single mention · model architecture
Continuous action representation
A continuous action representation lets a VLA model output actions directly as continuous values instead of discretizing them into bins.1 It avoids the discretization dilemma where finer bins improve precision but make individual tokens rarer in training data, hurting generalization.2
How this definition was written
Summarised by glm-5.3-flash from 1 source; every sentence is checked against the quote it cites.
with a continuous action representation, the VLA can directly model the action distribution without lossy discretization
— Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successincreasing the number of bins used for discretization improves precision but reduces the frequency of individual tokens in the training data, potentially hurting generalization
— Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
Also called continuous action representations.
Filed under model architecture › multimodal architecture