UniGen-1.5：通过强化学习中的奖励统一增强图像生成与编辑
UniGen-1.5: Enhancing Image Generation and Editing through Reward Unification in RL
用共享奖励模型把图像生成与编辑的 RL 训练统一起来，并先做轻量编辑指令对齐再上 RL，这套「先对齐指令、再统一奖励」的流程可直接迁移到其他统一生成/编辑模型的训练中。
原文依据 we propose a unified Reinforcement Learning (RL) strategy that improves both image generation and image editing jointly via shared reward models
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出 UniGen-1.5，一个用于高级图像理解、生成与编辑的统一多模态大语言模型（MLLM）。在 UniGen 的基础上，我们全面增强了模型架构与训练流程，以强化图像理解与生成能力，同时解锁强大的图像编辑能力。特别地，我们提出一种统一的强化学习（RL）策略，通过共享的奖励模型同时提升图像生成与图像编辑。为进一步提升图像编辑性能，我们提出一个轻量的编辑指令对齐阶段，显著改善编辑指令理解，而这对于 RL 训练的成功至关重要。实验结果表明，UniGen-1.5 展现出具有竞争力的理解与生成性能。具体而言，UniGen-1.5 在 GenEval 与 ImgEdit 基准上分别取得 0.89 和 4.31 的总体得分，超越了 BAGEL 等最优模型，并达到与 GPT-Image-1 等专有模型相当的水平。
英文原文摘要 1051 字符
We present UniGen-1.5, a unified multimodal large language model (MLLM) for advanced image understanding, generation and editing. Building upon UniGen, we comprehensively enhance the model architecture and training pipeline to strengthen the image understanding and generation capabilities while unlocking strong image editing ability. Especially, we propose a unified Reinforcement Learning (RL) strategy that improves both image generation and image editing jointly via shared reward models. To further enhance image editing performance, we propose a light Edit Instruction Alignment stage that significantly improves the editing instruction comprehension that is essential for the success of the RL training. Experimental results show that UniGen-1.5 demonstrates competitive understanding and generation performance. Specifically, UniGen-1.5 achieves 0.89 and 4.31 overall scores on GenEval and ImgEdit benchmarks that surpass the state-of-the-art models such as BAGEL and reaching performance comparable to proprietary models such as GPT-Image-1.