|
|
--- |
|
|
datasets: none |
|
|
library_name: transformers |
|
|
licence: license |
|
|
license: apache-2.0 |
|
|
language: |
|
|
- en |
|
|
base_model: |
|
|
- Qwen/Qwen2.5-VL-7B-Instruct |
|
|
pipeline_tag: video-text-to-text |
|
|
tags: |
|
|
- Video-LLMs |
|
|
- Long-Reasoning-Video-Model |
|
|
- Video-R1 |
|
|
--- |
|
|
<a href="https://arxiv.org/abs/2505.19000" target="_blank"> |
|
|
<img alt="arXiv" src="https://img.shields.io/badge/arXiv-VerIPO-red?logo=arxiv" height="20" /> |
|
|
</a> |
|
|
<a href="https://github.com/HITsz-TMG/VerIPO" style="display: inline-block; margin-right: 10px;"> |
|
|
<img alt="GitHub Code" src="https://img.shields.io/badge/Code-VerIPO-white?&logo=github&logoColor=white" /> |
|
|
</a> |
|
|
|
|
|
# VerIPO: Long Reasoning Video-R1 Model with Iterative Policy Optimization |
|
|
|
|
|
VerIPO is a fine-tuned version of [Qwen2.5-VL](https://github.com/QwenLM/Qwen2.5-VL). |
|
|
It has been trained using [OpenRLHF](https://github.com/OpenRLHF/OpenRLHF). |
|
|
|
|
|
## Quick start |
|
|
|
|
|
```python |
|
|
from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor |
|
|
from qwen_vl_utils import process_vision_info |
|
|
|
|
|
model = Qwen2_5_VLForConditionalGeneration.from_pretrained( |
|
|
"Uni-MoE/VerIPO-7B-v1.0", |
|
|
torch_dtype=torch.bfloat16, |
|
|
attn_implementation="flash_attention_2", |
|
|
device_map="auto", |
|
|
) |
|
|
processor = AutoProcessor.from_pretrained("Uni-MoE/VerIPO-7B-v1.0") |
|
|
messages = [ |
|
|
{ |
|
|
"role": "user", |
|
|
"content": [ |
|
|
{ |
|
|
"type": "video", |
|
|
"video": "file:///path/to/video1.mp4", |
|
|
"max_pixels": 128*28*28, |
|
|
"max_frames": 128, |
|
|
"fps": 2.0 |
|
|
}, |
|
|
{"type": "text", "text": "Describe this video."}, |
|
|
], |
|
|
} |
|
|
] |
|
|
text = processor.apply_chat_template( |
|
|
messages, tokenize=False, add_generation_prompt=True |
|
|
) |
|
|
image_inputs, video_inputs, video_kwargs = process_vision_info(messages, return_video_kwargs=True) |
|
|
inputs = processor( |
|
|
text=[text], |
|
|
images=image_inputs, |
|
|
videos=video_inputs, |
|
|
padding=True, |
|
|
return_tensors="pt", |
|
|
**video_kwargs, |
|
|
) |
|
|
inputs = inputs.to(model.device) |
|
|
|
|
|
# Inference: Generation of the output |
|
|
generated_ids = model.generate(**inputs, max_new_tokens=4096, temperature=1e-6, repetition_penalty=1.05) |
|
|
generated_ids_trimmed = [ |
|
|
out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids) |
|
|
] |
|
|
output_text = processor.batch_decode( |
|
|
generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False |
|
|
) |
|
|
print(output_text) |
