Urban Air Mobility (UAM) envisions the widespread use of small aerial vehicles to transform transportation in dense urban environments. However, UAM faces critical operational challenges, particularly the balance between minimizing noise exposure and maintaining safe separation in low-altitude urban airspace, two objectives that are often addressed separately. We propose a reinforcement learning (RL)-based air traffic management system that integrates both noise and safety considerations within a unified, decentralized framework. Under this scalable air traffic coordination solution, agents operate in a structured, multi-layered airspace and learn altitude adjustment policies to jointly manage noise impact and separation constraints. The system demonstrates strong performance across both objectives and reveals tradeoffs among separation, noise exposure, and energy efficiency under high traffic density. The findings highlight the potential of RL and multi-objective coordination strategies in enhancing the safety, quietness, and efficiency of UAM operations.

Large Language Models (LLMs) such as ChatGPT-4, Claude 3, and LLaMA 4 are increasingly embedded in software/application development, supporting tasks from code generation to debugging. Yet, their real-world effectiveness in detecting diverse software bugs, particularly complex, security-relevant vulnerabilities, remains underexplored. This study presents a systematic, empirical evaluation of these three leading LLMs using a benchmark of foundational programming errors, classic security flaws, and advanced, production-grade bugs in C++ and Python. The dataset integrates real code from SEED Labs, OpenSSL (via the Suresoft GLaDOS database), and PyBugHive, validated through local compilation and testing pipelines. A novel multi-stage, context-aware prompting protocol simulates realistic debugging scenarios, while a graded rubric measures detection accuracy, reasoning depth, and remediation quality. Our results show that all models excel at identifying syntactic and semantic issues in well-scoped code, making them promising for educational use and as first-pass reviewers in automated code auditing. Performance diminishes in scenarios involving complex security vulnerabilities and large-scale production code, with ChatGPT-4 and Claude 3 generally providing more nuanced contextual analyses than LLaMA 4. This highlights both the promise and the present constraints of LLMs in serving as reliable code analysis tools.

The rapid advancement of large language models (LLMs) has significantly propelled progress in natural language processing (NLP). However, their effectiveness in specialized, low-resource domains-such as Arabic legal contexts-remains limited. This paper introduces MizanQA (pronounced Mizan, meaning "scale" in Arabic, a universal symbol of justice), a benchmark designed to evaluate LLMs on Moroccan legal question answering (QA) tasks, characterised by rich linguistic and legal complexity. The dataset draws on Modern Standard Arabic, Islamic Maliki jurisprudence, Moroccan customary law, and French legal influences. Comprising over 1,700 multiple-choice questions, including multi-answer formats, MizanQA captures the nuances of authentic legal reasoning. Benchmarking experiments with multilingual and Arabic-focused LLMs reveal substantial performance gaps, highlighting the need for tailored evaluation metrics and culturally grounded, domain-specific LLM development.

We constructed JaParaPat (Japanese-English Parallel Patent Application Corpus), a bilingual corpus of more than 300 million Japanese-English sentence pairs from patent applications published in Japan and the United States from 2000 to 2021. We obtained the publication of unexamined patent applications from the Japan Patent Office (JPO) and the United States Patent and Trademark Office (USPTO). We also obtained patent family information from the DOCDB, that is a bibliographic database maintained by the European Patent Office (EPO). We extracted approximately 1.4M Japanese-English document pairs, which are translations of each other based on the patent families, and extracted about 350M sentence pairs from the document pairs using a translation-based sentence alignment method whose initial translation model is bootstrapped from a dictionary-based sentence alignment method. We experimentally improved the accuracy of the patent translations by 20 bleu points by adding more than 300M sentence pairs obtained from patent applications to 22M sentence pairs obtained from the web.

Recently, Vision-Language-Action (VLA) models have demonstrated strong performance on a range of robotic tasks. These models rely on multimodal inputs, with language instructions playing a crucial role -- not only in predicting actions, but also in robustly interpreting user intent, even when the requests are impossible to fulfill. In this work, we investigate how VLAs can recognize, interpret, and respond to false-premise instructions: natural language commands that reference objects or conditions absent from the environment. We propose Instruct-Verify-and-Act (IVA), a unified framework that (i) detects when an instruction cannot be executed due to a false premise, (ii) engages in language-based clarification or correction, and (iii) grounds plausible alternatives in perception and action. Towards this end, we construct a large-scale instruction tuning setup with structured language prompts and train a VLA model capable of handling both accurate and erroneous requests. Our approach leverages a contextually augmented, semi-synthetic dataset containing paired positive and false-premise instructions, enabling robust detection and natural language correction. Our experiments show that IVA improves false premise detection accuracy by 97.56% over baselines, while increasing successful responses in false-premise scenarios by 50.78%.

Air pollution forecasting is critical for proactive environmental management, yet data irregularities and scarcity remain major challenges in low-resource regions. Northern Nigeria faces high levels of air pollutants, but few studies have systematically compared the performance of advanced machine learning models under such constraints. This study evaluates Long Short-Term Memory (LSTM) networks and the Facebook Prophet model for forecasting multiple pollutants (CO, SO2, SO4) using monthly observational data from 2018 to 2023 across 19 states. Results show that Prophet often matches or exceeds LSTM's accuracy, particularly in series dominated by seasonal and long-term trends, while LSTM performs better in datasets with abrupt structural changes. These findings challenge the assumption that deep learning models inherently outperform simpler approaches, highlighting the importance of model-data alignment. For policymakers and practitioners in resource-constrained settings, this work supports adopting context-sensitive, computationally efficient forecasting methods over complexity for its own sake.

