EditReward MiMo VL 7B SFT 2508

--- license: apache-2.0 language: - en base_model: - XiaomiMiMo/MiMo-VL-7B-SFT-2508 base_model_relation: finetune datasets: - TIGER-Lab/EditReward-Data metrics: - accuracy pipeline_tag: image-to-text library_name: transformers tags: - editing - reward --- <p align="center" width="100%"> <img src="https://github.com/TIGER-AI-Lab/EditReward/raw/main/assets/logo.png" width="50%"> </p> <div align="center"> # EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing [](https://tiger-ai-lab.github.io/EditReward/) [](https://arxiv.org/abs/2509.26346) [](https://huggingface.co/papers/2509.26346) [](https://huggingface.co/collections/TIGER-Lab/editreward-68ddf026ef9eb1510458abc6) [](https://huggingface.co/datasets/TIGER-Lab/EditReward-Data) [](https://huggingface.co/datasets/TIGER-Lab/EditReward-Bench) </div> This repository contains the official implementation of the paper [EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing](https://huggingface.co/papers/2509.26346). ## 📖 Introduction We introduce **EditReward**, a human-aligned reward model powered by a high-quality dataset for instruction-guided image editing. **EditReward** is trained with **EditReward-Data**, a large-scale, high-fidelity preference dataset comprising over 200K manually annotated preference pairs. This dataset covers diverse edits produced by seven state-of-the-art models across twelve distinct sources, ensuring high alignment with human judgment. **EditReward** demonstrates superior alignment with human preferences in instruction-guided image editing tasks, achieving state-of-the-art human correlation on established benchmarks like GenAI-Bench, AURORA-Bench, ImagenHub, and our new **EditReward-Bench**. <p align="center"> <img src="https://raw.githubusercontent.com/TIGER-AI-Lab/EditReward/refs/heads/main/assets/pipeline.png" alt="Teaser" width="900"/> </p> ## 🚀 Quick Start To use the EditReward model for inference, follow these steps. For more details, including installation...

Source context: 44 downloads · 1 likes · Pipeline image-to-text · Library transformers · Repo TIGER-Lab/EditReward-MiMo-VL-7B-SFT-2508