图像生成

ReasonEdit: Towards Reasoning-Enhanced Image Editing Models

ReasonEdit: 向推理增强的图像编辑模型迈进

Fukun Yin, Shiyu Liu, Yucheng Han, Zhibo Wang, Peng Xing, Rui Wang, Wei Cheng, Yingming Wang, Aojie Li, Zixin Yin, Pengtao Chen, Xiangyu Zhang, Daxin Jiang, Xianfang Zeng, Gang Yu

专题命中 图像编辑 ：image editing(title,abstract)；diffusion(abstract)；分类 cs.CV

AI总结 ReasonEdit通过引入思考和反思机制，提升图像编辑模型的推理能力，实现更准确的编辑效果。

Comments code: https://github.com/stepfun-ai/Step1X-Edit

TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models

TUNA: 降低统一视觉表示以适应原生统一多模态模型

Zhiheng Liu, Weiming Ren, Haozhe Liu, Zijian Zhou, Shoufa Chen, Haonan Qiu, Xiaoke Huang, Zhaochong An, Fanny Yang, Aditya Patel, Viktar Atliha, Tony Ng, Xiao Han, Chuyan Zhu, Chenyang Zhang, Ding Liu, Juan-Manuel Perez-Rua, Sen He, Jürgen Schmidhuber, Wenhu Chen, Ping Luo, Wei Liu, Tao Xiang, Jonas Schult, Yuren Cong

机构 * Meta BizAI ； University of Waterloo（滑铁卢大学） 纠错

专题命中 图像编辑 ：image editing(abstract)；分类 cs.CV

AI总结 TUNA通过统一视觉表示提升多模态模型的性能，实现端到端理解和生成任务的高效处理。

Comments Project page: https://tuna-ai.org/