DiTo shifts token reduction in DiTs to output token similarity, reusing prior-step matches across timesteps with PMR scheduling and frequency-aware penalties to raise PSNR at given speedups.
CVPR Workshop on Efficient Deep Learning for Computer Vision (2023)
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
LIPAR prunes redundant inter-frame latent patches in video generation and recovers attention to deliver 1.53x speedup at 19.3 FPS with no quality drop or extra training.
citing papers explorer
-
Rethinking Token Reduction for Diffusion Models via Output-Similarity-Awareness
DiTo shifts token reduction in DiTs to output token similarity, reusing prior-step matches across timesteps with PMR scheduling and frequency-aware penalties to raise PSNR at given speedups.
-
Video Compression Meets Video Generation: Latent Inter-Frame Pruning with Attention Recovery
LIPAR prunes redundant inter-frame latent patches in video generation and recovers attention to deliver 1.53x speedup at 19.3 FPS with no quality drop or extra training.