Multimodal coding agents decouple 4D world construction from visual generation, repurposing video models from world generators toward generative renderers. This division of labor raises a fundamental question: if code builds the world, can video models just render it? A reliable generative renderer hinges on two complementary criteria: (i) world preservation, retaining prescribed 4D kinematics and camera paths; and (ii) visual realization, persistently binding text-specified target attributes over time. To evaluate this capability, we introduce WorldDraft, a benchmark of 432 strictly paired test cases across 48 executable 4D world families spanning six dynamic challenge categories. Under a 3×3 factorial design, WorldDraft orthogonally crosses draft granularity (abstract proxy to previs) and appearance alignment (neutral to conflicting) under identical dynamics. Extensive evaluations across 12 representative models reveal that: (I) world preservation and visual realization remain in stark operational tension; (II) richer draft scaffolding anchors structure but paradoxically impairs appearance fidelity; and (III) conflicting source cues trigger severe source leakage (up to 64%), exposing fragile cross-modal disentanglement. To mitigate these bottlenecks, we propose WorldDraft-Primer, a plug-and-play visual prompting strategy that consistently improves both objectives across frozen video renderers. Together, WorldDraft and WorldDraft-Primer lay a foundation for bridging programmatic 4D simulation with video generation, advancing physically grounded generative rendering.
Figures & tables
Figure 1: Performance overview of 12 video models on WorldDraft across 3 dimensions.
Figure 2: Overview of WorldDraft . ( a ) Six challenge categories across 48 executable 4D worlds (shown at P1,AA ). ( b ) 3×3 factorial grid crossing draft granularity ( P0→P2 ) and appearance alignment ( AN,AA,AC ). ( c ) Full benchmark totaling 48×3×3=432 cases.
Figure 3: Overview of our proposed ( Top ) WorldDraft benchmark and ( Bottom ) WorldDraft-Primer strategy.
Model
Size
Rendering Performance
Granularity Gains
Conflict Robustness
Overall ↑
Preservation ↑
Realization ↑
Quality ↑
Persistence ↑
Structure ↑
Appearance ↑
Binding ↑
Adherence ↑
Retention ↑
Penalty ↓
Leakage ↓
Open-Weight Models
OmniWeaving
8.3B
61.61
66.37
62.02
58.01
+12.75
-14.47
-15.95
58.13
47.68
10.63
50.97
57.62
UniVideo
13B
53.34
67.31
63.01
59.10
+15.61
-4.24
-7.43
63.39
51.78
6.02
52.24
57.82
VINO
13B
52.83
67.95
63.43
60.38
+15.99
-2.70
-5.21
67.34
56.75
3.57
38.26
59.78
Wan2.1-VACE
14B
60.97
60.86
60.78
51.68
+18.82
-2.89
-2.68
60.93
50.37
8.05
64.17
56.89
Table 1: Main results on WorldDraft . We highlight the best and second best scores ( ↑/↓ : higher/lower is better). Rendering Performance averages the full 3×3 grid; Granularity Gains measure P0→P2 changes under AN ; Conflict Robustness is evaluated at P1 under AC . Overall weights the three perspectives by 0.50/0.25/0.25 (details in Appendix B ).
Figure 4: Failure cases demonstration of LynnReal-Omni and Seedance 2.5 across the 3×3 grid on: ( a ) C05 ( Occlusion & Reappearance , warehouse forklift) and ( b ) A04 ( Multi-Entity Orchestration , 12-sailboat fleet). More case studies are in https://haroldchen19.github.io/WorldDraft-site .
Model
Rendering Performance
Granularity Gains
Conflict Robustness
Overall ↑
Preservation ↑
Realization ↑
Quality ↑
Persistence ↑
Structure ↑
Appearance ↑
Binding ↑
Adherence ↑
Retention ↑
Penalty ↓
Leakage ↓
LynnReal-Omni
60.52
75.51
65.48
68.41
+7.26
-3.62
-5.28
75.32
68.05
2.26
30.54
64.89
Seedance 2.5
58.66
75.55
63.10
69.20
+10.88
+2.51
+3.21
76.60
69.53
1.97
41.57
64.73
OmniWeaving
61.61
66.37
62.02
58.01
+12.75
-14.47
-15.95
58.13
47.68
10.63
50.97
57.62
+ Text PE
62.63
67.98
63.46
59.36
+12.98
-14.81
-16.32
60.06
48.79
10.30
49.79
58.52
+ WorldDraft-Primer
64.60
70.93
66.19
61.90
+13.51
-15.45
-17.02
62.97
50.88
10.41
47.55
60.13
Table 2: Evaluation on WorldDraft with WorldDraft-Primer . We bold the best results. Qualitative results are in Figures 13 and 14 .
