Video Generation on VideoPhy v1 (test)
73Overall SALaMo-5B (Ours)
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| LaMo-5B (Ours)Extra Supervision=Self-supervised2026.05 | 73 | 62.9 | 26.6 | 80.8 | 41.1 | 78.2 | 78.2 | 41 | |
| MoAlign-5B (reimpl.)Extra Supervision=VideoMAE2026.05 | 72.2 | 62.5 | 26.3 | 79.6 | 38.4 | 78 | 76.2 | 39.4 | |
| VideoREPA-5BExtra Supervision=VideoMAEv22026.05 | 72.1 | 58 | 28 | 82.9 | 39 | 80 | 74.5 | 40.1 | |
| CogVideoX-5BExtra Supervision=-2026.05 | 70 | 62.9 | 19.6 | 76 | 33.6 | 72.7 | 61.8 | 32.3 | |
| LaMo-2B (Ours)Extra Supervision=Self-supervised2026.05 | 67.2 | 58.7 | 16.8 | 74.7 | 32.2 | 69.1 | 67.3 | 31.4 | |
| WISA-5BExtra Supervision=Qwen2VL2026.05 | 67 | — | — | — | — | — | — | 38 | |
| MoAlign-2B (reimpl.)Extra Supervision=VideoMAE2026.05 | 64.5 | 54.6 | 18.3 | 73.5 | 31.9 | 66.2 | 55.7 | 30.1 | |
| VideoREPA-2BExtra Supervision=VideoMAEv22026.05 | 64.2 | 52.4 | 18.2 | 77.4 | 32.2 | 60 | 52.7 | 29.7 | |
| PhyT2V-5BExtra Supervision=o1-preview2026.05 | 61 | — | — | — | — | — | — | 37 | |
| CogVideoX-2BExtra Supervision=-2026.05 | 60.5 | 49.6 | 13.3 | 71.2 | 28.1 | 60 | 50.9 | 25.6 | |
| DreamWorld-1.3BExtra Supervision=VGGT, DINOv22026.05 | 52.9 | 54.5 | 24.5 | 48.6 | 25.4 | 60.1 | 32.7 | 26.2 | |
| MoAlign-2B (paper)Extra Supervision=VideoMAE2026.05 | 49.3 | 24.7 | 31.7 | 66.9 | 40.7 | 67.3 | 56.4 | 39.4 | |
| PHANTOM-5BExtra Supervision=V-JEPA22026.05 | 47.5 | — | — | — | — | — | — | 37.9 |