Image Understanding on MMBCN
60.6ScoreVanilla
Evaluation Results
| Method | Links | |
|---|---|---|
| VanillaBackbone=LLaVA-NeXT-7B, Retained Tokens=2880, Token Retention Ratio=100%2026.06 | 60.6 | |
| ApETBackbone=LLaVA-NeXT-7B, Retained Tokens=640, Token Retention Ratio=↓ 77.8%2026.06 | 59.3 | |
| EvoCutBackbone=LLaVA-NeXT-7B, Retained Tokens=640, Token Retention Ratio=↓ 77.8%2026.06 | 59.2 | |
| PDropBackbone=LLaVA-NeXT-7B, Retained Tokens=640, Token Retention Ratio=↓ 77.8%2026.06 | 58.5 | |
| VisionZipBackbone=LLaVA-NeXT-7B, Retained Tokens=640, Token Retention Ratio=↓ 77.8%2026.06 | 57.8 | |
| EvoCutBackbone=LLaVA-NeXT-7B, Retained Tokens=320, Token Retention Ratio=↓ 88.9%2026.06 | 56.9 | |
| ApETBackbone=LLaVA-NeXT-7B, Retained Tokens=320, Token Retention Ratio=↓ 88.9%2026.06 | 56.6 | |
| PDropBackbone=LLaVA-NeXT-7B, Retained Tokens=320, Token Retention Ratio=↓ 88.9%2026.06 | 56.2 | |
| VisionZipBackbone=LLaVA-NeXT-7B, Retained Tokens=320, Token Retention Ratio=↓ 88.9%2026.06 | 55.3 | |
| PDropBackbone=LLaVA-NeXT-7B, Retained Tokens=160, Token Retention Ratio=↓ 94.4%2026.06 | 54.9 | |
| EvoCutBackbone=LLaVA-NeXT-7B, Retained Tokens=160, Token Retention Ratio=↓ 94.4%2026.06 | 53.6 | |
| VisionZipBackbone=LLaVA-NeXT-7B, Retained Tokens=160, Token Retention Ratio=↓ 94.4%2026.06 | 52.7 | |
| ApETBackbone=LLaVA-NeXT-7B, Retained Tokens=160, Token Retention Ratio=↓ 94.4%2026.06 | 52.3 |