For vision-language-action robots, token skipping stays reliable only when the gate that selects skipped tokens comes from a clean dense pass, not from the accelerated pass itself.
Proceedings of the 8th Conference on Robot Learning , pages =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The Gate, Not the Cache: Gate Provenance Bounds the Closed-Loop Reliability of Training-Free VLA Token Skipping
For vision-language-action robots, token skipping stays reliable only when the gate that selects skipped tokens comes from a clean dense pass, not from the accelerated pass itself.