---
license: apache-2.0
base_model: Qwen/Qwen3-VL-8B-Instruct
tags:
  - video-quality
  - reward-model
  - defect-detection
  - qwen3-vl
  - grpo
language:
  - en
pipeline_tag: text-generation
---

# DefectVideoReward (Qwen3-VL-8B, GRPO step800)

A video defect detection and quality scoring reward model, fine-tuned from Qwen3-VL-8B-Instruct using two-stage training:

1. **SFT**: Supervised fine-tuning on video defect annotations
2. **GRPO**: Group Relative Policy Optimization for 800 steps on pairwise video preference data

## Task

Given a text prompt and an AI-generated video, the model:
1. Identifies visible defects (artifacts, motion issues, misalignment, etc.)
2. Assigns an overall quality score (1-10)

## Input/Output Format

**Input**: System prompt + user message with video and text prompt

**Output**: JSON with defects and score
```json
{"defects": [{"issue": "...", "weight": 1|2|3}, ...], "score": 7}
```

## Usage

```python
from transformers import Qwen3VLForConditionalGeneration, AutoProcessor

model = Qwen3VLForConditionalGeneration.from_pretrained(
    "CaoruiLi/DefectVideoReward", torch_dtype="bfloat16", device_map="auto")
processor = AutoProcessor.from_pretrained("CaoruiLi/DefectVideoReward")
```

## Training Details

- **Base model**: Qwen/Qwen3-VL-8B-Instruct
- **SFT data**: Video defect annotations with expert-labeled defect lists
- **GRPO data**: 400 text prompts × pairwise video comparisons from VideoGen-RewardBench
- **GRPO steps**: 800 (best checkpoint by validation accuracy)
- **KL coefficient**: 0.01