Lesson plan
Vision–language–action model
In robot learning, a vision–language–action model (VLA) is a class of multimodal foundation models that integrates vision, language and actions. Given an input image (or video) of the robot's surroundings and a text instruction, a VLA directly outputs low-level robot actions that can be executed to accomplish the requested task. VLAs are generally constructed by fine-tuning a vision-language model (VLM) (i.e. a large language model extended with vision capabilities) on a large-scale dataset that pairs visual observation and language instructions with robot trajectories. These models combine a vision-language encoder (vision transformer), which translates an image observation and a natural language description into a distribution within a latent space, with an action decoder that transforms this representation into continuous output actions, directly executable on the robot. The concept was pioneered in July 2023 by Google DeepMind with -2, a VLM adapted for end-to-end manipulation tasks, capable of unifying perception, reasoning and control.
Article summary
In robot learning, a vision–language–action model (VLA) is a class of multimodal foundation models that integrates vision, language and actions. Given an input image (or video) of the robot's surroundings and a text instruction, a VLA directly outputs low-level robot actions that can be executed to accomplish the requested task. VLAs are generally constructed by fine-tuning a vision-language model (VLM) (i.e. a large language model extended with vision capabilities) on a large-scale dataset that pairs visual observation and language instructions with robot trajectories. These models combine a vision-language encoder (vision transformer), which translates an image observation and a natural language description into a distribution within a latent space, with an action decoder that transforms this representation into continuous output actions, directly executable on the robot. The concept was pioneered in July 2023 by Google DeepMind with -2, a VLM adapted for end-to-end manipulation tasks, capable of unifying perception, reasoning and control.
Key claims
- release date: 2025 — source: Wikipedia, revision 1376359770, retrieved 2026-10-20 · confidence 0.95
Discussion questions
- Summarise the article in your own words. Which single claim would you verify first, and why?
- The record states that the release date is "2025". What evidence would count against this claim?
- Which claim in this article is most likely to be revised as the sources update? How would you check its current status?
- If two sources disagreed about one of these facts, what would you need in order to trust one over the other?
Bibliography
- Wikipedia, “Vision–language–action model”, revision 1376359770, retrieved 2026-10-20 https://en.wikipedia.org/w/index.php?oldid=1376359770
Key claims and bibliography are generated from the same tracked claims and sources as the article page.