Honeycomb: Constant-Size Scene Memory Representation for Video World Models

arXiv:2609.37690 · cs.CV · Submitted 2026-09-29 · Read on arXiv

cs.CV

Submitted: 2026-09-29

Updated: 2026-09-30

Terminology

• World Model — 26× in this paper · explained in 7 episodes
• Consistency — 13× in this paper · explained in 3 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Diffusion Model — 5× in this paper · explained in 8 episodes
• Benchmark — 4× in this paper · explained in 2 episodes
• Transformer — 4× in this paper · explained in 2 episodes
• Benchmarking — 3× in this paper · explained in 3 episodes
• Diffusion Models — 3× in this paper · explained in 6 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Action-Conditioned World Model — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• Optical Flow — 1× in this paper · explained in 2 episodes
• Tokenization — 1× in this paper · explained in 2 episodes

Sources

• MemoBench: Benchmarking World Modeling in Dynamically Changing Environments
• Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models
• LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models
• Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation
• ViPE: Video Pose Engine for 3D Geometric Perception
• MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens
• ReRoPE: Repurposing RoPE for Relative Camera Control
• LoopNav: Benchmarking Spatial Consistency in World Models
• UNIVERSE: Unified Video Action Models for Autonomous Driving with Flexible Mask-Modulated Modality Generation
• Current World Models Lack a Persistent State Core
• Out of Sight, Out of Mind? Evaluating State Evolution in Video World Models
• Wan: Open and Advanced Large-Scale Video Generative Models
• EvoWorld: Evolving Panoramic World Generation with Explicit 3D Memory
• Latent Spatial Memory for Video World Models
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Geometry-Aware Implicit Memory for Video World Models
• Infinite-World: Scaling Interactive World Models to 1000-Frame Horizons via Pose-Free Hierarchical Memory
• Addressable Memory for Video World Models
• CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation

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