Awesome World Model Hub Papers · Datasets · Projects
← Back to papers

Latent Spatial Memory for Video World Models

arXiv 2026 56.6 method

TLDR

Introduces latent spatial memory for video world models, storing 3D scene info in diffusion latent space, achieving faster generation and reduced memory.

Reasoning

The paper presents a novel method (Mirage) that avoids pixel-space reconstruction, showing significant speed and memory improvements. Strengths include clear methodology and strong empirical results on benchmarks; weaknesses are limited scope to video generation without explicit interaction or RL context.

Read-first score

Read-first score 56.6, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 39.

Recency 6%
100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Citation impact 18%
94.5

Uses OpenAlex-shaped citation metadata as a bibliometric attention signal, separate from paper quality. citation_normalized_percentile=0.94468804

Methodology quality 18%
70

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=baseline,experiment,metric

Topical relevance 29%
55.7

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Reproducibility 18%
30

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=none

Citation velocity 12%
0

Citation velocity estimates citations per publication-year to reduce old-paper bias. velocity=0.00

Field roles

FoundationFrontierBridgeMethodology anchor

Rank sensitivity

Stability: volatile; rank range: 440.

Keyword Scores

video world model
10
world model
9
generative world model
8
world simulator
6
world dynamics prediction
5
interactive world model
1
model-based reinforcement learning world model
0

Deep Analysis

Innovations

  • Latent spatial memory that stores scene information directly in diffusion latent space, avoiding pixel-space reconstruction and its associated information loss and computational cost.
  • Depth-guided back-projection to lift latent tokens into 3D and direct latent-space warping for novel view synthesis, forming a unified latent-space spatial memory framework (Mirage).
  • Elimination of the round trip through pixel space, reducing both information loss and the computational burden of repeated rendering and VAE encoding.

Methodology

Mirage constructs a persistent 3D cache by lifting latent tokens from a diffusion model into 3D using depth-guided back-projection, and queries this memory by synthesizing novel views through direct latent-space warping. This avoids explicit point cloud memory in RGB space and the associated rendering and encoding steps.

Key Results

Latent spatial memory achieves up to 10.57× faster end-to-end video generation and 55× reduction in memory footprint relative to explicit 3D baselines. Mirage attains state-of-the-art performance on WorldScore and strong reconstruction quality on RealEstate10K.

Tags

video world modelslatent spatial memory3D consistencydiffusion modelsnovel view synthesisCV