X-Cache achieves 71% block skip rate and 2.6x wall-clock speedup in few-step autoregressive multi-camera driving world models via cross-chunk residual caching with dual-metric gating and forced KV updates.
Deepcache: Accelerating diffusion models for free
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Focused Forcing is a training-free per-frame KV selection method that combines attention scores with diversity metrics and head-importance estimation to accelerate autoregressive video diffusion up to 1.48x while improving quality.
citing papers explorer
-
X-Cache: Cross-Chunk Block Caching for Few-Step Autoregressive World Models Inference
X-Cache achieves 71% block skip rate and 2.6x wall-clock speedup in few-step autoregressive multi-camera driving world models via cross-chunk residual caching with dual-metric gating and forced KV updates.
-
Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video Diffusion
Focused Forcing is a training-free per-frame KV selection method that combines attention scores with diversity metrics and head-importance estimation to accelerate autoregressive video diffusion up to 1.48x while improving quality.