Researchers from Hefei University of Technology and the University of Science and Technology of China have proposed a neural architecture search framework that allows an algorithm to automatically look for suitable network structures for EEG-based seizure prediction.

Researchers from Shenzhen Polytechnic University, the University of California, Riverside, and Tsinghua University evaluated real-world emissions from China V and China VI heavy-duty diesel trucks using portable emissions measurement systems (PEMS). The study found that compliant China VI trucks can substantially reduce NO_x and particle number (PN) emissions, but some vehicles still showed severe emission exceedances under real driving conditions, highlighting the importance of in-use monitoring and after-treatment system performance.

Researchers from McGill University, The Hong Kong University of Science and Technology (Guangzhou), and the University of Luxembourg have developed MILD, an AI-powered mediator system that helps drivers and automated vehicles better understand each other. By combining driver-state monitoring, traffic-scene understanding, and explainable decision-making, the system aims to improve trust, safety, and collaboration in partially automated driving.

To address the dual challenges of reducing fuel consumption and ensuring maritime safety under extreme weather, researchers from Dalian University of Technology, Nanyang Technological University, and Chongqing Jiaotong University have developed a novel ship weather routing framework based on Dual-Mode Deep Reinforcement Learning. Utilizing the D3QN algorithm, this framework effectively navigates both normal sea states and severe typhoon conditions, providing a robust route toward maritime safety security and decarbonization.

Researchers developed Found-RL, an open-source platform that integrates vision-language models into reinforcement learning for autonomous driving. By using an asynchronous batch inference framework, Found-RL allows large foundation models to provide semantic feedback without slowing down high-frequency simulation training. Experiments in CARLA show that lightweight reinforcement learning agents can achieve competitive driving performance while maintaining real-time policy inference.

To address the severe safety challenges of AI-driven autonomous driving under the Autonomy 2.0 paradigm, a joint research team from Tongji University, SAMR Defective Product Recall Technical Center, and Tsinghua University, proposed a hierarchical risk-filtering safety assurance framework, establishing a four-category assessment metric system and layered safety strategies, with a dedicated safety monitor for system-level architecture design.

Can vision-language models understand unstructured road scenes under degraded sensing conditions? Researchers developed the Unstructured Scene Benchmark (USB), a test and evaluation framework for autonomous driving models in unstructured road scenes and degraded visual conditions. By testing seven open-source vision-language models across six camera views, 20 corruption types, and 45,969 question-answer samples, the study reveals uneven robustness, weak planning ability, and signs of insufficient visual grounding.

Researchers have developed a method to generate customizable virtual road networks with adjustable complexity, which cuts required test mileage by over 30% while preserving real-world road features. This enables faster, more efficient identification of functional defects and performance boundaries in autonomous vehicles.