Appendix figures & tables10 assets
Supplementary material from the paper’s appendix.
Appendix
Figure 5: Data demonstration of I. Multi-Entity Orchestration.
Figure 6: Data demonstration of II. Multi-Stage Dynamics.
Figure 7: Data demonstration of III. Occlusion & Reappearance.
Figure 8: Data demonstration of IV. Camera Motion.
Figure 9: Data demonstration of V. Non-Rigid Deformation.
Figure 10: Data demonstration of VI. Hybrid Interactions.
Figure 11: Metric-human alignment. Agreement between automated VLM judgments and five-annotator human consensus across sampled cases, averaging 91.0% across all six metrics.
Figure 12: Component ablation of WorldDraft-Primer on MiniMax-H3.
Current world models for explicit world simulation typically follow two distinct pathways: (1) video generative models (e.g., Sora), which simulate realistic appearances but fail to preserve 3D consistency; and (2) 3D generative models (e.g., Marble), which generate geometrically consistent scenes but often yield static, less realistic observations. We present AEON, a unified framework that bridges video-based and 3D-based world models and combines the benefits of both. The key insight of AEON lies in a generative model that operates within the text- or image-conditioned video latent space while producing renderable 4D graphics primitives---specifically, 4D Gaussian Splatting (4DGS)---as the explicit world representation. We train a 4D reconstruction model to predict both 4DGS and camera poses from monocular videos, serving as our initialized 4D decoder. Furthermore, we design a domain adapter that translates generative video latents into reconstructive 4D latents through a distillation process on the video VAE. AEON naturally supports video-based world modeling by rendering 4DGS at predicted camera trajectories, and constructs a persistent 4D environment with scene dynamics for realistic world simulation. Consequently, AEON empowers a diverse range of world modeling applications and achieves state-of-the-art performance on standard benchmarks. Project Page: https://weiqi-zhang.github.io/AEON
Weiqi Zhang, Wenyuan Zhang, Yu-Shen Liu +1
School of Software, Tsinghua University, Beijing, China
We introduce CoDeR, a new paradigm for world modeling. Unlike existing video world models that implicitly represent world dynamics through visual observations, our system explicitly constructs an executable world with code and employs video generation models for visual realization. Specifically, we coordinate five complementary roles to translate high-level concepts into structured world rules, executable dynamics, and perceptual observations. This design enables long-term memory, open-ended interactions, autonomous world evolution, and multi-agent scenarios, where multiple entities can act, interact, and evolve persistently beyond the current observation. Extensive experiments demonstrate that our framework substantially extends the capabilities of existing world models, enabling long-term memory, open-ended interactions, autonomous evolution, and persistent multi-agent dynamics, while achieving state-of-the-art performance across multiple evaluation settings. Code and model weights will be made publicly available. Project Page: CoDeR.
Despite impressive progress in video generation, existing models remain limited to surface-level plausibility, lacking a coherent and unified understanding of the world. Prior approaches typically incorporate only a single form of world-related knowledge or rely on rigid alignment strategies to introduce additional knowledge. However, aligning the single world knowledge is insufficient to constitute a world model that requires jointly modeling multiple heterogeneous dimensions (e.g., physical commonsense, 3D and temporal consistency). To address this limitation, we introduce DreamWorld, a unified framework that integrates complementary world knowledge into video generators via a Joint World Modeling Paradigm, jointly predicting video pixels and features from foundation models to capture temporal dynamics, spatial geometry, and semantic consistency. However, naively optimizing these heterogeneous objectives can lead to visual instability and temporal flickering. To mitigate this issue, we propose Consistent Constraint Annealing (CCA) to progressively regulate world-level constraints during training, and Multi-Source Inner-Guidance to enforce learned world priors at inference. Extensive evaluations show that DreamWorld improves world consistency, outperforming Wan2.1 by 2.26 points on VBench. Code will be made publicly available at \href{https://github.com/ABU121111/DreamWorld}{\textcolor{mypink}{**Github**}}.
Boming Tan, Xiangdong Zhang, Ning Liao +7
University of Science and Technology of China, Hefei, China · Shanghai Jiao Tong University, Shanghai, China