|
|
``` |
|
|
|
|
|
## Experimental Result |
|
|
|
|
|
| Model | Params | VSI-Bench | Video-MMMU | MMU (mc) | TOMATO | LVBench | Video-MME (w/o sub) | |
|
|
|---------------------|----------|-----------------|------------|----------|--------|--------------------------|---------| |
|
|
| GPT-4o [64] | - | 34.0 | 61.2 | - | 37.7 | 48.9 | 71.9 | |
|
|
| Gemini 1.5 Pro [59] | - | 45.4 | 53.8 | - | 36.1 | 33.1 | 75.0 | |
|
|
| mPLUG-Owl3 [83] | 7B | - | 42.0 | - | - | 43.5 | 53.5 | |
|
|
| LongVa [89] | 7B | 29.2 | 23.9 | - | - | - | 52.6 | |
|
|
| LLaVA-Video [91] | 7B | 35.6 | 36.1 | - | - | - | 63.3 | |
|
|
| LLaVA-OneVision [24]| 7B | 32.4 | 33.8 | 49.2 | - | - | 58.2 | |
|
|
| VideoLLaMA2 [9] | 7B | - | - | 44.8 | - | - | 47.9 | |
|
|
| VideoLLaMA3 [86] | 7B | - | 47.0 | - | - | 45.3 | 66.2 | |
|
|
| VILA-1.5 [33] | 8B | 28.9 | 20.8 | - | - | - | - | |
|
|
| InternV-L5 [33] | 40B | 31.2 | 34.0 | - | - | - | 60.1 | |
|
|
| InternVL2 [63] | 8B | 34.6 | 37.4 | 39.0 | 21.7 | - | 54.0 | |
|
|
| InternVL2 [63] | 40B | 36.0 | - | - | 29.0 | 39.6 | 61.2 | |
|
|
| InternVL2.5 [8] | 8B | - | - | - | - | - | 64.2 | |
|
|
| InternVL2.5 [8] | 26B | - | - | - | - | - | 66.9 | |
|
|
| InternVideo2.5 [70] | 8B | - | 43.0 | - | - | **46.4** | 65.1 | |
|
|
| Llama-3.2-Vision [62]| 11B | 20.6 | 41.8 | - | 21.5 | - | 46.0 | |
|
|
| Gemma-3-JT [60] | 12B | 32.4 | _57.2_ | - | 28.1 | - | 58.2 | |
|
|
| Kimi-VL [61] | 16B (A3B)| 37.4 | 52.6 | - | _31.7_ | - | **67.8**| |
|
|
| DeepSeek-VL2 [77] | 28B (A4B)| 21.7 | - | - | 27.2 | - | - | |
|
|
| Qwen2.5-VL [2] | 7B | 37.5 | 54.3 | **67.2** | 29.3 | 42.8 | 66.2 | |
|
|
| TinyLLaVA-Video-R1 [90]| 3B | - | - | 46.9 | - | - | 46.6 | |
|
|
| Qwen2.5-VL (thinking)[2]| 7B | _23.8_ | 46.8 | 63.0 | 25.8 | _35.2_ | 60.4 | |
|
|
| Video-R1 [18] | 7B | 35.8 | _52.3_ | 64.3 | - | - | 59.3 | |
|
|
| Kimi-VL-Thinking [61]| 16B (A3B)| 32.2 | - | 56.8 | 20.6 | 30.0 | - | |
|
|
| **VerlPo (Iteration1)** | 7B | **41.8** | 56.2 | 65.9 | _31.6_ | _41.5_ | 67.2 | |
|
|
| **VerlPo (Iteration2)** | 7B | 41.0 | **57.9** | **66.9** | 31.5 | 41.7 | 67.6 | |
|
|
| **VerlPo (Iteration3)** | 7B | _41.3_ | 56.8 | _66.7_ | **32.2** | 41.7 | 67.2 | |
|
|
|
|
|
|
|
|
# Citations |
|
|
|
|
|
```bibtex |
|
|
@article{li2025veripo, |
|
|
title={VerIPO: Cultivating Long Reasoning in Video-LLMs via Verifier-Gudied Iterative Policy Optimization}, |
|
|
author={Li, Yunxin and Chen, Xinyu and Li, Zitao and Liu, Zhenyu and Wang, Longyue and Luo, Wenhan and Hu, Baotian and Zhang, Min}, |
|
|
journal={arXiv preprint arXiv:2505.19000}, |
|
|
year={2025} |
|
|
} |
|
|
``` |
