History Forcing: Distilling History-Dependent Continuations for Long-Horizon Video World Models
cs.CV
Submitted: 2026-11-02
Updated: 2026-11-02
Code: https://github.com/ziplab/History-Forcing
Project page: https://ziplab.github.io/History-Forcing-Project-Page
Terminology
Sources
- Cosmos World Foundation Model Platform for Physical AI
- Context-Matched Distillation: Teacher Causality for Autoregressive Video Distillation
- Echo-Infinity: Learning Evolving Memory for Real-Time Infinite Video Generation
- Mode Seeking meets Mean Seeking for Fast Long Video Generation
- Data-Forcing Distillation: Restoring Diversity and Fidelity in Few-Step Video Generation
- Context Forcing: Consistent Autoregressive Video Generation with Long Context
- LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation
- PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives
- LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models
- One-Forcing: Towards Stable One-Step Autoregressive Video Generation
- Advancing Open-source World Models
- Long-Context Autoregressive Video Modeling with Next-Frame Prediction
- LTX-Video: Realtime Video Latent Diffusion
- Matrix-game 2.0: An open-source, real-time, and streaming interactive world model
- Classifier-Free Diffusion Guidance
- Memory Forcing: Spatio-Temporal Memory for Consistent Scene Generation on Minecraft
- HunyuanVideo: A Systematic Framework For Large Video Generative Models
- Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition
- Flow Matching for Generative Modeling
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