DreamX-World 1.0: A General-Purpose Interactive World Model

arXiv 2026 61.1 method, system

TLDR

DreamX-World 1.0 is a general-purpose interactive world model for controllable long-horizon video generation with camera and event control.

Reasoning

The paper presents a comprehensive system with novel components like E-PRoPE and memory-conditioned scene persistence, and uses diverse data sources including real-world videos. However, the abstract lacks explicit quantitative results or comparisons, and the claim of 'general-purpose' may be overstated without broader evaluation.

Read-first score

Read-first score 61.1, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 54.

Recency 6%

100

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

Citation impact 18%

94.2

Uses OpenAlex-shaped citation metadata as a bibliometric attention signal, separate from paper quality. citation_normalized_percentile=0.94171295

Topical relevance 29%

77.1

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

Methodology quality 18%

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

Reproducibility 18%

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

Citation velocity 12%

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

Field roles

FoundationFrontierBridge

Rank sensitivity

Stability: volatile; rank range: 479.

Keyword Scores

world model

interactive world model

generative world model

video world model

world dynamics prediction

world simulator

model-based reinforcement learning world model

Deep Analysis

Innovations

E-PRoPE: a lightweight variant of projective positional encoding that retains PRoPE's projective camera geometry while applying camera-aware attention to spatially reduced tokens
Conversion of a bidirectional video generator into a few-step autoregressive world model using causal forcing, DMD-style distillation, and long-rollout training
Memory-Conditioned Scene Persistence: retrieves earlier views through camera-geometry-based retrieval
Residual recycling: makes the conditioning path less sensitive to imperfect memory latents
Event Instruction Tuning: adds composable event control
Reinforcement learning alignment: recovers camera control and visual quality after distillation
Mixed-precision DiT execution, residual reuse, 75%-pruned VAE decoding, and asynchronous pipeline parallelism for real-time inference (up to 16 FPS on eight RTX 5090 GPUs)

Methodology

DreamX-World 1.0 is a general-purpose interactive text/image-to-video world model. It uses a data engine combining camera-accurate Unreal Engine rendering, action-rich gameplay recordings, and real-world videos with recovered camera geometry. The model converts a bidirectional video generator into a few-step autoregressive world model via causal forcing, DMD-style distillation, and long-rollout training on self-generated long-horizon contexts. Evaluation is performed on a 5-second basic evaluation benchmark with camera-control and overall scores.

Key Results

On the 5-second basic evaluation, DreamX-World 1.0 achieves a camera-control score of 73.75 and an overall score of 84.76, outperforming HY-WorldPlay 1.5 (80.79) and LingBot-World (80.45) in overall score.

Resources

Paper