Open Models Almanac
Methodsmodel architecturemultimodal architecture

single mention · model architecture

Natural-language hardware-configuration prompts

Language prompts supply natural-language descriptions of hardware configurations as additional inputs to the model.1 Leveraging the language reasoning of pretrained VLMs, they let the model attend to embodiment-specific variations explicitly through text.2,3

Trade-off They rely on carefully scripted textual descriptions, which hinders adaptability and scalability in practice.4

How this definition was written

Summarised by glm-5.3-flash from 1 source; every sentence is checked against the quote it cites.

  1. natural language descriptions of hardware configurations are provided as additional inputs — X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model
  2. leverages the language reasoning capabilities of pretrained VLMs — X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model
  3. enabling the model to attend to embodiment-specific variations through textual descriptions explicitly — X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model
  4. rely on carefully scripted textual descriptions of hardware configurations, which greatly hinder adaptability and scalability in practice — X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model

Also called Language prompts.

Filed under model architecture › multimodal architecture