Diffusion policies trained on small robot demonstration sets act as action lookup tables, and a simple nearest-neighbor policy with a contrastive encoder matches their performance at a fraction of the cost.
Stable diffusion
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Demystifying Diffusion Policies: Action Memorization and Simple Lookup Table Alternatives
Diffusion policies trained on small robot demonstration sets act as action lookup tables, and a simple nearest-neighbor policy with a contrastive encoder matches their performance at a fraction of the cost.