French technology company Valeo and NATIX Network have announced a partnership to develop a multi-camera World Foundation Model (WFM). The project combines Valeo’s research in artificial intelligence and generative modelling with NATIX’s decentralised physical infrastructure network (DePIN) to create an open-source platform for autonomous driving and robotics.
The initiative aims to move beyond perception-based models by creating a system capable of predicting future states and reasoning about physical interactions in a four-dimensional environment. The model will be trained using NATIX’s data network, which has collected 600,000 hours of video data across the US, Europe and Asia over seven months. This data provides the multi-camera inputs necessary for the spatial perception required by autonomous vehicles and robots.
The partnership builds upon Valeo’s existing open-source frameworks, VaViM (Video Autoregressive Model) and VaVAM (Video-Action Model). While these frameworks were previously trained primarily on front-camera datasets, the integration of NATIX’s multi-camera network expands the AI’s field of vision to 360 degrees.
Under the open-source framework, the partners will release models, datasets and training tools. This approach is intended to allow the research community to fine-tune models and benchmark physical AI across various driving conditions and geographic regions. The collaboration seeks to accelerate the deployment of end-to-end AI models by learning from real-world edge cases captured by vehicles in operation.
Marc Vrecko, Chief Executive Officer, Valeo’s Brain Division, said, “Since our creation in 2018, Valeo’s AI research center has been at the forefront of AI research in the automotive industry, especially in the fields of assisted and autonomous driving. Our goal has always been to advance mobility intelligence safely and responsibly. By combining Valeo’s generative world modeling research expertise with NATIX’s global multi-camera data, we are accelerating both the quality and the accessibility of next-generation end-to-end AI models, enabling the research community to build upon strong open models.”
Alireza Ghods, CEO and Co-Founder, NATIX, added, “WFMs are a once-in-a-generation opportunity — similar to the rise of LLMs in 2017–2020. The teams that build the first scalable world models will define the foundation of the next AI wave: Physical AIs. With our distributed multi-camera network, NATIX has a clear advantage of being able to move faster than large OEMs.”
Comments (0)
ADD COMMENT