---
library_name: transformers
base_model:
  - Qwen/Qwen3-VL-8B-Instruct
tags:
  - reward-model
  - super-resolution
  - qwen3-vl
  - grpo
  - academic-research
pipeline_tag: image-text-to-text
---

<h1 align="center">RefReward-SR</h1>
<h3 align="center">LR-Conditioned Reward Modeling for Preference-Aligned Super-Resolution</h3>

<div align="center">
  <a href="https://arxiv.org/abs/2603.24198"><img src="https://img.shields.io/badge/Paper%20(arXiv)-2603.24198-red?logo=arxiv"></a> &nbsp;
  <a href="https://huggingface.co/datasets/casyssong/RefSR-18K"><img src="https://img.shields.io/badge/Dataset-RefSR--18K-yellow?logo=huggingface"></a>
</div>

## Model Card

This repository contains the released **RefReward-SR** checkpoint only. The **SR-GRPO-LoRA** weights are released in a separate repository.

RefReward-SR is an LR-conditioned reward model for super-resolution. Given a low-resolution (LR) reference image and a super-resolved (HR) image, it assesses semantic consistency and perceptual plausibility using the LR image as a semantic anchor. The model supports direct scoring (`fast`) and reasoning-aware scoring (`think`).

## Checkpoint

| Item | Description | Size |
| --- | --- | --- |
| RefReward-SR (`checkpoint-1200`) | Qwen3-VL-8B LR-conditioned reward model fine-tuned with GRPO | 17G |

## Base Weight and Training Dataset

| Type | Resource | Role |
| --- | --- | --- |
| Base weight | [Qwen3-VL-8B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct) | Initialization for GRPO fine-tuning |
| Training dataset | [RefSR-18K](https://huggingface.co/datasets/casyssong/RefSR-18K) | LR-conditioned human preference data used for reward-model training |

## Upstream License Information

This model card does not declare a new license for the released checkpoint. The relevant upstream terms are:

| Resource | Upstream license |
| --- | --- |
| Qwen3-VL-8B-Instruct | [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0) |
| RefSR-18K | See the [RefSR-18K dataset card](https://huggingface.co/datasets/casyssong/RefSR-18K) |

Users are responsible for reviewing and complying with the applicable upstream terms.

## Citation

```bibtex
@article{song2026refreward,
  title={RefReward-SR: LR-Conditioned Reward Modeling for Preference-Aligned Super-Resolution},
  author={Song, Yushuai and Quan, Weize and Wang, Weining and Sun, Jiahui and Liu, Jing and Li, Meng and Yu, Pengbin and Chen, Zhentao and Shen, Wei and Yuan, Lunxi and Yan, Dong-ming},
  journal={arXiv preprint arXiv:2603.24198},
  year={2026}
}
```