Video Multi-modal Multi-task Understanding on VideoMMMU
46.3ScoreEchoPrune
Evaluation Results
| Method | Links | |
|---|---|---|
| EchoPruneNumber of Frames (F)=320, Compression Ratio=20x, Token Budget=5% (ultra)2026.05 | 46.3 |
| Method | Links | |
|---|---|---|
| EchoPruneNumber of Frames (F)=320, Compression Ratio=20x, Token Budget=5% (ultra)2026.05 | 46.3 |