Long-Horizon Video Generation

Overview

Long-horizon video generation studies how to extend generated videos across many scenes or minutes of streaming while preserving subjects, environments, motion, and events. Common approaches include autoregressive diffusion with compressed or retrieved memory, sparse KV-cache policies, training on model-generated rollouts, and geometry- or action-conditioned world models. These methods support multi-shot storytelling, interactive world simulation, and camera-controlled exploration, with benchmarks such as VBench-Long testing consistency, visual quality, and control over extended rollouts. A central tension is balancing persistent memory and natural motion with bounded compute, especially when models trained on short clips must remain stable far beyond their training horizon.

Latest papers

CardsList

186 papers21 papers in the last four weeks, down 42% on the four weeks before. 0.2% of all new papers.

  1. End-to-End Training for Autoregressive Video Diffusion via Self-Resampling

    Dec 17, 2025Yuwei Guo, Ceyuan Yang, Hao He +5Video Diffusion ModelsAutoregressive Diffusion

  2. BIFE: Better Interaction, Fewer Errors for Minute-Long Video Generation

    Nov 28, 2025Zeyu Zhang, Jinyuan Mao, Shuning Chang +5Long-Horizon Video GenerationAutoregressive Video Generation

  3. Compact Attention: Exploiting Structured Spatio-Temporal Sparsity for Fast Video Generation

    Aug 18, 2025Qirui Li, Guangcong Zheng, Qi Zhao +6Efficient Video GenerationSpatio-Temporal Attention