A training-free cache of intermediate actions, retrieved by random-projected VLM embeddings, cuts flow-based VLA action-head latency up to 40× in tests while keeping success rates near base-model levels.
EfficientVLA: Training-free acceleration and compression for vision- language-action models
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
-
ActionCache: Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinement
A training-free cache of intermediate actions, retrieved by random-projected VLM embeddings, cuts flow-based VLA action-head latency up to 40× in tests while keeping success rates near base-model levels.