LongTake: Learning to Sustain Dynamics in Long-Horizon Video Generation

arXiv:2609.38562 · cs.CV · Submitted 2026-09-29 · Read on arXiv

cs.CV

Submitted: 2026-09-29

Updated: 2026-09-29

Project page: https://bw-park.github.io/LongTake

Terminology

• Distillation — 37× in this paper · explained in 2 episodes
• Consistency — 14× in this paper · explained in 3 episodes
• Diffusion Model — 10× in this paper · explained in 8 episodes
• Distribution Matching — 9× in this paper · explained in 2 episodes
• Transformer — 9× in this paper · explained in 2 episodes
• Two-stage training — 7× in this paper · explained in 2 episodes
• Conference on Computer Vision and Pattern Recognition — 6× in this paper
• Diffusion Models — 6× in this paper · explained in 6 episodes
• Consistency Distillation — 5× in this paper · explained in 2 episodes
• Teacher Forcing — 5× in this paper
• World Model — 5× in this paper · explained in 7 episodes
• Benchmark — 4× in this paper · explained in 2 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Generative Model — 3× in this paper · explained in 2 episodes
• Generative Models — 3× in this paper · explained in 3 episodes
• Aggregation — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Flow Matching — 2× in this paper · explained in 8 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• CVF International Conference on Computer Vision — 1× in this paper
• Embeddings — 1× in this paper · explained in 2 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Temporal consistency — 1× in this paper · explained in 2 episodes

Sources

• Context-Matched Distillation: Teacher Causality for Autoregressive Video Distillation
• SkyReels-V2: Infinite-length Film Generative Model
• AdaState: Self-Evolving Anchors for Streaming Video Generation
• RELIC: Interactive Video World Model with Long-Horizon Memory
• Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length
• Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation
• HunyuanVideo: A Systematic Framework For Large Video Generative Models
• Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion
• Movie Gen: A Cast of Media Foundation Models
• Hunyuan-GameCraft-2: Instruction-following Interactive Game World Model
• MAGI-1: Autoregressive Video Generation at Scale
• Wan: Open and Advanced Large-Scale Video Generative Models
• Knot Forcing: Taming Autoregressive Video Diffusion Models for Real-time Infinite Interactive Portrait Animation
• Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation
• Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation
• Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models
• Self Gradient Forcing: Native Long Video Extrapolation

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