---
title: VisionReward-Video
canonical_url: "https://www.modelscope.cn/models/ZhipuAI/VisionReward-Video"
md_url: "https://www.modelscope.cn/models/ZhipuAI/VisionReward-Video.md"
repository: ZhipuAI/VisionReward-Video
last_updated: 2026-01-20
license: other
pipeline_tag: text-generation
tasks:
  - text-generation
architectures:
  - CogVLMVideoForCausalLM
parameters: 12.5B
tensor_type:
  - BF16
library_name:
  - safetensors
language:
  - en
downloads: 539
stars: 0
tags:
  - chat
  - cogvlm2
  - cogvlm--video
---

# VisionReward-Video

> VisionReward-Video - ZhipuAI 在 ModelScope 开源的模型。Introduction We present VisionReward, a general strategy to aligning visual generation models——both image and video generation——with human preferences through a fine-grainedand multi-dimensional framework. We…

ZhipuAI/VisionReward-Video 是 ModelScope 魔搭社区上的 12.5B 参数text-generation模型，采用 other 许可。

- **Repository**: ZhipuAI/VisionReward-Video
- **License**: other
- **Tasks**: text-generation
- **Parameters**: 12.5B
- **Tags**: chat, cogvlm2, cogvlm--video
- **Downloads**: 539
- **Stars**: 0
- **Last updated**: 2026-01-20

Source: https://www.modelscope.cn/models/ZhipuAI/VisionReward-Video

---

# VisionReward-Video

## Introduction
We present VisionReward, a general strategy to aligning visual generation models——both image and video generation——with human preferences through a fine-grainedand multi-dimensional framework. We decompose human preferences in images and videos into multiple dimensions,each represented by a series of judgment questions, linearly weighted and summed to an interpretable and accuratescore. To address the challenges of video quality assess-ment, we systematically analyze various dynamic features of videos, which helps VisionReward surpass VideoScore by 17.2% and achieve top performance for video preference prediction.
Here, we present the model of VisionReward-Video.

## Using this model
You can quickly install the Python package dependencies and run model inference in our [github](https://github.com/THUDM/VisionReward).