Update README.md
Browse files
README.md
CHANGED
|
@@ -78,6 +78,38 @@ output_text = processor.batch_decode(
|
|
| 78 |
print(output_text)
|
| 79 |
```
|
| 80 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 81 |
|
| 82 |
# Citations
|
| 83 |
|
|
|
|
| 78 |
print(output_text)
|
| 79 |
```
|
| 80 |
|
| 81 |
+
## Experimental Result
|
| 82 |
+
|
| 83 |
+
| Model | Params | VSI-Bench | Video-MMMU | MMU (mc) | TOMATO | LVBench | Video-MME (w/o sub) |
|
| 84 |
+
|---------------------|----------|-----------------|------------|----------|--------|--------------------------|---------|
|
| 85 |
+
| GPT-4o [64] | - | 34.0 | 61.2 | - | 37.7 | 48.9 | 71.9 |
|
| 86 |
+
| Gemini 1.5 Pro [59] | - | 45.4 | 53.8 | - | 36.1 | 33.1 | 75.0 |
|
| 87 |
+
| mPLUG-Owl3 [83] | 7B | - | 42.0 | - | - | 43.5 | 53.5 |
|
| 88 |
+
| LongVa [89] | 7B | 29.2 | 23.9 | - | - | - | 52.6 |
|
| 89 |
+
| LLaVA-Video [91] | 7B | 35.6 | 36.1 | - | - | - | 63.3 |
|
| 90 |
+
| LLaVA-OneVision [24]| 7B | 32.4 | 33.8 | 49.2 | - | - | 58.2 |
|
| 91 |
+
| VideoLLaMA2 [9] | 7B | - | - | 44.8 | - | - | 47.9 |
|
| 92 |
+
| VideoLLaMA3 [86] | 7B | - | 47.0 | - | - | 45.3 | 66.2 |
|
| 93 |
+
| VILA-1.5 [33] | 8B | 28.9 | 20.8 | - | - | - | - |
|
| 94 |
+
| InternV-L5 [33] | 40B | 31.2 | 34.0 | - | - | - | 60.1 |
|
| 95 |
+
| InternVL2 [63] | 8B | 34.6 | 37.4 | 39.0 | 21.7 | - | 54.0 |
|
| 96 |
+
| InternVL2 [63] | 40B | 36.0 | - | - | 29.0 | 39.6 | 61.2 |
|
| 97 |
+
| InternVL2.5 [8] | 8B | - | - | - | - | - | 64.2 |
|
| 98 |
+
| InternVL2.5 [8] | 26B | - | - | - | - | - | 66.9 |
|
| 99 |
+
| InternVideo2.5 [70] | 8B | - | 43.0 | - | - | **46.4** | 65.1 |
|
| 100 |
+
| Llama-3.2-Vision [62]| 11B | 20.6 | 41.8 | - | 21.5 | - | 46.0 |
|
| 101 |
+
| Gemma-3-JT [60] | 12B | 32.4 | _57.2_ | - | 28.1 | - | 58.2 |
|
| 102 |
+
| Kimi-VL [61] | 16B (A3B)| 37.4 | 52.6 | - | _31.7_ | - | **67.8**|
|
| 103 |
+
| DeepSeek-VL2 [77] | 28B (A4B)| 21.7 | - | - | 27.2 | - | - |
|
| 104 |
+
| Qwen2.5-VL [2] | 7B | 37.5 | 54.3 | **67.2** | 29.3 | 42.8 | 66.2 |
|
| 105 |
+
| TinyLLaVA-Video-R1 [90]| 3B | - | - | 46.9 | - | - | 46.6 |
|
| 106 |
+
| Qwen2.5-VL (thinking)[2]| 7B | _23.8_ | 46.8 | 63.0 | 25.8 | _35.2_ | 60.4 |
|
| 107 |
+
| Video-R1 [18] | 7B | 35.8 | _52.3_ | 64.3 | - | - | 59.3 |
|
| 108 |
+
| Kimi-VL-Thinking [61]| 16B (A3B)| 32.2 | - | 56.8 | 20.6 | 30.0 | - |
|
| 109 |
+
| **VerlPo (Iteration1)** | 7B | **41.8** | 56.2 | 65.9 | _31.6_ | _41.5_ | 67.2 |
|
| 110 |
+
| **VerlPo (Iteration2)** | 7B | 41.0 | **57.9** | **66.9** | 31.5 | 41.7 | 67.6 |
|
| 111 |
+
| **VerlPo (Iteration3)** | 7B | _41.3_ | 56.8 | _66.7_ | **32.2** | 41.7 | 67.2 |
|
| 112 |
+
|
| 113 |
|
| 114 |
# Citations
|
| 115 |
|