Visual Foundation Models (VFMs) are becoming ubiquitous in computer vision, powering systems for diverse tasks such as object detection, image classification, segmentation, pose estimation, and motion tracking. VFMs are capitalizing on seminal innovations in deep learning models, such as LeNet-5, AlexNet, ResNet, VGGNet, InceptionNet, DenseNet, YOLO, and ViT, to deliver superior performance across a range of critical computer vision applications. These include security-sensitive domains like biometric verification, autonomous vehicle perception, and medical image analysis, where robustness is essential to fostering trust between technology and the end-users. This article investigates network robustness requirements crucial in computer vision systems to adapt effectively to dynamic environments influenced by factors such as lighting, weather conditions, and sensor characteristics. We examine the prevalent empirical defenses and robust training employed to enhance vision network robustness against real-world challenges such as distributional shifts, noisy and spatially distorted inputs, and adversarial attacks. Subsequently, we provide a comprehensive analysis of the challenges associated with these defense mechanisms, including network properties and components to guide ablation studies and benchmarking metrics to evaluate network robustness.

--With the increasing deployment of small Unmanned Aircraft Systems (sUAS) in unfamiliar and complex environments, Environmental Digital Twins (EDT) that comprise weather, airspace, and terrain data are critical for safe flight planning and for maintaining appropriate altitudes during search and surveillance operations. With the expansion of sUAS capabilities through edge and cloud computing, accurate EDT are also vital for advanced sUAS capabilities, like geolocation. However, real-world sUAS deployment introduces significant sources of uncertainty, necessitating a robust validation process for EDT components. This paper focuses on the validation of terrain models, one of the key components of an EDT, for real-world sUAS tasks. These models are constructed by fusing U.S. Geological Survey (USGS) datasets and satellite imagery, incorporating high-resolution environmental data to support mission tasks. V alidating both the terrain models and their operational use by sUAS under real-world conditions presents significant challenges, including limited data granularity, terrain discontinuities, GPS and sensor inaccuracies, visual detection uncertainties, as well as onboard resources and timing constraints. We propose a 3-Dimensions validation process grounded in software engineering principles, following a workflow across granularity of tests, simulation to real world, and the analysis of simple to edge conditions. We demonstrate our approach using a multi-sUAS platform equipped with a T errain-A ware Digital Shadow. As swarms of small Unmanned Aircraft Systems (sUAS) are increasingly deployed in complex, unstructured environments such as disaster zones, wilderness areas, and wildfire regions, the need for accurate environmental models becomes critical. Effective sUAS mission planning requires awareness not only of dynamic airspace and weather conditions but also of the underlying terrain. In such settings, terrain is often the dominant factor influencing flight safety, sensor placement, line-of-sight communications, and search effectiveness. This paper focuses specifically on the role of terrain models that enable mission-level decision-making and flight planning for sUAS operations. However, terrain inaccuracies or blind spots, such as missing elevation data, undetected peaks, or mismatched georeferencing, can result in ineffective or even hazardous behavior by autonomous vehicles. To minimize these issues, we construct and maintain a terrain model by fusing multiple sources of environmental data, including public USGS datasets [1], [2], and satellite imagery [3].

The Madden-Julian Oscillation (MJO) is the dominant mode of tropical atmospheric variability on intraseasonal timescales, and reliable MJO predictions are essential for protecting lives and mitigating impacts on societal assets. However, numerical models still fall short of achieving the theoretical predictability limit for the MJO due to inherent constraints. In an effort to extend the skillful prediction window for the MJO, machine learning (ML) techniques have gained increasing attention. This study examines the MJO prediction performance of the FuXi subseasonal-to-seasonal (S2S) ML model during boreal winter, comparing it with the European Centre for Medium- Range Weather Forecasts S2S model. Results indicate that for the initial strong MJO phase 3, the FuXi-S2S model demonstrates reduced biases in intraseasonal outgoing longwave radiation anomalies averaged over the tropical western Pacific (WP) region during days 15-20, with the convective center located over this area. Analysis of multiscale interactions related to moisture transport suggests that improvements could be attributed to the FuXi-S2S model's more accurate prediction of the area-averaged meridional gradient of low-frequency background moisture over the tropical WP. These findings not only explain the enhanced predictive capability of the FuXi-S2S model but also highlight the potential of ML approaches in advancing the MJO forecasting.

Large language models (LLMs) are increasingly deployed in politically sensitive settings, raising concerns about their potential to encode, amplify, or be steered toward specific ideologies. We investigate how adopting synthetic personas influences ideological expression in LLMs across seven models (7B-70B+ parameters) from multiple families, using the Political Compass Test as a standardized probe. Our analysis reveals four consistent patterns: (i) larger models display broader and more polarized implicit ideological coverage; (ii) susceptibility to explicit ideological cues grows with scale; (iii) models respond more strongly to right-authoritarian than to left-libertarian priming; and (iv) thematic content in persona descriptions induces systematic and predictable ideological shifts, which amplify with size. These findings indicate that both scale and persona content shape LLM political behavior. As such systems enter decision-making, educational, and policy contexts, their latent ideological malleability demands attention to safeguard fairness, transparency, and safety.