompt generation (using both hate speech and non-hate speech examples). Experiments show all augmentation methods improve classification performance, with our dual-class approach achieving the best results (88.5% accuracy, 88.1% F1-score using Random Forest). Semantic similarity analysis reveals dual-class prompt generation produces the most novel content, while T-SNE visualizations confirm these samples occupy distinct feature space regions while maintaining class characteristics. Our findings suggest that incorporating examples from both classes helps language models generate more diverse yet representative samples, effectively addressing limited data challenges in specialized hate speech detection.

Simultaneous Localization and Mapping (SLAM) allows mobile robots to navigate without external positioning systems or pre-existing maps. Radar is emerging as a valuable sensing tool, especially in vision-obstructed environments, as it is less affected by particles than lidars or cameras. Modern 4D imaging radars provide three-dimensional geometric information and relative velocity measurements, but they bring challenges, such as a small field of view and sparse, noisy point clouds. Detecting loop closures in SLAM is critical for reducing trajectory drift and maintaining map accuracy. However, the directional nature of 4D radar data makes identifying loop closures, especially from reverse viewpoints, difficult due to limited scan overlap. This article explores using 4D radar for loop closure in SLAM, focusing on similar and opposing viewpoints. We generate submaps for a denser environment representation and use introspective measures to reject false detections in feature-degenerate environments. Our experiments show accurate loop closure detection in geometrically diverse settings for both similar and opposing viewpoints, improving trajectory estimation with up to 82 % improvement in ATE and rejecting false positives in self-similar environments.

--Federated Learning has gained a significant amount of attraction in recent years. Federated learning enables clients to learn about their private data and then share their learnings with the central server to create a generalized global model and further share the generalized model with all clients. This aggregation of knowledge is based on the aggregation of model weights which has many associated issues. The model weights are more susceptible to model inversion attacks and would use a significant amount of bandwidth to share. In this work, we propose a loss-based federated learning framework using deep mutual learning between all clients using knowledge distillation.