arXiv Computer Vision August 25, 2026 By Qichao Ma, Jikang Cheng, Ling Liang, Zhaofei Yu, Tiejun Huang, Renye Yan

Can We Perform Online RL for Image Editing without Editing Rewards?

Read the original on arXiv Computer Vision →

The Flow has not summarised this story yet — read it at arXiv Computer Vision.

arXiv Machine Learning

Jun 29

Qwen-Image-2.0-RL Technical Report

arXiv:2606. 27608v1 Announce Type: cross Abstract: We present Qwen-Image-2.

By Yixian Xu, Kaiyuan Gao, Yuxiang Chen, Yilei Chen, Zecheng Tang, Zihao Liu, Zikai Zhou, Deqing Li, Hao Meng, Kuan Cao, Jiahao Li, Jie Zhang, Liang Peng, Lihan Jiang, Ningyuan Tang, Shengming Yin, Tianhe Wu, Xiaoyue Chen, Yan Shu, Yanran Zhang, Yi Wang, Yu Wu, Yujia Wu, Zekai Zhang, Zhendong Wang, Xiao Xu, Kun Yan, Chenfei Wu

llms diffusion reinforcement-learning fine-tuning efficiency multimodal safety

Hugging Face Trending Papers

Jun 1

MT-EditFlow: Reinforcement Learning for Multi-Turn Image Editing with Flow Matching

Recent breakthroughs in instruction-based image editing have captured significant attention, as models are now capable of handling real-world editing demands with the practicality required by everyday users. However, editing models trained primarily for single-turn edits often break down in multi-turn editing--the natural interactive setting where a user iteratively refines an image based on the model's own previous outputs.

diffusion reinforcement-learning multimodal benchmarks safety

arXiv AI

Jun 18

ProductConsistency: Improving Product Identity Preservation in Instruction-Based Image Editing via SFT and RL

arXiv:2606. 19103v1 Announce Type: cross Abstract: Recent advances in instruction-based image editing have enabled models to perform complex visual edits from natural language instructions.

By Mukund Khanna, Raj Singh Yadav, Kunal Singh

computer-vision reinforcement-learning fine-tuning benchmarks

arXiv AI

Jun 6

Edit-R2: Context-Aware Reinforcement Learning for Multi-Turn Image Editing

arXiv:2606. 05950v1 Announce Type: new Abstract: Text-guided image editing has advanced rapidly with diffusion models and unified multimodal foundation models.

By Yuxiao Ye, Haoran He, Fangyuan Kong, Xintao Wang, Pengfei Wan, Kun Gai, Ling Pan

diffusion reinforcement-learning multimodal benchmarks

arXiv AI

Jun 16

Efficient Reinforcement for Visual-Textual Thinking with Discrete Diffusion Model

arXiv:2606. 14792v1 Announce Type: cross Abstract: RL-based post-training has been widely adopted to enable interleaved visual and textual reasoning in unified multimodal models capable of both text and image generation.

By Yoonjeon Kim, Yuhta Takida, Chieh-Hsin Lai, Eunho Yang, Yuki Mitsufuji

diffusion reinforcement-learning multimodal

arXiv AI

6d ago

DARS: Dual-Level Credit Assignment RL with Structured Reasoning for Instruction-Based Image Editing

arXiv:2608. 20161v1 Announce Type: new Abstract: Instruction-based image editing uses a planner-renderer pipeline: a vision-language model (VLM) first converts the instruction into an edit plan, and a diffusion model then executes that plan.

By Haoxiang Cao, Jiajiong Cao, Xuanpu Zhang, Changqian Yu, Chaoqun Wang

llms diffusion reinforcement-learning multimodal benchmarks

One email a morning, machine-written

Related stories

Qwen-Image-2.0-RL Technical Report

MT-EditFlow: Reinforcement Learning for Multi-Turn Image Editing with Flow Matching

ProductConsistency: Improving Product Identity Preservation in Instruction-Based Image Editing via SFT and RL

Edit-R2: Context-Aware Reinforcement Learning for Multi-Turn Image Editing

Efficient Reinforcement for Visual-Textual Thinking with Discrete Diffusion Model

DARS: Dual-Level Credit Assignment RL with Structured Reasoning for Instruction-Based Image Editing