HERO accelerates world model inference 1.73x via hierarchical patch-wise refresh in shallow layers and linear extrapolation in deeper layers with minimal quality loss.
Quantcache: Adaptive importance-guided quantization with hierarchical latent and layer caching for video generation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
HERO: Hierarchical Extrapolation and Refresh for Efficient World Models
HERO accelerates world model inference 1.73x via hierarchical patch-wise refresh in shallow layers and linear extrapolation in deeper layers with minimal quality loss.