Visual Synthesis on 4D World Modeling
0.684IQWan-2.1-I2V-14B
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| Wan-2.1-I2V-14BModel category=Video Generation Models2026.07 | 0.684 | 0.988 | 0.891 | 0.956 | 0.536 | 12.72 | 0.568 | |
| 4DNeXModel category=4D World Models2026.07 | 0.637 | 0.994 | 0.917 | 0.986 | 0.649 | 14.47 | 0.404 | |
| RynnWorld-4DModel category=4D World Models2026.07 | 0.635 | 0.995 | 0.957 | 0.992 | 0.754 | 17.85 | 0.269 | |
| w/o RoPE in JAAblation configuration=w/o RoPE in JA2026.07 | 0.628 | 0.99 | 0.935 | 0.98 | 0.71 | 17.1 | 0.295 | |
| w/o MAAblation configuration=w/o MA2026.07 | 0.621 | 0.992 | 0.952 | 0.975 | 0.699 | 17.85 | 0.303 | |
| shared FFNAblation configuration=shared FFN2026.07 | 0.618 | 0.985 | 0.902 | 0.965 | 0.695 | 16.5 | 0.32 | |
| w/o 4D Pre-trainingAblation configuration=w/o 4D Pre-training2026.07 | 0.615 | 0.982 | 0.879 | 0.938 | 0.651 | 16.25 | 0.344 | |
| Independent BranchesAblation configuration=Independent Branches2026.07 | 0.613 | 0.986 | 0.922 | 0.971 | 0.683 | 17.26 | 0.346 | |
| TesserActModel category=4D World Models2026.07 | 0.608 | 0.992 | 0.904 | 0.956 | 0.693 | 16.91 | 0.335 | |
| CogVideoXModel category=Video Generation Models2026.07 | 0.604 | 0.976 | 0.866 | 0.917 | 0.534 | 12.17 | 0.577 | |
| Wan-2.2-TI2V-5BModel category=Video Generation Models2026.07 | 0.555 | 0.97 | 0.886 | 0.909 | 0.593 | 14.54 | 0.489 | |
| Free4DModel category=4D World Models2026.07 | 0.354 | 0.993 | 0.787 | 0.848 | 0.492 | 12.4 | 0.597 |