Trajectory Forcing: Exploiting Diffusion Trajectories for Autoregressive Long Video Generation
cs.CV
Submitted: 2026-11-06
Updated: 2026-11-06
Project page: https://wangbohan97.github.io/Trajectory-Forcing/Abstract
Terminology
Sources
- SkyReels-V2: Infinite-length Film Generative Model
- Self-Forcing++: Towards Minute-Scale High-Quality Video Generation
- Autoregressive Video Generation without Vector Quantization
- End-to-End Training for Autoregressive Video Diffusion via Self-Resampling
- LTX-Video: Realtime Video Latent Diffusion
- VideoScore2: Think before You Score in Generative Video Evaluation
- Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion
- Pyramidal Flow Matching for Efficient Video Generative Modeling
- Rolling Forcing: Autoregressive Long Video Diffusion in Real Time
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- BAgger: Backwards Aggregation for Mitigating Drift in Autoregressive Video Diffusion Models
- Movie Gen: A Cast of Media Foundation Models
- Qwen2.5 Technical Report
- History-Guided Video Diffusion
- Wan: Open and Advanced Large-Scale Video Generative Models
- MAGI-1: Autoregressive Video Generation at Scale
- Demystifying Video Reasoning
- Pack and Force Your Memory: Long-form and Consistent Video Generation
- LongLive: Real-time Interactive Long Video Generation
- Yan: Foundational Interactive Video Generation
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs