Researchers introduce HalluTruthQA, a new fine-grained benchmark designed for hallucination detection, localization, and explanation in Arabic question answering. This benchmark comprises 2,400 expert-curated examples across Islamic knowledge, history, science, and geography, featuring character-level error spans, human explanations, and various hallucination types. The study evaluated four open-source Arabic LLMs (ALLaM-7B, Falcon-H1R-7B, Qwen3-32B, SILMA) across detection, localization, factual verification, and explanation tasks, revealing no single model outperforms others across all metrics. Why it matters: HalluTruthQA provides a critical tool for advancing the factual accuracy and reliability of Arabic LLMs by enabling more granular and comprehensive hallucination evaluation beyond response-level detection.
Researchers have introduced HalluTruthQA, a new fine-grained benchmark designed for hallucination detection, localization, and explanation in Arabic Question Answering. The benchmark comprises 2,400 expert-curated examples spanning four knowledge-intensive domains: Islamic knowledge, history, science, and geography, with detailed annotations including character-level erroneous spans and human-written explanations. Four open-source LLMs ( extsc{Allam}, extsc{Falcon-H1}, extsc{Qwen32}, and extsc{Silma}) were evaluated, demonstrating varied performance across detection, localization, factual verification, and explanation tasks. Why it matters: This benchmark offers a comprehensive tool for evaluating and enhancing the factual accuracy and trustworthiness of Arabic LLMs, promoting more sophisticated assessment beyond simple hallucination detection.
YOLO26-RipeLoc Lite is a new lightweight deep learning architecture designed for simultaneous detection, ripeness classification, and center-point localization of greenhouse tomatoes for robotic harvesting. The model incorporates a Lightweight Feature Pyramid Network, a Ripeness-Aware Attention Module, and a Compact Detection Head for efficient and precise operation. Evaluated on a custom dataset from the SILAL greenhouse in Abu Dhabi, UAE, it achieved a mAP@0.5 of 92.9% with only 2.38 million parameters, outperforming existing YOLO models in accuracy-efficiency. Why it matters: This research provides an efficient and accurate solution for automating a critical agricultural process, enhancing food security and technological capabilities in the region's greenhouse farming.
This work presents a dual pose-graph architecture for robust real-time localization in autonomous drone racing. The system fuses monocular visual-inertial odometry with semantic gate detections, using a temporary graph to optimize multiple observations into refined constraints before promoting them to a persistent main graph. Evaluated on the TII-RATM dataset and deployed in the A2RL competition, it achieved a 56-74% reduction in Absolute Trajectory Error (ATE) compared to standalone VIO and reduced odometry drift by up to 4.2 meters per lap. Why it matters: This research significantly improves the reliability and accuracy of vision-based localization for high-speed autonomous drones, crucial for advanced robotics applications and competitive racing.
This paper introduces ADR-VINS, a monocular visual-inertial state estimation framework based on an Error-State Kalman Filter (ESKF) designed for autonomous drone racing, integrating direct pixel reprojection errors from gate corners as innovation terms. It also introduces ADR-FGO, an offline Factor-Graph Optimization framework for generating high-fidelity reference trajectories for post-flight evaluation in GNSS-denied environments. Validated on the TII-RATM dataset, ADR-VINS achieved an average RMS translation error of 0.134 m and was successfully deployed in the A2RL Drone Championship Season 2. Why it matters: The framework provides a robust and efficient solution for drone state estimation in challenging racing environments, and enables performance evaluation without relying on external localization systems.
The Oil Sustainability Program (OSP), in partnership with PIF, SIRC, NEOM, SIKA, and ClimateCrete, has launched the "NovusCrete" Consortium to innovate in sustainable concrete solutions. The initiative prioritizes localization using materials like seawater, recycled construction waste, and fine sand, supported by entities like the American Concrete Institute (ACI). ClimateCrete, a KAUST spin-off, uses patented technology to transform fine sand into high-quality concrete sand, reducing cement use and CO2 emissions by up to 60%. Why it matters: The consortium and ClimateCrete's technology represent significant steps towards sustainable construction practices in the region, aligning with Saudi Arabia's carbon neutrality goals and fostering a deep-tech startup ecosystem.
MBZUAI researchers introduce PG-Video-LLaVA, a large multimodal model with pixel-level grounding capabilities for videos, integrating audio cues for enhanced understanding. The model uses an off-the-shelf tracker and grounding module to localize objects in videos based on user prompts. PG-Video-LLaVA is evaluated on video question-answering and grounding benchmarks, using Vicuna instead of GPT-3.5 for reproducibility.
Researchers from MBZUAI, IBM, and ServiceNow introduced GEOBench-VLM, a benchmark for evaluating vision-language models on Earth observation tasks using satellite and aerial imagery. The benchmark includes over 10,000 human-verified instructions across 31 sub-tasks spanning object classification, localization, change detection, and more. GEOBench-VLM addresses the gap in current VLMs' ability to perform spatially grounded reasoning and change detection in satellite imagery. Why it matters: This benchmark will drive progress in AI's ability to analyze satellite data for critical applications like disaster response, climate monitoring, and urban planning in the Middle East and globally.