A survey that groups efficient video diffusion methods into four paradigms—step distillation, efficient attention, model compression, and cache/trajectory optimization—and outlines open challenges for practical use.
Arlon: Boosting diffusion transformers with autoregressive models for long video generation
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
fields
cs.CV 8roles
background 3representative citing papers
DisCo uses discrete action primitives for camera control in video world models to achieve more reliable action following than continuous trajectories.
Lumos-Nexus is a training-efficient video generation framework using two-stage alignment of a lightweight model followed by progressive frequency bridging to a high-fidelity generator in homogeneous latent space, plus the new VR-Bench for reasoning evaluation.
Stream-T1 is a test-time scaling framework for streaming video generation using scaled noise propagation from history, reward pruning across short and long windows, and feedback-guided memory sinking to improve temporal consistency and visual quality.
AdaCluster delivers a training-free adaptive query-key clustering framework for sparse attention in video DiTs, yielding 1.67-4.31x inference speedup with negligible quality loss on CogVideoX-2B, HunyuanVideo, and Wan-2.1.
Rolling Forcing generates multi-minute videos in real time by jointly denoising frames at increasing noise levels, anchoring attention to early frames, and using windowed distillation to limit error accumulation.
A geometry-aware 4D video generation model trained with cross-view pointmap alignment to produce spatio-temporally consistent future videos from novel viewpoints for robot manipulation.
VRAG improves long-horizon interactive video generation by conditioning autoregressive diffusion on retrieved historical frames and explicit global state, outperforming long-context baselines on the tested Minecraft and RealEstate10K benchmarks.
citing papers explorer
-
Efficient Video Diffusion Models: Advancements and Challenges
A survey that groups efficient video diffusion methods into four paradigms—step distillation, efficient attention, model compression, and cache/trajectory optimization—and outlines open challenges for practical use.
-
DisCo: World Models with Discrete Camera Motion Control
DisCo uses discrete action primitives for camera control in video world models to achieve more reliable action following than continuous trajectories.
-
Lumos-Nexus: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified Models
Lumos-Nexus is a training-efficient video generation framework using two-stage alignment of a lightweight model followed by progressive frequency bridging to a high-fidelity generator in homogeneous latent space, plus the new VR-Bench for reasoning evaluation.
-
Stream-T1: Test-Time Scaling for Streaming Video Generation
Stream-T1 is a test-time scaling framework for streaming video generation using scaled noise propagation from history, reward pruning across short and long windows, and feedback-guided memory sinking to improve temporal consistency and visual quality.
-
AdaCluster: Adaptive Query-Key Clustering for Sparse Attention in Video Generation
AdaCluster delivers a training-free adaptive query-key clustering framework for sparse attention in video DiTs, yielding 1.67-4.31x inference speedup with negligible quality loss on CogVideoX-2B, HunyuanVideo, and Wan-2.1.
-
Rolling Forcing: Autoregressive Long Video Diffusion in Real Time
Rolling Forcing generates multi-minute videos in real time by jointly denoising frames at increasing noise levels, anchoring attention to early frames, and using windowed distillation to limit error accumulation.
-
Geometry-aware 4D Video Generation for Robot Manipulation
A geometry-aware 4D video generation model trained with cross-view pointmap alignment to produce spatio-temporally consistent future videos from novel viewpoints for robot manipulation.
-
VRAG: Learning World Models for Interactive Video Generation
VRAG improves long-horizon interactive video generation by conditioning autoregressive diffusion on retrieved historical frames and explicit global state, outperforming long-context baselines on the tested Minecraft and RealEstate10K benchmarks.