Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
Frequency-Step Cache: Separating Synchronization and Repair for Efficient Autoregressive Video Diffusion
Kerry Xu, Param Misra, Zachary Stenglein +3
Autoregressive (AR) video generation enables long-horizon synthesis but requires repeated forward passes through large diffusion transformers. Training-free caching reduces this co…
cs.CV2026
TIDE: Text-Informed Dynamic Extrapolation with Step-Aware Temperature Control for Diffusion Transformers
Yihua Liu, Fanjiang Ye, Bowen Lin +2
Diffusion Transformer (DiT) faces challenges when generating images with higher resolution compared at training resolution, causing especially structural degradation due to attenti…
cs.CV2026
SDiT: Semantic Region-Adaptive for Diffusion Transformers
Bowen Lin, Fanjiang Ye, Yihua Liu +7
Diffusion Transformers (DiTs) achieve state-of-the-art performance in text-to-image synthesis but remain computationally expensive due to the iterative nature of denoising and the…