Glance Forcing: Making Bidirectional Diffusion Autoregressive at a Glance
Glance Forcing distills causal video diffusion with one PF-ODE trajectory and dual slow-fast experts.
Stories per day · 30 days
1 RSS
Relatedautoregressive2distillation2diffusion1glance-forcing1repforcing1video-diffusion1video-generation1world-models1
7 stories, newest first · one card per story
Stories tagged #vbench
RepForcing: Representation-Space Initialization for Autoregressive Video Distillation
RepForcing improves four-step autoregressive video distillation using representation-space initialization before DMD.
GRACE: Generation-aware latent compression for efficient video generation
GRACE cuts Wan2.1-I2V-14B video tokens 8x and latency 11.1x without losing VBench quality.
SoL-Refiner: Speed-of-Light One-Step Refinement for High-Resolution Video
SoL-Refiner converts low-resolution outputs into 4K video in one denoising step, beating multi-step refiners.
PDMD: Projected Distribution Matching Distillation for Video Diffusion Models
PDMD stabilizes video diffusion distillation by filtering critic errors, beating DMD at 4 NFE.
In-Flight KV Cache with Clean Anchors for Faster Autoregressive Video Diffusion
FlashForward reuses in-flight KV caches and clean anchors to speed long autoregressive video diffusion.
ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation
ViRDM post-trains few-step causal video generators without a teacher, scoring 84.87 on VBench.