single mention · optimization
Two-step prompt-and-head warm-up adaptation
A two-step adaptation procedure that first warms up new learnable prompts while keeping pretrained weights frozen, then jointly optimizes the backbone and warmed-up prompts.1,2 The warm-up projects prompts onto pretrained embodiment-agnostic features, giving a good starting point before full joint training specializes the policy to a new domain.3
How this definition was written
Summarised by glm-5.3-flash from 1 source; every sentence is checked against the quote it cites.
The prompt is first warmed up while keeping the pretrained weights frozen
— X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Modelwe jointly optimize both the backbone and the warmed-up prompt
— X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Modelprompts are projected to exploit pretrained embodiment-agnostic features, offering good starts for next-round joint training
— X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model
Also called two-step adaptation procedure.
Filed under optimization › training stability