Groundbreaking Release Advances Vision-Language-Action Foundation Models for Autonomous Driving, Robotics, and Embodied AI
LAS VEGAS, Jan. 8, 2026 /PRNewswire/ — At CES 2026, Tensor today announced the official open-source release of OpenTau (τ), a powerful AI training toolchain designed to accelerate the development of Vision-Language-Action (VLA) foundation models – a critical building block for the next generation of Physical AI systems.
At Tensor, we’re pushing the frontier of large foundation models for Physical AI. VLA models integrate vision, language, and action into a single multimodal foundation model, enabling intelligent systems to understand the world, reason about it, and act within it. This approach is increasingly recognized as a leading paradigm for Embodied AI, with applications spanning autonomous driving, robotic manipulation, and navigation.
OpenTau (τ) is Tensor’s open-source AI training platform for frontier VLA models, purpose-built to make large-scale AI training reproducible, accessible, and scalable. By releasing OpenTau to the global research and developer community, Tensor is making advanced training capabilities available beyond closed, proprietary environments—helping accelerate innovation across the industry. We believe the most meaningful technological advances are defined by clarity, rigor, and reproducibility. Open-sourcing is central to that philosophy, providing scientific transparency and enabling independent validation.
“At Tensor, we believe meaningful progress in Physical AI requires transparency,” said Jay Xiao, Founder and CEO of Tensor. “OpenTau is our way of giving back to the research and developer community that has helped advance this field. By open-sourcing our training toolchain, we’re supporting broader collaboration—so everyone can build, experiment, and move faster together..”
OpenTau brings state-of-the-art VLA training capabilities to the open-source community, including:
Designed with reproducibility and extensibility in mind, OpenTau enables researchers and developers to experiment with advanced training strategies that were previously difficult to implement or inaccessible outside of large-scale industrial research settings. We believe open research benefits the whole AI industry in the long run.
Tensor is inviting researchers, developers, and builders to explore OpenTau, contribute to its evolution, and help shape the future of Physical AI by starring the repository, forking and experimenting with the codebase, and building or extending frontier Vision-Language-Action models.
Explore OpenTau on GitHub: https://github.com/TensorAuto/OpenTau
CES 2026 attendees are invited to connect with the Tensor team and experience its technology firsthand:
About Tensor
Tensor Auto Inc. is an American AI company dedicated to building agentic products that empower individual consumers. Our flagship product, the Tensor Robocar, is the world’s first personal Robocar and the first AI agentic vehicle—fully autonomous, automotive-grade, and built for private ownership at scale. With native support for L0–L4 autonomy and a true Dual Mode design, you can choose to drive or be driven, enhanced by a foldable steering wheel and sliding display. Founded in 2016 in Silicon Valley, Tensor is headquartered in San Jose, California, with offices in Barcelona, Singapore, and Dubai. At Tensor, we champion personal AI autonomy and ownership. Our vision is to build a future where everyone owns their own Artificial General Intelligence – a personal AGI that enables more time, freedom, and autonomy. We’re forging an alternative path where AGI serves only you, and is controlled solely by you. To those who share this vision: Own Your Autonomy. Learn more at www.tensor.auto For the full list of Tensor Robocar features and vehicle specification, see more at www.tensor.auto.
View original content:https://www.prnewswire.com/news-releases/tensor-unveils-opentau–at-ces-2026-introducing-a-breakthrough-open-source-training-platform-for-physical-ai-302656833.html
SOURCE Tensor


