AnyFlow enables any-step video diffusion by distilling flow-map transitions over arbitrary time intervals with on-policy backward simulation.
From slow bidirectional to fast autoregressive video diffusion models
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 5roles
baseline 1polarities
baseline 1representative citing papers
StreamingEffect enables real-time 720p human-centric video effect generation on one GPU via teacher-student distillation, keyframe control, and a new 130K video dataset.
Self-Forcing++ scales autoregressive video diffusion to over 4 minutes by using self-generated segments for guidance, reducing error accumulation and outperforming baselines in fidelity and consistency.
Self Forcing trains autoregressive video diffusion models by performing autoregressive rollout with KV caching during training to close the exposure bias gap, using a holistic video-level loss and few-step diffusion for efficiency.
A 14B-parameter mixture-of-experts world model is distilled to a four-step autoregressive generator and claimed to deliver camera-controllable video at up to 50 FPS on NPUs with 30-50% of prior inference cost.
citing papers explorer
-
AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
AnyFlow enables any-step video diffusion by distilling flow-map transitions over arbitrary time intervals with on-policy backward simulation.
-
StreamingEffect: Real-Time Human-Centric Video Effect Generation
StreamingEffect enables real-time 720p human-centric video effect generation on one GPU via teacher-student distillation, keyframe control, and a new 130K video dataset.
-
Self-Forcing++: Towards Minute-Scale High-Quality Video Generation
Self-Forcing++ scales autoregressive video diffusion to over 4 minutes by using self-generated segments for guidance, reducing error accumulation and outperforming baselines in fidelity and consistency.
-
Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion
Self Forcing trains autoregressive video diffusion models by performing autoregressive rollout with KV caching during training to close the exposure bias gap, using a holistic video-level loss and few-step diffusion for efficiency.
-
MoWorld: A Flash World Model
A 14B-parameter mixture-of-experts world model is distilled to a four-step autoregressive generator and claimed to deliver camera-controllable video at up to 50 FPS on NPUs with 30-50% of prior inference cost.