SmolVLA
Hugging FaceCross-attention (CA), where action tokens attend to the VLM’s features
1 more from this model
in the CA setting the VLM features act as keys and values for attention in the action expert.
specific method · filed under model architecture
Cross-attention is an attention mechanism in which one set of tokens queries a different set of tokens that serves as the keys and values.1 It lets the action expert's tokens condition on VLM features rather than only attending to each other.2
Summarised by glm-5.3-flash from 1 source; every sentence is checked against the quote it cites.
in the CA setting the VLM features act as keys and values for attention— SmolVLA: A vision-language-action model for affordable and efficient robotics
CA layers cross-attend the VLM’s keys and values, while SA layers allow the action tokens in to attend to each other— SmolVLA: A vision-language-action model for affordable and efficient robotics
Also called simple cross-attention mechanism, cross-attention (CA).
3 quotes from 3 sources, one card per model, each opening with its strongest.
Cross-attention (CA), where action tokens attend to the VLM’s features
in the CA setting the VLM features act as keys and values for attention in the action expert.
we use a simple cross-attention mechanism