Memorizon: Training World Models Beyond Their Context Window

arXiv:2610.00544 · cs.CV · Submitted 2026-09-30 · Read on arXiv

cs.CV

Submitted: 2026-09-30

Updated: 2026-09-30

Project page: https://tingtingliao.github.io/memorizon

Terminology

• World Model — 32× in this paper · explained in 7 episodes
• Consistency — 11× in this paper · explained in 3 episodes
• Ablation — 9× in this paper · explained in 1 episode
• Transformer — 7× in this paper · explained in 2 episodes
• Distillation — 5× in this paper · explained in 2 episodes
• Computer Vision and Pattern Recognition — 4× in this paper
• Sparse Attention — 4× in this paper · explained in 5 episodes
• Trace — 3× in this paper · explained in 2 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Diffusion Model — 2× in this paper · explained in 8 episodes
• Diffusion Models — 2× in this paper · explained in 6 episodes
• Exposure Bias — 2× in this paper · explained in 2 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• Generative Model — 2× in this paper · explained in 2 episodes
• Generative Models — 2× in this paper · explained in 2 episodes
• In International Conference on Learning Representations — 2× in this paper
• Alignment — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• CVF International Conference on Computer Vision — 1× in this paper
• Calibration — 1× in this paper · explained in 7 episodes
• Distribution Matching — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• KV cache — 1× in this paper · explained in 3 episodes

Sources

• Mixture of Contexts for Long Video Generation
• DreamX-World 1.0: A General-Purpose Interactive World Model
• Infinite Worlds with Versatile Interactions
• Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation
• End-to-End Training for Autoregressive Video Diffusion via Self-Resampling
• Matrix-game 2.0: An open-source, real-time, and streaming interactive world model
• RELIC: Interactive Video World Model with Long-Horizon Memory
• Memory Forcing: Spatio-Temporal Memory for Consistent Scene Generation on Minecraft
• World Model on Million-Length Video And Language With Blockwise RingAttention
• PAN: A World Model for General, Actionable, and Long-Horizon World Simulation
• Closing the Loop: Training-Free Revisit Consistency for Autoregressive Generative Rendering
• Yume-1.5: A Text-Controlled Interactive World Generation Model
• TetherCache: Stabilizing Autoregressive Long-Form Video Generation with Gated Recall and Trusted Alignment
• Compression and Retrieval: Implicit Memory Retrieval for Video World Models
• Advancing Open-source World Models
• WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling
• Wan: Open and Advanced Large-Scale Video Generative Models
• Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory
• Infinite-World: Scaling Interactive World Models to 1000-Frame Horizons via Pose-Free Hierarchical Memory
• Video World Models with Long-term Spatial Memory

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