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.

To answer this question: How to accurately predict the future trajectories of mixed-flow vehicle platoons in traffic oscillation scenarios? This study introduces CPIDLM, a hybrid AI model that significantly improves vehicle movement predictions during traffic speed changes by combining physical driving laws with individual human behavior patterns. By explicitly accounting for driver uncertainty and how vehicles affect one another, this approach reduced distance prediction errors by 16.7% compared to existing methods, providing a more reliable foundation for autonomous vehicles.

Researchers developed COIN, a collaborative and interaction-aware reinforcement learning framework for multi-agent autonomous driving. COIN enables vehicles to learn both individual navigation and system-level cooperation, improving safety and efficiency in dense scenarios such as intersections, roundabouts, and bottlenecks. The framework was evaluated in simulation and further validated on a hybrid robotic platform.

A new study has identified RUNX1 (RUNX family transcription factor 1) as a key driver of a harmful fibroblast state in skin fibrosis. 

As demand for rechargeable batteries grows across electric transportation, grid-scale energy storage and consumer electronics, the search for electrode materials that combine high performance with lower environmental impact has become increasingly important. In a review published in the Journal of Bioresources and Bioproducts, researchers assess the potential of biomass-derived carbon produced from agricultural residues, forestry by-products and other renewable resources. The article compares thermochemical and emerging conversion routes, summarizes reported performance across lithium-, sodium- and potassium-based batteries, and considers techno-economic assessment, life-cycle impacts and technology readiness. The review identifies biomass-derived carbon as a promising materials platform, while emphasizing that feedstock variability, electrode performance limitations and scalable manufacturing must be addressed before broader deployment.

A mini-review published in the Journal of Bioresources and Bioproducts explores teak-derived quinones as potential redox-active additives for alkaline pulping. Anthraquinone has long been used to promote lignin removal while helping preserve carbohydrates, but safety concerns have encouraged the search for alternatives. By examining studies published between 1972 and 2026, the review compares synthetic anthraquinone derivatives, teak wood extracts and individual compounds such as 2-methylanthraquinone, deoxylapachol and lapachol. The findings suggest that some teak-derived materials can improve delignification, retain carbohydrates or reduce alkali requirements under specific cooking conditions. Nevertheless, differences in extract composition, limited toxicological evidence and the lack of comprehensive process-level assessments remain important barriers to wider application.

Nanophotonic biosensors are often evaluated by device-level metrics such as sensitivity, quality factor, linewidth, and detection limit. However, these parameters alone cannot fully determine practical performance in complex biological environments. This article introduces a Mode–Interface–Measurement–Decision framework, or MIMD, to reinterpret nanophotonic biosensing as a complete information-transfer process, emphasizing how biological information is generated, preserved, measured, and finally converted into meaningful decisions.

Maternal disorders remain critical indicators of national development and public health. In this study, researchers analyzed the burden of maternal disorders in China from 1990 to 2023 using data from the Global Burden of Diseases, Injuries, and Risk Factors Study 2023. The findings reveal a substantial decline in prevalence, mortality, and disability-adjusted life years over the past three decades, alongside notable shifts in leading causes and emerging challenges associated with China's changing fertility policies.