In this study, we proposed a novel Knowledge-Informed Deep Learning (KIDL) paradigm that, to the best of our knowledge, is the first to unify behavioral generalization and traffic flow stability by systematically integrating high-level knowledge distillation from LLMs with physically grounded stability constraints in car-following modeling. Generalization is enhanced by distilling car-following knowledge from LLMs into a lightweight and efficient neural network, while local and string stability are achieved by embedding physically grounded constraints into the distillation process. Experimental results on real-world traffic datasets validate the effectiveness of the KIDL paradigm, showing its ability to replicate and even surpass the LLM's generalization performance. It also outperforms traditional physics-based, data-driven, and hybrid CFMs by at least 10.18% in terms of trajectory simulation error RMSE. Furthermore, the resulting KIDL model is proven through theoretical and numerical analysis to ensure local and string stability at all equilibrium states, offering a strong foundation for advancing AV technologies.

Practically, KIDL offers a deployable solution for AV control, serving as a high-level motion reference that ensures realistic and stable car-following in mixed traffic environments. Moreover, this framework provides a promising pathway for integrating LLM-derived knowledge into traffic modeling by distilling it into a lightweight model with embedded physical constraints, balancing generalization with real-world feasibility.

Researchers at Chang’an University have developed a novel combined virtual-real testing (CVRT) platform for validating autonomous vehicles. This innovative approach utilizes digital twin technology to simulate realistic scenarios and conduct parallel AEB (autonomous emergency braking) tests across various conditions. The results indicate that CVRT closely replicates real-world performance while significantly reducing test time by up to 70%. This breakthrough offers a safer, more efficient method for validating autonomous systems, with implications for scalable testing and regulation in the autonomous vehicle industry.

Socially compliant automated vehicles (SCAVs) mark a new frontier in human-centric driving automation. Integrating sensing, socially aware decision-making, safety constraints, spatial-temporal memory, and bidirectional behavioral adaptation, the proposed framework aims for AVs to interpret, learn from, and respond to human drivers. By embedding social intelligence into automated driving systems, this research paves the way for vehicles that not only drive safely but also drive socially.

The CNRS, Institut d’Optique Graduate School and the scaleup Pasqal inaugurated the AtomIQ-Lab associated research laboratory on 26 November 2025. This collaboration between academic research and business aims to push back the technical limits of laser-cooled atom manipulation. The goal is to considerably increase the performance of quantum processors based on this technology, which are marketed by Pasqal, as well as to extend the range of accessible phenomena in the fundamental physics experiments conducted by the team from the Charles Fabry Laboratory (CNRS/Institut d’Optique).

As cold weather sets in, viruses such as influenza, RSV, and COVID-19 are resurfacing. Quickly identifying symptomatic individuals is an essential part of any strategy to fight their spread. Yet, traditional thermal cameras, which measure facial temperature on the forehead or cheeks, are easily skewed by airflow, sweat, or face coverings—leading to unreliable readings.

To address this, a team at the Institut national de la recherche scientifique (INRS) led by Professor Jinyang Liang, an expert in computational imaging, has developed SPIRIT (Single-pixel infrared imaging thermometry), a technology that could change how we screen for fever in public spaces.

A new Swansea University study shows that AI can enhance, not replace, human creativity, with participants producing better, more imaginative designs and feeling more engaged when supported by diverse AI-generated suggestions. The research argues that evaluating AI tools should go beyond efficiency metrics to consider how they influence users’ emotions, thinking and exploration.