Rollout-Marginal Distillation for Long-Horizon Autoregressive Video Generation

arXiv:2609.37925 · cs.CV, cs.AI · Submitted 2026-09-29 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-09-29

Updated: 2026-09-29

Project page: https://cjeen.github.io/RMD

Terminology

• Distillation — 28× in this paper · explained in 2 episodes
• Consistency — 13× in this paper · explained in 3 episodes
• Distribution Matching — 13× in this paper · explained in 2 episodes
• Rollout-Marginal Distillation — 7× in this paper
• Diffusion Model — 6× in this paper · explained in 8 episodes
• Temporal consistency — 6× in this paper · explained in 2 episodes
• Conference on Computer Vision and Pattern Recognition — 4× in this paper
• Ablation — 3× in this paper · explained in 1 episode
• World Model — 3× in this paper · explained in 7 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Context-Matched Distillation — 2× in this paper
• Diffusion Models — 2× in this paper · explained in 6 episodes
• Regularization — 2× in this paper · explained in 3 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Computational overhead — 1× in this paper · explained in 2 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Diffusion Process — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Optimal Transport — 1× in this paper · explained in 5 episodes
• Self-Distillation — 1× in this paper · explained in 7 episodes

Sources

• Context-Matched Distillation: Teacher Causality for Autoregressive Video Distillation
• Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion
• OPSD-V: On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators
• Solaris: Building a Multiplayer Video World Model in Minecraft
• Wan: Open and Advanced Large-Scale Video Generative Models
• Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models