DynamicRad achieves 1.7x-2.5x inference speedups in long video diffusion with over 80% sparsity by grounding adaptive selection in a radial locality prior, using dual-mode static/dynamic strategies and offline BO with a semantic motion router.
arXiv preprint arXiv:2503.03588 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
BlossomRec is a sparse attention mechanism that uses two distinct block-level patterns for long-term and short-term interests, fused by a gated output, to reduce computation in sequential recommendation Transformers.
citing papers explorer
-
DynamicRad: Content-Adaptive Sparse Attention for Long Video Diffusion
DynamicRad achieves 1.7x-2.5x inference speedups in long video diffusion with over 80% sparsity by grounding adaptive selection in a radial locality prior, using dual-mode static/dynamic strategies and offline BO with a semantic motion router.
-
BlossomRec: Block-level Fused Sparse Attention Mechanism for Sequential Recommendations
BlossomRec is a sparse attention mechanism that uses two distinct block-level patterns for long-term and short-term interests, fused by a gated output, to reduce computation in sequential recommendation Transformers.