Flash-WAM introduces modality-specific consistency parametrizations to distill joint video-action diffusion models to single-step inference, delivering 23x speedup with preserved benchmark performance.
Zico Kolter, and Guo jun Qi
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Flash-WAM: Modality-Aware Distillation for World Action Models
Flash-WAM introduces modality-specific consistency parametrizations to distill joint video-action diffusion models to single-step inference, delivering 23x speedup with preserved benchmark performance.